本项目每月自动从 arXiv 获取最新的论文，基于关键词进行筛选。
点击 'Watch' 按钮可以接收每月自动推送的邮件通知。
本次更新执行命令
D:\a\MyAutoPapers\MyAutoPapers\target\release\my_auto_papers.exe --keywords=
efficient reinforcement learning/sample efficient reinforcement learning,
model-based reinforcement learning/world model,
offline reinforcement learning,
safe policy improvement,
object-centric world model/structured world model,
efficient vision transformer/mobile vit/lightweight vit,
efficient image classification/efficient object detection/efficient semantic segmentation,
efficient diffusion model/one-step diffusion/distillation diffusion,
efficient cpu inference/on-device inference/edge inference,
model quantization/low-bit quantization/binary neural network,
network pruning/sparse neural network/knowledge distillation,
tensor compilation/computation graph optimization/operator fusion,
SIMD/AVX-512/vectorized inference,
fast matrix multiplication/sparse matrix multiplication/cache-efficient,
linear attention/low-rank compression/Winograd convolution,
image super resolution/efficient super resolution,
video super resolution,
quantitative trading/algorithmic trading/reinforcement learning for trading,
stock prediction/portfolio optimization/financial time series forecasting,
neuroevolution/NEAT/evolutionary neural network,
neural architecture search/multi-objective neural architecture search,
open-ended learning/quality-diversity,
neuro-symbolic/neural symbolic reasoning,
meta-learning/continual learning/lifelong learning,
intrinsic motivation/curiosity-driven exploration,
learned optimizer/meta-gradient,
active inference/predictive coding
--exclude-keywords=multi-agent,multiagent --per-keyword-max-result=5
参数详解
- 关键词：
efficient reinforcement learning/sample efficient reinforcement learning,model-based reinforcement learning/world model,offline reinforcement learning,safe policy improvement,object-centric world model/structured world model,efficient vision transformer/mobile vit/lightweight vit,efficient image classification/efficient object detection/efficient semantic segmentation,efficient diffusion model/one-step diffusion/distillation diffusion,efficient cpu inference/on-device inference/edge inference,model quantization/low-bit quantization/binary neural network,network pruning/sparse neural network/knowledge distillation,tensor compilation/computation graph optimization/operator fusion,SIMD/AVX-512/vectorized inference,fast matrix multiplication/sparse matrix multiplication/cache-efficient,linear attention/low-rank compression/Winograd convolution,image super resolution/efficient super resolution,video super resolution,quantitative trading/algorithmic trading/reinforcement learning for trading,stock prediction/portfolio optimization/financial time series forecasting,neuroevolution/NEAT/evolutionary neural network,neural architecture search/multi-objective neural architecture search,open-ended learning/quality-diversity,neuro-symbolic/neural symbolic reasoning,meta-learning/continual learning/lifelong learning,intrinsic motivation/curiosity-driven exploration,learned optimizer/meta-gradient,active inference/predictive coding - 排除关键词：
multi-agent,multiagent - 每关键词最大结果：
5 - 目标领域：
cs,stat - 每关键词重试次数：
3
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Efficient Geothermal Well-Control Optimization via Diffusion-Surrogate Reinforcement Learning | 2026-08-28 | 展开Real-time decision-making for enhanced geothermal systems (EGS) is challenging because long-term production periods involve high-dimensional control spaces and a large number of time-consuming high-fidelity hydrothermal simulations. Reinforcement learning provides a natural framework for state-dependent sequential control, but direct policy training with numerical simulators is computationally expensive. To address this issue, we propose a diffusion-surrogate guided reinforcement learning framework for long-horizon EGS well-control optimization. The reservoir temperature and pressure fields are used as system states, while injection rates are selected as control actions. A learned surrogate environment is constructed using conditional diffusion models to predict the evolution of reservoir temperature and pressure fields and a separate reward model to estimate the corresponding economic return. The surrogate environment is then integrated with Proximal Policy Optimization (PPO) for efficient policy training. Experiments on a fractured EGS benchmark show that the diffusion surrogate can accurately reproduce reservoir-state evolution over multiple control stages. The resulting surrogate-assisted PPO policy achieves competitive well-control performance compared with direct simulator-based PPO and existing optimization methods, while substantially reducing the dependence on expensive high-fidelity simulations. These results demonstrate the potential of diffusion-based surrogate environments for efficient reinforcement learning in geothermal well-control optimization. |
| 2 | Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving | 2026-08-11 | 展开Sample-efficient reinforcement learning for autonomous driving is often limited by the trade-off between data efficiency and model bias. While world models reduce the reliance on costly environment interactions, policy optimization over learned dynamics remains sensitive to prediction errors. This paper proposes the Dreamer-SAC framework, which integrates a recurrent state-space world model with an off-policy soft actor-critic algorithm trained directly in latent space. The framework uses a combination of real interactions and short-horizon generated trajectories with n-step target estimation and multi-objective supervision. Evaluated in autonomous driving scenarios with objectives encompassing driving efficiency and safety, the proposed framework consistently outperforms representative reinforcement learning baselines, including DreamerV3, SAC, and PPO, while achieving improved performance with substantially fewer real environment interactions. Experiments reveal an inverted-U relationship between rollout horizon and policy performance, where short-horizon latent rollouts achieve the best trade-off between additional training signals and accumulated model bias. Furthermore, n-step target estimation demonstrates more effectiveness over one-step temporal-difference targets in exploiting predicted experience for value learning. |
| 3 | Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks | 2026-08-11 | 展开Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcement learning (RL) is a natural fit for this setting, but multi-turn on-policy rollouts create long contexts, while model-specific attention layers may require custom masks and learned sink normalization. We present SINKFLEX-RL, a modular training system for RL in dual-control tool-use environments. The system combines a Gymnasium-compatible environment wrapper, a VERL-style rollout dataflow, group-relative policy optimization without a separate value model, and a sink-aware FlexAttention path designed to preserve model-specific sink scaling under causal and sliding-window masks. In a preliminary Tau2Bench retail run, validation reward (mean@1) rises from 0.25 early in training to |
| 4 | A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning | 2026-08-08 | 展开Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning. Reward shaping addresses these limitations by supplementing the task reward with an auxiliary signal that can accelerate learning while, in the classical setting, the original objective remains the evaluation criterion. Established theory guarantees safety for fixed shaping signals: potential-based reward shaping preserves optimal policies when the auxiliary term is the discounted difference of a time-invariant potential. In contemporary reinforcement learning systems, however, both the learner and the information available for guidance evolve during training: value estimates improve, novelty diminishes, feedback shifts, and predictive models are refined. Adaptive reward mechanisms occur across exploration, Bayesian inference, human-in-the-loop learning, automated reward design, and foundation-model-based approaches. This study introduces a unified analytical framework for comparing dynamic reward shaping and neighbouring adaptive reward mechanisms. The proposed framework distinguishes parametric revision from state-dependent variation, separates additive shaping from reward replacement and reward-adjacent guidance, and organises existing methods along temporal, informational, and theoretical dimensions. Using this framework, twelve method families are comparatively analysed. The framework further highlights the conditions under which optimality guarantees survive contemporary deep reinforcement learning pipelines, replay buffers, bootstrapped critics, and reward normalisation, while exposing the unresolved relationship between adaptation rate and learner stability. |
| 5 | Gated Q-learning: Add Off-Policy Bias to Taste | 2026-07-31 | 展开Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge. For 30 years, practitioners have been limited to a binary choice: eliminate the bias at the cost of severely truncated eligibility traces (Watkins' Q( |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning | 2026-08-28 | 展开Complete your ad view and grab a 5-cent bonus! In incentivized advertising, a platform promises users a bonus before observing downstream ad revenue, encouraging them to click and complete ads. It must balance the incentive promised in advance against the revenue realized afterward: insufficient incentives forfeit monetization opportunities, whereas excessive incentives reduce net profit. Because current incentives may also shape user expectations and future engagement, incentive allocation is a sequential decision problem with delayed revenue, cost sensitivity, and carryover effects. Existing work has not studied decision-making algorithms for this setting. Auto-bidding assumes available ad opportunities, while targeted promotion optimizes incentives outside the ad monetization pipeline. We formulate the problem as an MDP and develop an offline model-based RL framework for cost-controllable sequential incentive allocation. It learns a world model of user feedback and ad revenue, then performs conservative policy optimization. An independent counterfactual scorer evaluates each learned policy on held-out logs, enabling pre-launch selection without costly online exposure. Experiments on large-scale industrial data and online A/B tests show that the scorer provides a stable offline signal. The deployment path from causal inference to offline RL and then Offline-MBRL further validates the framework: MB-IQL improves per-user net profit by 7.96% over TD3+BC, whereas reverting to plain IQL reduces it by 6.56% (both (p<0.0001)). |
| 2 | Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts | 2026-08-21 | 展开Heterogeneous multi-robot service systems must assign requests to compatible robots, construct feasible schedules, and adapt as new tasks arrive online. Historical data can help anticipate future demand, but relying too heavily on inaccurate predictions can degrade performance under distribution shifts. We develop a prediction-aware adaptive rollout framework for heterogeneous multi-robot task assignment with scheduled and real-time requests. The problem is formulated as a finite-horizon stochastic dynamic program incorporating robot-task compatibility, ordered service requirements, routing constraints, service windows, and end-of-horizon return requirements. The proposed policy evaluates current assignments using sampled future request scenarios while restricting immediate commitments to requests already observed. To enable online use, the framework combines pruned candidate controls, wait actions, and an interaction-aware base policy for efficient future-cost estimation. Robustness to forecast error is provided by adaptively reweighting predicted requests based on recent prediction mismatch and selectively re-optimizing assigned but unstarted requests. We also introduce a historical-data-driven procedure for selecting the heterogeneous fleet composition before deployment. In a case study using real nursing-task requests from hospital inpatient floors, the proposed approach achieves near-complete service and reduces serviced-request wait times relative to reactive, token-passing, prediction-positioning, and myopic greedy baselines, with the largest improvements in tail-delay metrics. |
| 3 | AlphaClifford: Efficient Clifford Synthesis and Transpilation with Model-based RL | 2026-08-19 | 展开Clifford circuits play a foundational role in quantum computing, particularly due to their importance in quantum error correction and fault-tolerant logical synthesis. While these circuits can be efficiently simulated and represented as symplectic matrices, standard synthesis methods-such as the Aaronson-Gottesman algorithm-often yield sub-optimal circuits with excessively high gate counts. In this work, we introduce AlphaClifford, a model-based Reinforcement Learning framework powered by Monte Carlo Tree Search, designed to efficiently synthesize Clifford circuits from the fundamental gate set composed of H, S, and CNOT. By modeling the state space through the algebraic properties of the symplectic group, AlphaClifford effectively explores this combinatorial space to minimize overall circuit cost. For unconstrained Clifford optimization, our approach achieves a consistent reduction in both total and two-qubit (CNOT) gate counts compared to state-of-the-art synthesis heuristics, despite operating with a strictly less expressive gate set. Furthermore, we demonstrate the broad applicability of our framework on two additional tasks: hardware-constrained Clifford transpilation, where we outperform existing RL-based compilers, and as a post-synthesis optimization component within a full Clifford+T logical synthesis pipeline. Our results underscore that model-based RL is highly effective at addressing the combinatorial complexities of quantum compilation, offering a scalable pathway to mitigate hardware constraints in both near-term and future fault-tolerant quantum devices. |
| 4 | Towards Zero-Shot Task Transfer with Neurosymbolic World Models | 2026-08-18 | 展开State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement by planning in a latent space, without assumptions on the structure of the underlying environment. While expressive, these models are generally task-dependent: they learn uninterpretable latent representations that are tied to the training task and thus hard to generalize to new tasks. In this work, we present a novel world model formulation where the reward prediction only depends on a subset of structured, symbolic components of the whole latent state. Decoupling observation reconstruction and reward prediction allows us to learn world models that can adapt zero-shot, i.e. without further environment interactions, to new reward functions defined over the same symbolic state space. We discuss the main advantages and challenges of learning these neurosymbolic world models and demonstrate the strong generalisation properties of our approach over purely neural methods. |
| 5 | Stable Multi-Step Rollouts via Uncertainty-Guided Hybrid Dynamics | 2026-08-17 | 展开Multi-step rollouts are essential for model-based reinforcement learning (RL) and predictive control, yet learned dynamics models often become unstable when recursively applied, leading to divergence and unreliable policy updates. This paper proposes a model-agnostic hybrid dynamics framework that blends a provably contracting nominal model with a flexible excursion model through an uncertainty-guided switching law. The switching signal is derived from calibrated epistemic uncertainty and activates only when the system leaves the nominal region, ensuring that each model operates within its reliability regime. Under clearly stated smoothness and boundedness assumptions, we show that the resulting hybrid predictor yields globally bounded recursive multi-step rollouts: trajectories remain Lyapunov-stable in the nominal region and exhibit at most affine growth during excursions. To illustrate the theory in practice, we instantiate the hybrid dynamics framework within a model-based RL scheme that uses real one-step transitions for value learning and hybrid rollouts for policy improvement. Experiments on a nonlinear Duffing oscillator demonstrate stable long-horizon prediction and improved cost-effort trade-offs relative to a stabilizing baseline. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry | 2026-08-31 | 展开Recent offline reinforcement learning (RL) studies report policies that outperform physician decisions on clinical outcomes. We conduct a systematic, partially crossed evaluation of five offline RL algorithm families and 14 reward designs in 44,894 post-2018 acute ischemic stroke patients from a nationwide registry (N = 129,033). Standard Fitted Q-Evaluation (FQE) yields an apparent policy-improvement estimate of +0.0069; adding an Early Neurological Deterioration penalty increases it to +0.0101. We identify reward-embedded confounding, in which a proxy terminal reward encodes baseline severity and prognosis as well as treatment efficacy. A 2 x 2 factorial analysis finds that terminal reward confounding accounts for 218.6% of the observed signal change, so its removal overshoots the null. After DML-inspired GBM reward residualization, the FQE estimate attenuates to +0.0033 (p = 0.132), and full deconfounding yields +0.0025 (p = 0.291). FQE-based diagnostics, T-learner analyses, and direct recurrence analyses converge away from a clinically meaningful aggregate improvement. A 1-year mRS factorial analysis replicates the attenuation. We provide an empirically motivated six-step evaluation checklist. NIHSS-stratified heterogeneity is hypothesis-generating for prospective trial design; hospital-level disagreement does not persist after full reward deconfounding. |
| 2 | Simple Actors and Deep Critics for Scalable Reinforcement Learning | 2026-08-27 | 展开Recent progress in offline reinforcement learning (RL) has been driven by expressive generative actors such as diffusion and flow-matching policies, which capture multimodal behavior in offline datasets. However, these actors require multiple denoising or integration steps per action and thus incur substantial overhead at every decision in deployment. In this work, we revisit where capacity should be invested in an offline actor--critic method. Since the critic is used only during training and is discarded at deployment while the actor runs at every decision step, allocating capacity to the critic rather than the actor is more favorable for inference-time efficiency. However, scaling MLP critics in offline RL is known to introduce several distinct instabilities that have, in practice, kept critics shallow. We identify three distinct failure modes that arise when critics are deepened in offline RL---optimization, bootstrap-noise amplification, and value-range drift---and address each with a corresponding ingredient: a residual MLP backbone, n-step bootstrap targets, and a categorical cross-entropy loss. Combining these ingredients with a lightweight deterministic actor, we propose LAC (Light Actor, deep Critic). On OGBench, LAC matches the strongest diffusion- and flow-matching baselines while achieving up to 4x lower inference latency, comparable to one-step distilled policies without distillation. Its critic recipe also transfers across actor parametrizations. |
| 3 | Soft Fitted Q-Iteration without Bellman Completeness: Occupancy Reweighting and Temperature Annealing | 2025-12-30 | 展开Fitted (Q)-iteration (FQI) is a standard regression-based method for optimal control in offline reinforcement learning, but its stability under function approximation often relies on Bellman completeness, which requires Bellman images of the fitted class to remain in the class. We study Kullback--Leibler (KL)-regularized, or soft, FQI relative to a fixed reference policy without this assumption. Our key insight is that soft control locally inherits the contraction of policy evaluation in a discounted-occupancy norm. At the soft-optimal fixed point, the linearization of the soft Bellman operator is exactly the Bellman operator for the soft-optimal policy, which contracts in its discounted-occupancy norm; projection in the same norm preserves this contraction. Standard soft FQI instead projects under the offline state-action distribution and need not preserve this property. Motivated by this observation, we propose \emph{occupancy-reweighted soft FQI}, which retains standard Bellman targets and least-squares updates while reweighting regressions by discounted-occupancy ratios induced by the current soft policy. Under (Q)-function realizability and local regularity, we establish local contraction and finite-sample convergence with estimated ratios, without Bellman completeness. We then use temperature annealing to convert the local result into global convergence from arbitrary initialization: sufficiently high temperature provides a globally contractive starting regime, while gradual cooling connects successive local contraction regions to any prescribed positive target temperature. Under an action-gap margin condition, switching at a fixed positive temperature to hard FQI with refreshed occupancy weights also yields population and finite-sample convergence to the unregularized optimum. |
| 4 | RADAR: Accelerate Large Language Model Inference With RL-Based Dynamic Draft Trees | 2025-12-16 | 展开Inference with modern Large Language Models (LLMs) is expensive and slow, and speculative sampling has emerged as an effective solution to this problem. However, the number of calls to the draft model for generating candidate tokens in speculative sampling is a preset hyperparameter, lacking flexibility. To generate and utilize the candidate tokens more effectively, we propose RADAR, a novel speculative sampling method with RL-based dynamic draft trees. RADAR formulates the draft tree generation process as a Markov Decision Process (MDP) and employs offline reinforcement learning to train a prediction model, which enables real-time decisions on calls to the draft model, reducing redundant computations and further accelerating inference. Evaluations across three LLMs and four tasks show that RADAR achieves a speedup of 3.17x-4.82x over the auto-regressive decoding baseline. The code is available at https://github.com/minaduki-sora/RADAR. |
| 5 | Amortizing intractable inference in diffusion models for vision, language, and control | 2024-05-31 | 展开Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data, |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Adaptive Policy Portfolios for Robust Markov Decision Processes | 2026-08-18 | 展开Robust Markov decision processes optimize one policy against a set of plausible transition functions. This can be conservative when the unknown dynamics are fixed and become partially identifiable after deployment. We study adaptive policy portfolios: finite sets of memoryless randomized policies synthesized offline and paired with a lightweight online selector. Robust regret is a natural measure of portfolio quality: for each plausible environment, it measures the loss of the best portfolio member relative to the policy that would have been optimal had that environment been known. Related regret objectives were studied by Ghavamzadeh et al. (2016) with an emphasis on approximations and relaxations for safe policy improvement. We give a complexity-theoretic account of portfolio certification and synthesis. Certifying a given portfolio is |
| 2 | Robust Probabilistic Shielding for Safe Offline Reinforcement Learning | 2026-05-11 | 展开In offline reinforcement learning (RL), we learn policies from fixed datasets without environment interaction. The major challenges are to provide guarantees on the (1) performance and (2) safety of the resulting policy. A technique called safe policy improvement (SPI) provides a performance guarantee: with high probability, the new policy outperforms a given baseline policy, which is assumed to be safe. Orthogonally, in the context of safe RL, a shield provides a safety guarantee by restricting the action space to those actions that are provably safe with respect to a given safety-relevant model. We integrate these paradigms by extending shielding to offline RL, relying solely on the available dataset and knowledge of safe and unsafe states. Then, we shield the policy improvement steps, guaranteeing, with high probability, a safe policy. Experimental results demonstrate that shielded SPI outperforms its unshielded counterpart, improving both average and worst-case performance, particularly in low-data regimes. |
| 3 | FORLER: Federated Offline Reinforcement Learning with Q-Ensemble and Actor Rectification | 2026-02-02 | 展开In Internet-of-Things systems, federated learning has advanced online reinforcement learning (RL) by enabling parallel policy training without sharing raw data. However, interacting with real environments online can be risky and costly, motivating offline federated RL (FRL), where local devices learn from fixed datasets. Despite its promise, offline FRL may break down under low-quality, heterogeneous data. Offline RL tends to get stuck in local optima, and in FRL, one device's suboptimal policy can degrade the aggregated model, i.e., policy pollution. We present FORLER, combining Q-ensemble aggregation on the server with actor rectification on devices. The server robustly merges device Q-functions to curb policy pollution and shift heavy computation off resource-constrained hardware without compromising privacy. Locally, actor rectification enriches policy gradients via a zeroth-order search for high-Q actions plus a bespoke regularizer that nudges the policy toward them. A |
| 4 | Policy Learning with Abstention | 2025-10-22 | 展开Policy learning algorithms are widely used in areas such as personalized medicine and advertising to develop individualized treatment regimes. However, most methods force a decision even when predictions are uncertain, which is risky in high-stakes settings. We study policy learning with abstention, where a policy may defer to a safe default or an expert. When a policy abstains, it receives a small additive reward on top of the value of a random guess. We propose a two-stage learner that first identifies a set of near-optimal policies and then constructs an abstention rule from their disagreements. We establish fast O(1/n)-type regret guarantees when propensities are known, and extend these guarantees to the unknown-propensity case via a doubly robust (DR) objective. We further show that abstention is a versatile tool with direct applications to other core problems in policy learning: it yields improved guarantees under margin conditions without the common realizability assumption, connects to distributionally robust policy learning by hedging against small data shifts, and supports safe policy improvement by ensuring improvement over a baseline policy with high probability. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Graph-Operator World Models for Morphology-Parameter Generalization in Continuous Control | 2026-08-21 | 展开World models for continuous control are commonly trained for a fixed physical system and can degrade when known morphology parameters such as link lengths, masses, damping, and actuation change. Existing approaches often provide these parameters as conditioning information, but leave unspecified which part of the learned transition should remain reusable and which part should change with morphology. We propose Graph-Operator World Models (GraphOp-WM), a structured world model for generalization across unseen morphology parameters within related articulated robot families. GraphOp-WM represents bodies and their kinematic relations as an attributed graph and factorizes each transition into a morphology-independent local dynamics basis and a morphology-conditioned structured operator. The operator combines node-local modulation, kinematic-tree coupling, and a low-rank global correction, while architectural information separation, basis normalization, and paired-morphology supervision encourage static morphology dependence to be carried by the operator pathway. Graph-level readout and edge-wise action representations provide a compatible interface for reward, value, and TD-MPC-style planning. We further define controlled MuJoCo parameter splits covering interpolation, extrapolation, and held-out compositions of link geometry, mass, damping, and actuation parameters in Hopper, Walker2d, and HalfCheetah. |
| 2 | Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics | 2026-08-05 | 展开World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing world models represent these states using classical vectors, probability distributions, recurrent hidden states, or transformer activations. In this paper, we introduce Quantum-Structured World Models (QSWMs), a quantum-inspired framework for predictive world modeling with structured latent states, latent transition operators, and measurement-inspired decoding maps. We study whether mathematical structures inspired by quantum theory, such as complex-valued representations and density-matrix-like latents, provide useful inductive biases for world modeling. We establish three foundational properties: classical inclusion, predictive sufficiency, and structured compactness. We then instantiate complex-valued and density-matrix-like QSWM variants and evaluate them on elementary cellular automata against strong classical baselines. Results show promising local predictive potential for complex-valued QSWMs, while also revealing limitations in long-horizon rollout, density-matrix variants |
| 3 | DreamWAM: Beyond RGB Future Prediction for World Action Models | 2026-08-05 | 展开World Action Models (WAMs) learn action-relevant representations by predicting how the observed world will evolve. Most existing WAMs define this future in RGB space, where task-relevant state transitions are entangled with nuisance variations in texture, illumination, background, and viewpoint. We argue that WAMs should explicitly predict action-relevant future state rather than relying on RGB prediction alone. We introduce DreamWAM, which reformulates future prediction as structured world modeling beyond RGB, representing future states through complementary views of appearance, motion, geometry, and semantics. During training, DreamWAM combines joint latent denoising of RGB and motion with lightweight gated residual branches for geometry and semantics. Shared attention between VideoDiT and ActionDiT allows the action branch to learn from these future-state predictions, while all beyond-RGB supervision branches are disabled at inference and deployment remains RGB-only. Across both no-rollout and joint video-action inference, DreamWAM consistently improves the matched RGB-only baselines on LIBERO, from 97.30% to 98.40% and from 98.00% to 98.90%, respectively. The gains become larger under unseen LIBERO-Plus perturbations, from 51.36% to 63.44% and from 69.16% to 75.47%. The same robustness extends to real-world manipulation, where DreamWAM attains an average success rate of 74.4% across unseen changes in lighting, background, and object layout, compared with 55.6% for Fast-WAM-Joint. These results show that robust world-action learning depends not only on predicting the future, but on representing it in a form that matters for action. The code and models are publicly released at https://github.com/hustvl/DreamWAM. |
| 4 | Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling | 2026-07-05 | 展开Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making. However, existing approaches often rely on high-dimensional latent spaces or generic visual embeddings that retain many factors irrelevant to control, limiting efficiency and generalization across tasks. To this end, we study how agents can learn world models with representations that are task-specific, minimal, and sufficient for decision-making. We achieve this via a closed-loop synergy between the agent and the world model, in which structured world-model learning distills task-sufficient representations from informative interaction data. On the agent side, agents actively probe the environment to collect informative trajectories that expose task-relevant latent factors, guided by an adaptive curriculum. On the world-model side, we learn structured representations over observations to distill compact, task-sufficient latent states from the collected interaction data. This synergy enables the empirical recovery of task-sufficient latent representations that capture all control-relevant factors. Leveraging these representations, the resulting policies achieve improved sample efficiency and generalization, including generalization across skills, object-skill compositions, and previously unseen tasks on standard continuous-control and robotic-manipulation benchmarks. |
| 5 | Logic-Guided Socially-aware Robot Navigation World Model | 2025-10-27 | 展开Social robot navigation increasingly relies on large language models for reasoning, path planning, and enabling movement in dynamic human spaces. However, relying solely on LLMs for planning often leads to unpredictable and unsafe behaviors, especially in dynamic human spaces, due to limited physical grounding and weak logical consistency. In this work, we introduce NaviWM, a socially-aware robot Navigation World Model that augments LLM reasoning with a structured world model and a logic-driven chain-of-thought process. NaviWM consists of two main components: (1) a spatial-temporal world model that captures the positions, velocities, and activities of agents in the environment, and (2) a deductive reasoning module that guides LLMs through a multi-step, logic-based inference process. This integration enables the robot to generate navigation decisions that are both socially compliant and physically safe, under well-defined constraints such as personal space, collision avoidance, and timing. Unlike previous methods based on prompting or fine-tuning, NaviWM encodes social norms as first-order logic, enabling interpretable and verifiable reasoning. Experiments show that NaviWM improves success rates and reduces social violations, particularly in crowded environments. These results demonstrate the benefit of combining formal reasoning with LLMs for robust social navigation. Additional experimental details and demo videos for this work can be found at: https://sites.google.com/view/NaviWM. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving | 2026-06-24 | 展开Large language models (LLMs) can improve autonomous driving planning but are costly to query online, and existing fast-slow planners often rely on hand-designed triggering rules that either over-call the slow system or call it at the wrong times. We formulate slow-system invocation as a resource-aware sequential decision problem and propose the Adaptive Slow-System Control Gate (ASSCG), which makes frame-level Query/Cache/Drop decisions to refresh, reuse, or suppress slow guidance. ASSCG uses an RWKV backbone for efficient long-horizon gating and is trained with supervised fine-tuning followed by GRPO-style compute-aware reinforcement fine-tuning. We apply ASSCG to two different fast-slow architectures: (i) AsyncDriver on nuPlan Hard20 closed-loop evaluation, where ASSCG improves score to 67.28 (+2.28) while reducing average end-to-end inference latency by 60%; and (ii) a RecogDrive-based dual system that we build by replacing its original VLM-2B module with a lightweight ViT-based fast planner and adding an LLM slow planner, evaluated on NAVSIM, where ASSCG achieves 91.4 PDMS (+0.6) and increases average speed by 25%. The project page, including video visualizations and additional results, is available at https://williamxuanyu.github.io/asscg/. |
| 2 | RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following | 2026-05-25 | 展开Embodied instruction following (EIF) requires agents to understand and execute complex natural language commands within interactive 3D environments. Despite recent advances, existing methods often fail in long-horizon planning and handling irreversible state changes, resulting in low task success rates. To address these challenges, we introduce RePlan-Bot, a novel EIF agent that performs multi-level, continuous replanning throughout task execution. RePlan-Bot integrates a high-level LLM-based auditor for dynamic sub-goal adjustments guided by environmental feedback, a commonsense-guided search mechanism based on a multi-layered instance map for precise and structured object localization, and a lightweight ViT-based corrector to preemptively fix risky low-level actions. Evaluated on the ALFRED benchmark, RePlan-Bot achieves state-of-the-art performance in both seen and unseen environments, demonstrating superior adaptability and reliability. |
| 3 | A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors | 2026-03-22 | 展开The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal action localization techniques often struggle to balance accuracy with computational efficiency. In this work, we develop and evaluate a temporal action localization framework tailored for driver monitoring scenarios, particularly suitable for periodic inspection settings such as transportation safety checkpoints or fleet management assessment systems. Our approach follows a two-stage pipeline that combines VideoMAE-based feature extraction with an Augmented Self-Mask Attention (AMA) detector, enhanced by a Spatial Pyramid Pooling-Fast (SPPF) module to capture multi-scale temporal features. Experimental results reveal a distinct trade-off between model capacity and efficiency. At the feature extraction stage, the ViT-Giant backbone delivers higher representations with 88.09% Top-1 test accuracy, while the ViT-based variant proves to be a practical alternative, achieving 82.55% accuracy with significantly lower computational fine-tuning costs (101.85 GFLOPs/segment compared to 1584.06 GFLOPs/segment for Giant). In the downstream localization task, the integration of SPPF consistently improves performance across all configurations. Notably, the ViT-Giant + SPPF model achieves a peak mAP of 92.67%, while the lightweight ViT-based configuration maintains robust results. |
| 4 | $D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation | 2026-03-17 | 展开Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality. Conversely, diffusion models offer high fidelity but at a prohibitive computational cost. To overcome these limitations, we propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ( |
| 5 | Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition | 2025-10-26 | 展开Radar-based human activity recognition (HAR) is attractive for unobtrusive and privacy-preserving monitoring, yet many CNN/RNN solutions remain too heavy for edge deployment, and even lightweight ViT/SSM variants often exceed practical compute and memory budgets. We introduce Neural-HAR, a dimension-gated CNN accelerator tailored for real-time radar HAR on resource-constrained platforms. At its core is GateCNN, a parameter-efficient Doppler-temporal network that (i) embeds Doppler vectors to emphasize frequency evolution over time and (ii) applies dual-path gated convolutions that modulate Doppler-aware content features with temporal gates, complemented by a residual path for stable training. On the University of Glasgow UoG2020 continuous radar dataset, GateCNN attains 86.4% accuracy with only 2.7k parameters and 0.28M FLOPs per inference, comparable to CNN-BiGRU at a fraction of the complexity. Our FPGA prototype on Xilinx Zynq-7000 Z-7007S reaches 107.5 $μ$s latency and 15 mW dynamic power using LUT-based ROM and distributed RAM only (zero DSP/BRAM), demonstrating real-time, energy-efficient edge inference. Code and HLS conversion scripts are available at https://github.com/lab-emi/AIRHAR. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation | 2026-05-04 | 展开We present FoR-Net, an efficient semantic segmentation framework that focuses on identifying and enhancing hard regions. Instead of relying on heavy global modeling, FoR-Net adopts an efficient strategy that selectively emphasizes informative regions through a learned importance map and a Top-K activation mechanism. Specifically, a selector module predicts region-wise importance, enabling the model to focus on challenging areas such as thin structures and object boundaries. Multi-scale reasoning is achieved using convolutional branches with different receptive fields, allowing diverse spatial context aggregation. We evaluate FoR-Net on the Cityscapes benchmark under limited computational resources. Despite its efficient design and standard training configuration, FoR-Net achieves competitive performance and exhibits improved attention to difficult regions. These results suggest that selective region-focused reasoning can serve as a practical and efficient alternative for semantic segmentation. This work explores region-focused reasoning under resource-constrained settings and provides insights for developing efficient and region-aware segmentation models. |
| 2 | Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation | 2026-04-25 | 展开High-performance semantic segmentation has achieved significant progress in recent years, often driven by increasingly large backbones and higher computational budgets. While effective, such approaches introduce substantial computational overhead and limit accessibility under constrained hardware settings. In this paper, we propose DGM-Net (Directional Geometric Mamba Network), an efficient architecture that improves modeling capability through structural design rather than increasing model capacity. We introduce Directional Geometric Mamba (G-Mamba), a linear-complexity O(N) operator as an alternative to conventional context modeling modules such as ASPP and PPM. To further enhance structural awareness in state space model (SSM)-based modeling, we design the DGM-Module, which extracts centripetal flow fields and topological skeletons to guide the scanning process and improve boundary preservation. Without relying on large-scale pretraining or heavy backbone scaling, DGM-Net achieves 80.8% mIoU within 28k iterations, 82.3% mIoU on Cityscapes test set, and 45.24% mIoU on ADE20K. In addition, the model maintains stable performance under constrained hardware settings (e.g., batch size of 2 on 8GB VRAM), highlighting its efficiency and practicality. These results demonstrate that incorporating geometric guidance into SSM-based architectures provides an effective and resource-efficient direction for semantic segmentation. |
| 3 | Semantic-Fast-SAM: Efficient Semantic Segmenter | 2026-04-22 | 展开We propose Semantic-Fast-SAM (SFS), a semantic segmentation framework that combines the Fast Segment Anything model with a semantic labeling pipeline to achieve real-time performance without sacrificing accuracy. FastSAM is an efficient CNN-based re-implementation of the Segment Anything Model (SAM) that runs much faster than the original transformer-based SAM. Building upon FastSAM's rapid mask generation, we integrate a Semantic-Segment-Anything (SSA) labeling strategy to assign meaningful categories to each mask. The resulting SFS model produces high-quality semantic segmentation maps at a fraction of the computational cost and memory footprint of the original SAM-based approach. Experiments on Cityscapes and ADE20K benchmarks demonstrate that SFS matches the accuracy of prior SAM-based methods (mIoU ~ 70.33 on Cityscapes and 48.01 on ADE20K) while achieving approximately 20x faster inference than SSA in the closed-set setting. We also show that SFS effectively handles open-vocabulary segmentation by leveraging CLIP-based semantic heads, outperforming recent open-vocabulary models on broad class labeling. This work enables practical real-time semantic segmentation with the "segment-anything" capability, broadening the applicability of foundation segmentation models in robotics scenarios. The implementation is available at https://github.com/KBH00/Semantic-Fast-SAM. |
| 4 | I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation | 2025-09-12 | 展开Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost. Quantization offers an effective strategy to improve efficiency, but ViT-based segmentation models are notoriously fragile under low precision, as quantization errors accumulate across deep encoder-decoder pipelines. We introduce I-Segmenter, the first fully integer-only ViT segmentation framework. Building on the Segmenter architecture, I-Segmenter systematically replaces floating-point operations with integer-only counterparts. To further stabilize both training and inference, we propose |
| 5 | SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation | 2024-11-26 | 展开The Vision Transformer (ViT) has achieved notable success in computer vision, with its variants widely validated across various downstream tasks, including semantic segmentation. However, as general-purpose visual encoders, ViT backbones often do not fully address the specific requirements of task decoders, highlighting opportunities for designing decoders optimized for efficient semantic segmentation. This paper proposes Strip Cross-Attention (SCASeg), an innovative decoder head specifically designed for semantic segmentation. Instead of relying on the conventional skip connections, we utilize lateral connections between encoder and decoder stages, leveraging encoder features as Queries in cross-attention modules. Additionally, we introduce a Cross-Layer Block (CLB) that integrates hierarchical feature maps from various encoder and decoder stages to form a unified representation for Keys and Values. The CLB also incorporates the local perceptual strengths of convolution, enabling SCASeg to capture both global and local context dependencies across multiple layers, thus enhancing feature interaction at different scales and improving overall efficiency. To further optimize computational efficiency, SCASeg compresses the channels of queries and keys into one dimension, creating strip-like patterns that reduce memory usage and increase inference speed compared to traditional vanilla cross-attention. Experiments show that SCASeg's adaptable decoder delivers competitive performance across various setups, outperforming leading segmentation architectures on benchmark datasets, including ADE20K, Cityscapes, COCO-Stuff 164k, and Pascal VOC2012, even under diverse computational constraints. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | ReGenVC: End-to-End Real-Time Generative Video Coding at Ultra-Low Bitrate | 2026-07-30 | 展开We present ReGenVC, an end-to-end generative video codec that compresses talking-head video to an ultra-low bitrate and decodes it in real time. The encoder reduces a source clip to a compact bitstream -- a neurally compressed first frame, per-frame pose keypoints, and metadata -- totaling about 26 kB for a 77-frame sequence. The decoder is a four-step distilled diffusion transformer that reconstructs the video conditioned on the transmitted pose and reference frame. Compared with x264/x265, ReGenVC reduces the bitrate to roughly one tenth of that required by traditional codecs (about 26 kB vs. 250--280 kB for essentially artifact-free reconstruction); at a matched ultra-low bitrate, conventional codecs collapse into blocking artifacts while ReGenVC stays sharp by exploiting a strong generative prior. The central obstacle to deploying such a codec is decoder latency: multi-step sampling with transformer and VAE components is too slow for interactive use. We make the decoder real-time through four-step distillation and three model-preserving system techniques: (i) eight-GPU unified sequence parallelism (Ulysses & Ring), (ii) a spatially-split VAE, and (iii) a three-stage overlapped pipeline; an analytical timing model characterizes the real-time feasibility region. On an 8-GPU node, the system sustains 24 fps output (972 ms per 25-frame window, within the 1000 ms budget), enabling a live browser stream without observed frame underruns. A hybrid CPU-GPU deployment further runs the encoder on the CPU at 24 fps and offloads the decoder-side one-shot conditioning encoders to the CPU, reducing the per-GPU memory peak from 21.1 GB to about 7.7 GB. To our knowledge, ReGenVC is the first end-to-end generative video codec to combine ultra-low-bitrate encoding with real-time decoding on an 8-GPU system. |
| 2 | Parallel Decoding Distillation for Fast Image and Video Generation | 2026-07-28 | 展开Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA) acceleration methods heavily rely on variational score distillation (VSD) and adversarial losses to distill diffusion models into few-step generators. Albeit achieving high-quality video generation, these training losses are notoriously hard to optimize and suffer from mode collapse, leading to loss of video diversity and lack of motion. In this paper, we introduce Parallel Decoding Distillation (PDD), a simplified and scalable trajectory-based distillation method for fast inference of diffusion and flow matching models. Our architecture and training procedure are compatible with any pre-trained model and support sampling with a varying number of function evaluations (NFE). PDD accelerates generation by predicting multiple denoising steps per network evaluation. Conceptually, it learns a representation of the mean velocity without regressing its derivative using JVPs or finite-difference approximations. Our method achieves SOTA performance with 4-8 NFE on LTX-2.3 Text-to-Video/Audio, Wan 14B Text-to-Video, and Qwen-Image Text-to-Image. Moreover, PDD presents a significant improvement in generated video diversity. |
| 3 | Manifold-Constrained Noise Optimization for Diverse Diffusion Sampling | 2026-07-27 | 展开Few-step distilled diffusion models generate high-quality images quickly, but often lose per-prompt diversity, producing near-identical samples across random seeds. Optimizing the initial noise at inference time offers an appealing way to recover this diversity, yet existing methods directly update the initial noise in an unconstrained Euclidean space, ignoring both the geometry of the Gaussian prior and the model's sensitivity to noise frequencies. They therefore introduce auxiliary quality-control objectives to maintain generation fidelity, adding compute and weighting hyperparameters while still requiring conservative updates to prevent degradation. In this work, we propose MoNO, a training-free method that performs Manifold-constrained Noise Optimization on a low-dimensional, quality-stabilizing noise manifold. MoNO sequentially optimizes each new initial noise so that its predicted visual feature complements previous generations, while Riemannian updates on an affine low-frequency sphere preserve prior likelihood and fix unstable high-frequency components by construction. This enables large geodesic steps, removes the need for auxiliary quality-control objectives, and converges in far fewer iterations than prior noise-optimization methods. Experiments with multiple distilled text-to-image diffusion models show that MoNO consistently improves per-prompt diversity while maintaining image quality. |
| 4 | Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusion | 2026-05-08 | 展开LiDAR-based semantic segmentation is essential for autonomous-driving perception, yet dense point-wise annotations are costly, and long-tailed outdoor scenes make small safety-critical objects difficult to discover without supervision. Existing unsupervised methods face three key challenges: they struggle to preserve small and sparsely observed objects under substantial scale variation, have difficulty enforcing intra-region consistency and inter-region discrimination during cross-modal transfer, and lack an efficient feature-preserving mechanism for contextual propagation over superpoint graphs. We therefore propose DDS, an unsupervised 3D semantic segmentation framework. First, a coarse-to-fine multi-granularity mask cascade provides complementary 3D region cues for objects across different scales, improving the preservation of small and sparsely observed objects. Second, region-guided multi-level distillation transfers self-supervised visual knowledge through point-level alignment, mask-level prototype alignment, and prototype-level contrastive learning, enhancing intra-region consistency and inter-region discrimination. Third, restart-based graph diffusion efficiently propagates contextual information among superpoints while anchoring the refined representation to the initial distilled features and avoiding explicit graph eigendecomposition. Experiments on real-world driving datasets show that DDS outperforms representative unsupervised baselines, improving oAcc, mAcc, and mIoU by up to 2.9%, 9.7%, and 4.1%, respectively. These results demonstrate the effectiveness and transferability of DDS for unsupervised 3D scene understanding in autonomous-driving scenarios. |
| 5 | d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation | 2026-01-12 | 展开Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently face an accuracy-parallelism trade-off. Despite increasing interest, existing methods typically focus on only one-side of the coin, targeting either efficiency or accuracy. To address this limitation, we propose d3LLM (Pseudo-Distilled Diffusion Large Language Model), striking a balance between accuracy and parallelism: (i) during training, we introduce pseudo-trajectory distillation to teach the model which tokens can be decoded confidently at early steps, thereby improving parallelism; (ii) during inference, we employ entropy-based multi-block decoding with a KV-cache refresh mechanism to achieve high parallelism while maintaining accuracy. To better evaluate dLLMs, we also introduce AUP (Accuracy Under Parallelism), a new metric that jointly measures accuracy and parallelism. Experiments demonstrate that our d3LLM achieves up to 10$\times$ speedup over vanilla LLaDA/Dream, and 5$\times$ speedup over AR models without much accuracy drop. Our code is available at https://github.com/hao-ai-lab/d3LLM. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Accelerating Data Preprocessing for Efficient Vision Model Inference on Jetson Edge Device | 2026-08-27 | 展开Data preprocessing is a crucial part of deep learning workflows on edge devices. However, decoding data saved in JPEG format is very compute-intensive and occupies a major portion of the preprocessing pipeline. Therefore, increasing the decoding speed is vital for improving overall throughput, especially for inputs with large image sizes, which are often subject to preprocessing bottlenecks. On the other hand, edge devices are equipped with specialized hardware units to accelerate media processing and image decoding. For instance, the NVIDIA Jetson platform possesses a dedicated NVJPEG unit. These units can be used to enhance the performance of the preprocessing pipeline. This paper introduces the utilization of such specific hardware acceleration units for offloading decoding tasks. By combining this with a multi-instance approach, it allows for the parallelization of all compute resources including CPU, NVJPEG, GPU, and DLA in Jetson devices. In this work, we compare various potential pipeline designs. On ResNet18, ResNet50, and ResNet152, three models with different sizes, we evaluate the impact of batch sizes and image sizes, as well as the characteristics of GPU/DLA inference. Finally, a fine-tuning experiment for multi-instance design has been conducted. The multi-instance design with a specific hardware decoding unit involved offers up to 30.02% speedup for large image sizes, compared with the most optimized design without it. Based on these findings, we demonstrate the benefits of using the NVJPEG unit in deep learning workflows and provide guidelines for tuning and optimizing edge inference workflows. |
| 2 | Goodput Maximization for Large Language Model Edge Inference: A Two-Phase Maskable PPO Approach | 2026-08-26 | 展开This paper presents a novel two-phase maskable proximal policy optimization (TP-MPPO) algorithm, which maximizes the system goodput counting request throughput with strict service level objective (SLO) compliance for large language model (LLM) inference services in wireless edge networks. In the first phase of TP-MPPO, we optimize the task offloading decisions by MPPO with action masking mechanism, effectively avoiding exploring invalid actions and reducing the action space. In the second phase, closed-form solutions are derived for uplink bandwidth allocation; a greedy algorithm is designed for downlink bandwidth allocation to provide immediate rewards for the MPPO in the next round. The two stages alternate till convergence. Simulation results demonstrate that TP-MPPO can improve the system reward by 33.3%--87.5% compared to its benchmarks and achieve the highest goodput. |
| 3 | How Merge-Tolerant Are Vision Transformers for Wheat Phenotyping? | 2026-08-24 | 展开Vision-based wheat phenotyping requires repeated measurements under deployment constraints, from growth-stage recognition to wheat-head counting and organ segmentation. Plain Vision Transformers (ViTs) provide a common architecture for these tasks, but quadratic attention limits high-throughput and edge inference. Training-free token merging is attractive because it can be inserted into trained models without retraining. We provide a systematic benchmark of ToMe and Mutual Pair Merging across growth-stage classification, wheat-head detection, and wheat-organ segmentation, measuring task quality, throughput, token count, and peak GPU memory, with additional Raspberry Pi 5 measurements. The benchmark reveals a clear hierarchy: classification is highly merge-tolerant, while detection and segmentation are constrained by repeated instances, thin organs, dense boundaries, reconstruction, and runtime overhead. Optimized attention backends can erase apparent speedups, so deployment value must be profiled on the target runtime rather than inferred from token count. |
| 4 | TEE-X: TEE-aware Acceleration Framework for Large Vision Models at the Edge | 2026-08-24 | 展开Despite their remarkable success, machine learning models, particularly in vision applications, are alarmingly vulnerable to a range of security threats. One key factor in the attack landscape is the distinction between white-box and black-box threat models, as the latter poses challenges that limit attack effectiveness when access to model information is limited. As a result, using Trusted Execution Environments (TEEs) enhances security for machine learning applications by protecting model confidentiality and execution integrity, effectively shifting the execution environment from the white-box to the black-box side of the threat model spectrum. While adopting TEEs for large vision models, e.g., Vision Transformers (ViTs), is crucial for enhancing security and privacy, significant challenges related to memory constraints and increased computational latency must be addressed, especially in time-sensitive edge applications where safety and privacy are paramount. The objective of this work is to enable large vision models to be fully hosted within TEEs, achieving GPU-level inference latency for time-sensitive edge vision applications while maintaining performance. To this end, we propose TEE-X, a TEE-aware acceleration framework that introduces a sensitivity-aware modularization technique and enables vectorization in TEE inference. This design is validated on OP-TEE for Arm TrustZone, configured to optimize performance on the NVIDIA Jetson AGX Xavier for efficient edge vision applications using ViT models. The findings reveal that TEE-X delivers an effective TEE-aware acceleration framework that achieves minimal accuracy-latency trade-offs while ensuring fast and secure edge inference for vision models. |
| 5 | Dependency-Aware HARQ and Link Adaptation for Wireless Transmission of Open-Vocabulary Scene Graphs | 2026-08-08 | 展开Wireless visual uplinks increasingly carry structured representations for edge inference, making packet reliability part of task-aware link adaptation. In open-vocabulary scene-graph transmission, an indexed triplet is usable only if both its triplet packet and the vocabulary packets defining any newly introduced tokens are recovered. This prerequisite coupling makes the marginal value of packet reliability depend on neighboring packet reliabilities. We formulate a dependency-aware semantic distortion and jointly optimize finite choices of modulation and coding scheme (MCS), transmit power, and Chase-combining hybrid automatic repeat request (HARQ) depth under expected delay and energy constraints. The distortion is multi-affine in packet failure probabilities and cannot, in general, be reduced to static separable unequal error protection (UEP) weights when prerequisites are active. This structure yields a state-dependent reliability coefficient and explicit switching thresholds among wireless actions. A Lagrangian block method performs exact per-packet finite-action updates for fixed multipliers. On reduced instances, it matches exhaustive optimization in 28 of 30 cases, with a worst gap of 1.095%. On GQA traces using a table-driven block error rate (BLER) abstraction, it reduces mean semantic distortion by 58.71% and grounded-query failure by 57.03% relative to dependency-agnostic HARQ under the same budgets. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | HyQuant: Hybrid-Precision Quantization for LLM Attention | 2026-08-28 | 展开Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the \emph{attention} module often introduces large errors at very low bit-widths, causing performance degradation. Existing methods mainly rely on smoothing techniques to handle outliers, while we propose a hybrid quantization design to better balance accuracy and efficiency. Specifically, we propose \textbf{HyQuant}, an efficient hybrid quantization framework for LLM attention. HyQuant quantizes most attention states into low-bit formats while retaining a small set of vertical-line tokens and local-window states in high precision. These accuracy-critical regions are selected using lightweight vertical-line-aware attention-pattern signals, reducing quantization error with limited overhead. In the Prefill stage, HyQuant uses a hybrid-precision quantized attention operator that preserves vertical-line tokens and a local sliding window in full precision while quantizing the remaining context. In the Decode stage, HyQuant applies the same principle to KV-cache compression and fuses KV dequantization with attention computation to improve memory and hardware efficiency. Across diverse tasks, models, and datasets, HyQuant maintains nearly lossless accuracy with an extremely simple design, demonstrating the efficiency and practical feasibility of hybrid quantization for LLM attention. Code is available at: https://github.com/jerrysfls/HyQuant . |
| 2 | Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs | 2026-08-27 | 展开Low-bit quantization offers a promising avenue for reducing the computational and memory demands of Multimodal Large Language Models (MLLMs). Recent hardware support for low-precision formats, ranging from MXFP8 to ultra-low-bit formats such as MXFP4 and HiF4, has accelerated research into efficient MLLM training and deployment. In this work, we present a systematic study of these quantization schemes in representative MLLMs that span both video generation and reasoning tasks. Our analysis shows that MXFP8 achieves near-lossless performance, whereas aggressive 4-bit quantization leads to significant degradation. Through extensive ablations, we identify activation quantization as the primary source of this performance loss, contributing substantially more than weight quantization. Motivated by this observation, we propose Residual Fallback Quantization (RFQ), a lightweight activation reconstruction framework that supplements the primary ulta-low-bit activation representation with an auxiliary quantized residual pathway. By explicitly modeling and compensating for quantization errors, RFQ improves activation fidelity while preserving the efficiency advantages of ultra-low-bit computation. RFQ requires no architectural modifications and incurs negligible computational overhead. Extensive experiments on Wan2.2 and Qwen3-VL demonstrate that RFQ consistently recovers a substantial portion of the performance lost under the quantization of MXFP4 and HiF4, significantly narrowing the gap to BF16 baselines across both generation and 4 reasoning benchmarks. Our findings establish activation quantization as the dominant bottleneck in ultra-low-bit MLLMs and highlight residual-based activation reconstruction as an effective and practical strategy for robust 4-bit deployment. |
| 3 | SandwichQuant: Which Parameters Matter Before and After Quantization? | 2026-08-25 | 展开Quantization correction methods usually optimize weights, quantization parameters, or reconstruction objectives, while the underlying parameter subspaces responsible for effective correction remain unclear. In this work, we study quantization correction from a parameter subspace perspective and reveal that correction capability is highly non-uniform across parameter groups. By decomposing trainable parameters into backbone weights, normalization-affine parameters, and quantization parameters, we show that the low-dimensional normalization-affine subspace provides a highly efficient correction direction under matched budgets. Based on this finding, we propose SandwichQuant, a two-stage normalization-affine correction framework that performs adaptation before and after quantization. The pre-stage improves quantization robustness, while the post-stage compensates residual errors after the quantized graph is fixed. Extensive experiments on vision models and large language models demonstrate consistent improvements under various low-bit quantization settings, validating the effectiveness of subspace-aligned correction. |
| 4 | FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference | 2026-08-24 | 展开Recent years have witnessed remarkable achievements of Large Language Models (LLMs) in multiple domains, while the excessive resource requirements of LLMs hinder the deployment on resource-constrained devices. Although model quantization stands out as an effective approach, conventional quantization approaches typically incur severe performance degradation due to uniform bit-width or simple heuristic sensitivity evaluation. In this paper, we propose a novel Fisher information-based Adaptive Mixed Precision Weight Quantization approach, i.e., FAMPWQ, which performs layer-adaptive weight quantization for effective LLM inference on commodity GPUs. First, we propose a system model with a novel Fisher information metric to measure the layer-wise sensitivity to quantization. Second, we propose a reinforcement learning-based bit-width allocator in FAMPWQ, which generates an adaptive bit-width allocation strategy based on the Fisher information sensitivity metric. Extensive experiments on 7 models and 5 benchmarks demonstrate that FAMPWQ significantly outperforms 7 baseline approaches in terms of PPL (up to 3.39 smaller), accuracy (up to 6.87% higher), and LLM-as-a-judge comparison (up to 76% win rate). |
| 5 | Binarized High-Efficiency RAW Video Restoration and Beyond | 2026-08-17 | 展开RAW video restoration is fundamental to high-quality low-level perception and serves as the basis for a wide range of downstream vision applications. While binary neural networks (BNNs) enable efficient lightweight deployment for image enhancement, their deficiencies in modeling temporal coherence and activation value distributions hinder their effectiveness when applied to video scenarios. In this paper, we propose BinRVR, a binarized RAW video restoration framework that reduces computation and parameters by approximately 96% while incurring only about 4% performance degradation. Specifically, we present a Binarized Information Interaction Module (BIIM) to jointly model spatial and temporal information in an efficient and unified manner. Moreover, we develop a Distribution-Aware Binarized Convolution (DAB-Conv) that leverages the statistics of full-precision activations to mitigate quantization errors. The proposed framework further supports multi-bit quantization, enabling flexible accuracy-efficiency trade-offs across different hardware constraints. Extensive experiments demonstrate that our BinRVR achieves competitive performance compared with state-of-the-art binarized methods on RAW video restoration tasks, including low-light enhancement, denoising, deblurring, and super-resolution. We further explore the potential of our method on downstream video applications, including object detection and monocular depth estimation. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking | 2026-08-31 | 展开Most trajectory forecasting models are trained on clean annotated histories, and are often evaluated under the same idealized assumption, although practical deployments rely on trajectories produced by imperfect multi-object trackers. The real-world observations exhibit localization jitter, missed or unstable detections, and data-association ambiguity, which are usually either ignored or removed through denoising. This paper instead treats tracking-derived reliability cues as an informative signal to be propagated to the predictor. We propose a plug-in uncertainty-aware formulation in which each observed state is encoded as an uncertain state representation, modeled by a Gaussian distribution whose covariance combines detection-level localization uncertainty and association-level ambiguity through the law of total variance. Existing backbones are adapted with minimal architectural changes: input trajectories are represented as Gaussian observations, and predicted trajectories are produced as Gaussian forecasts rather than deterministic coordinates. To train predictors that remain robust under structured observation noise, we combine temporally correlated Ornstein-Uhlenbeck perturbations with response-based knowledge distillation from a teacher trained on clean trajectories. Experiments on Oxford Town Centre and VIRAT using real tracker outputs, together with a complementary ETH/UCY pseudo-detection protocol, show that the proposed formulation improves displacement accuracy and the reliability-sharpness trade-off of probabilistic forecasts. |
| 2 | KDGen-BF: A Generative Site-Specific Multi-User Beamforming Approach | 2026-08-30 | 展开This paper proposes knowledge-distilled generative beamforming (KDGen-BF) framework for site-specific multi-user beamforming. KDGen-BF generates a multi-user beamforming weights from low-dimensional reference signal received power (RSRP) observations without acquiring instantaneous channel state information (CSI). To address the ambiguity caused by limited RSRP observations and interference coupling, KDGen-BF formulates multi-user beamforming as a conditional generation problem and directly outputs beamforming weights beyond a finite codebook. A diffusion transformer is trained through knowledge-distillation and exponential-moving-average (KD-EMA) guidance, and multi-candidate strategy is used for online deployment. Numerical results on multiple DeepMIMO scenarios demonstrate that: 1) under limited probing budgets, KDGen-BF outperforms all baselines; 2) with larger probing budgets, KDGen-BF achieves performance comparable to exhaustive search over the discrete Fourier transform (DFT) codebook and outperforms all other baselines; and 3) under noisy RSRP observations, KDGen-BF remains robust and outperforms all compared baselines. |
| 3 | ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization | 2026-08-30 | 展开Knowledge distillation effectively transfers reasoning capabilities from large language models to lightweight student models. To enable knowledge transfer across disparate model families, researchers increasingly explore cross-tokenizer distillation. However, cross-tokenizer distillation remains challenging due to vocabulary and sequence misalignment, while approximate vocabulary alignment can introduce additional noise into distillation. To address these challenges, we propose Anchor-Based Cross-Tokenizer Distillation with Residual Regularization (ACTD). ACTD bridges structural heterogeneity through vocabulary and sequence alignment, while mitigating alignment noise via a novel anchor loss with residual regularization. We further extend this framework to a multi-teacher setting. Evaluated across five reasoning benchmarks with three distinct teacher models, ACTD achieves state-of-the-art performance. Moreover, its multi-teacher extension outperforms the strongest single-teacher and multi-teacher baselines, further demonstrating the robustness of our method. |
| 4 | CutClean: Neural Network Pruning for Privacy-Preserving Inference | 2026-08-13 | 展开Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occur even in the absence of representation imbalances that lead to traditional dataset biases. This poses significant privacy risks when deploying models that process sensitive attributes. In this context, we propose CutClean, a privacy-aware pruning method that allows to reduce privacy information flow through the network, while increasing its sparsity. Our approach employs auxiliary linear privacy heads placed at each network's block to quantify information leakage, and further applies increasing levels of sparsity to remove the private attribute leakage, measured in terms of the accuracy of the privacy head attached to the last block. Experiments on synthetic and real-world datasets demonstrate that our approach effectively minimizes private information flow while achieving high sparsity rates and preserving classification target accuracy. |
| 5 | Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic Masking | 2026-08-09 | 展开Domain generalization (DG) and neural network pruning are conventionally treated as distinct objectives, targeting out-of-distribution (OOD) robustness and model efficiency, respectively. In this work, we bridge this gap by introducing Domain-Aware Pruning (DAP), a framework that leverages network sparsity as a mechanism to implicitly enhance generalization to unseen domains. Diverging from standard binary mask optimization, DAP learns a continuous parameter retention probability |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | WingSpan: Concurrency and Dependence for Sparse and Structured Tensor Compilers | 2026-06-18 | 展开Sparse tensors represent data that is mostly zero or some other compressible fill pattern. Such datasets can be massive, so optimized tensor algebra libraries and compilers have been developed to exploit these patterns to improve performance. Existing systems, however, frequently lack support for parallelism, especially when outputs are sparse or multiple inputs are sparse. We propose WingSpan, a sparse tensor language enabling unrestricted parallel programming. WingSpan supports arbitrary composition of parallel loops and data structures, matching or exceeding the performance of hand-optimized parallel routines on critical kernels such as SpGEMM. We also introduce a dependence theory for the safety of parallel programs involving sparse tensors and structures beyond sparsity. |
| 2 | PassNet: Scaling Large Language Models for Graph Compiler Pass Generation | 2026-05-28 | 展开Modern tensor compilers such as TorchInductor deliver substantial speedups on mainstream models, yet face a systematic performance ceiling on long-tail workloads -- our profiling shows that 43% of real-world subgraphs experience end-to-end slowdowns under default compilation. While LLMs offer a path toward automated optimization, existing efforts focus on standalone kernel generation. We argue that pass generation -- where LLMs author structured graph transformations that integrate directly into compiler pipelines -- is the more appropriate abstraction. We propose PassNet, the first large-scale ecosystem for LLM-based compiler pass generation, comprising: (1) PassNet-Dataset, over 18K unique computational graphs from 100K real-world models; and (2) PassBench, 200 curated long-tail fusible tasks (comprising 2,060 subgraphs in total) evaluated under the Error-aware Speedup Score (ES_t) -- a metric unifying correctness, stability, and performance -- with layered integrity defenses against systematic LLM exploitation. Experiments reveal that PassBench is both highly discriminative and genuinely unsaturated: the best frontier model trails TorchInductor by 37% in aggregate, yet on individual subgraphs LLMs achieve up to 3x speedup over the same compiler -- indicating that the bottleneck is consistency, not capability. Fine-tuning a small model on merely ~4K PassNet trajectories yields a 2.67x improvement approaching frontier-model performance, demonstrating substantial headroom and validating PassNet as live training infrastructure for advancing LLM-driven compiler optimization. All data, benchmarks, and tooling are publicly available. |
| 3 | DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs | 2026-05-02 | 展开The scaling of large language models (LLMs) is currently bottlenecked by the rigidity of distributed programming. While high-performance libraries like CuBLAS and NCCL provide optimized primitives, they lack the flexibility required for rapidly evolving model architectures. Conversely, existing tensor compilers fail to address the complex memory hierarchy of distributed clusters effectively. To bridge this gap, we propose DITRON, a scalable tile-level compiler that democratizes high-performance distributed kernel development. DITRON introduces a novel hierarchical programming abstraction spanning Core, Device, and Task levels to map tensor programs efficiently onto heterogeneous distributed hardware. This abstraction allows DITRON to support diverse parallelism strategies while abstracting away the complexity of inter-node and intra-node communication. Evaluated across large-scale clusters, DITRON achieves performance parity with or exceeding expert-tuned CUDA libraries, delivering speedups of |
| 4 | Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel | 2026-04-14 | 展开Modern GPU workloads, especially large language model (LLM) inference, suffer from kernel launch overheads and coarse synchronization that limit inter-kernel parallelism. Recent megakernel techniques fuse multiple operators into a single persistent kernel to eliminate launch gaps and expose inter-kernel parallelism, but struggle to handle dynamic shapes and data-dependent computation in real workloads. We present Event Tensor, a unified compiler abstraction for dynamic megakernels. Event Tensor encodes dependencies between tiled tasks, and enables first-class support for both shape and data-dependent dynamism. Built atop this abstraction, our Event Tensor Compiler (ETC) applies static and dynamic scheduling transformations to generate high-performance persistent kernels. Evaluations show that ETC achieves state-of-the-art LLM serving latency while significantly reducing system warmup overhead. |
| 5 | VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination | 2026-02-11 | 展开With the widening gap between compute and memory operation latencies, data movement optimizations have become increasingly important for DNN compilation. Current optimizations such as layout transformations and operator fusion only target a subset of tensor operators and consequently miss important opportunities for reducing data movement in contemporary DNN workloads, including large language models. We introduce VTC, a novel tensor compilation framework that for the first time eliminates all unnecessary data movement by targeting the full spectrum of data movement operators. VTC proposes the concept of virtual tensors to track data movement between compute operators via index mappings rather than expensive physical data transfers to and from global memory, which can seamlessly interoperate with existing computation kernels and handle arbitrary tensor operator compositions. We also introduce a novel data movement elimination algorithm to automatically identify a profitable virtual tensor creation strategy. Evaluation on a variety of DNNs shows that VTC can outperform existing ML compilers by up to 1.93x (1.28x on average) on NVIDIA GPUs with up to 60% (17.5% on average) inference memory savings. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search | 2026-08-31 | 展开By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension, we reduce memory cost and memory bandwidth of a typical large-scale Approximate Nearest Neighbor (ANN) search system, while reducing its complexity and keeping or improving recall across multiple benchmark datasets. State-of-the-art systems filter candidates using coarse partitions, approximately score them to narrow the set, and then rescore the best with higher precision representations (often >=8 bits per dimension). Our relativized codecs can bring this down to 2--4 bits per dimension. We use the properties of the ANN system to encode residual vectors instead of full vectors, both for the approximate scoring phase and the rescoring phase. Since Maximum Inner Product Search (MIPS) is very sensitive to vector norms, we correct the |
| 2 | VoS: Variate Ordering Strategies for Skyline Query Optimization | 2026-08-26 | 展开Efficiency of skyline algorithms is highly influenced by the underlying data characteristics. Traditionally, optimization efforts have focused on minimizing the total number of tuple-pair dominance checks to improve query performance. However, in practice, a dominance check between two tuples does not necessarily require evaluating dominance relationships for each and every preference attribute of the data and this creates a disconnect between dominance checks optimization and query execution performance. In this paper, we argue that skyline algorithms need to optimize total per-attribute dominance checks, along with per-tuple dominance checks and that, for both of these goals, the ordering of the attributes (or variates) can have a substantial impact on the efficiency of skyline computation. Based on this premise, we present several strategies for identifying an effective variate order to minimize redundant attribute comparisons. Extensive experiments on both synthetic and real-world datasets, and on both scalar and SIMD architectures, confirm the effectiveness of the proposed approach in reducing computational overhead and improving skyline query performance. |
| 3 | Direct-Operable SIMD Bit-Slicing: A Framework for Memory-Efficient Predicate Evaluation | 2026-08-26 | 展开Traditional Java object models introduce significant memory overhead due to object headers and internal padding, often leading to performance bottlenecks in data-intensive distributed systems. This paper presents a novel framework that utilizes the Project Panama Vector API to perform predicate evaluation directly over bit-sliced, compressed data streams. By transposing standard row-oriented data into parallel bit-planes, we demonstrate a mechanism to evaluate complex filters using SIMD (Single Instruction, Multiple Data) instructions without requiring prior decompression. The framework supports integers, longs (timestamps), doubles (via IEEE 754 order-preserving transformation), and strings (via dictionary encoding). Our benchmarks indicate a reduction in memory footprint by up to 8x while maintaining or exceeding the throughput of uncompressed standard Java collections. End-to-end evaluation on TPCDS-modeled data at 50M rows demonstrates 2.4-10.8x speedup over scalar scans across five representative filter-heavy query patterns, with extended type benchmarks on TPCDS columns showing 1.5-43x speedups for timestamps, decimals, and dictionary-encoded strings. |
| 4 | Exposing SIMD Parallelism in SQIsign: An AVX-512 Implementation | 2026-08-14 | 展开Modern isogeny-based cryptosystems spend much of their running time in finite-field, elliptic-curve, and higher-dimensional isogeny arithmetic. Exploiting SIMD parallelism is nontrivial: routines such as Montgomery ladders contain loop-carried dependencies, while point, pairing, and theta-coordinate formulas expose only irregular fine-grained parallelism. We show that substantial SIMD parallelism can be recovered by reorganizing the arithmetic dependency graphs of higher-level primitives rather than vectorizing field multiplication in isolation. We develop an end-to-end AVX-512IFMA implementation of SQIsign in which data remain in a radix-$2^{51}$ vector representation across most of the curve-side computation. Our redesign includes projective xDBLADD schedules, batched point doubling in several coordinate systems, a vectorized biscalar ladder, fused cubical-arithmetic pairing steps, and batched one- and two-dimensional isogeny evaluation. Relative to the reference C implementation, we achieve end-to-end speedups of |
| 5 | RVANNS: Mixed-Precision Indexing and Locality-Aware Graph Traversal on RISC-V | 2026-08-10 | 展开Approximate nearest neighbor search (ANNS) on CPUs is increasingly constrained by candidate-vector movement and decoding rather than peak arithmetic throughput. Although the RISC-V Vector Extension (RVV) provides vector-length-agnostic execution and LMUL-based register grouping, generic low-precision decoding still incurs conversion overhead, while irregular graph traversal generates scattered accesses that degrade cache locality and memory-level parallelism. We present RVANNS, an RVV-oriented ANNS engine that jointly optimizes vector representation and graph locality. Its Mixed-Precision Multi-Layer Index (MPMI) represents each vector with a dense 8-bit affine base and sparse FP16/FP32 residuals, fusing reconstruction with distance accumulation and aligning widening with LMUL-sized register groups. ROrder co-locates likely co-visited graph nodes and sorts remapped adjacency lists, transforming scattered payload probes into denser, predominantly forward-moving address streams. Integrated into Milvus, RVANNS achieves 3.39x and 4.94x speedups over scalar execution on real 128-bit and 256-bit RVV processors, respectively. Under controlled HNSW configurations, it improves throughput by 2.27--2.76x over RVV SIMD+FP32 and by 1.18--1.59x over the corresponding AVX-512 and SVE baselines. On Cohere10M, it further delivers 1.82--2.27x higher QPS/W than the evaluated GPU baselines. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Diva++: Dynamic Range Filtering over Hard Workloads | 2026-08-27 | 展开Range filters are compact probabilistic data structures that answer approximate range emptiness queries. They are used in many domains, e.g., in key-value stores, to quickly rule out the existence of keys in a given query range and avoid searching for them in storage. However, all existing range filters exhibit at least one of three shortcomings: (1) they do not provide any false positive rate or performance guarantees, (2) they do not support variable-length keys and query ranges, and (3) they do not allow dynamic updates. We introduce Diva, the first range filter to address all the above challenges simultaneously. Diva learns the dataset's distribution by sampling keys and storing them in a cache-efficient trie. It compresses keys in-between samples by removing their longest common prefix and truncating their suffixes while leaving enough bits in the middle (i.e., an infix) to differentiate the keys in sorted order. It stores infixes in constant-time dynamic data blocks, which it splits to handle insertions and expansions. It processes a range query by traversing the trie and checking for the inclusion of infixes in the target query range. We mathematically prove that Diva provides the best possible trade-off between memory and false positive rate on many common real-world data distributions. We extend these benefits to a wider range of real-world workloads by introducing Diva++, an enhanced Diva variant. Diva++ saves memory by removing redundancies among infixes using order-preserving entropy encoding. It then removes any remaining identical infixes and uses the freed space to store more bits of the original keys within compact binary tries. We compare Diva and Diva++ to all prior range filters, and show that they achieve a false positive rate on par with the state of the art on real-world datasets while supporting dynamicity and variable-length queries and keys. |
| 2 | Threat Aware Task Offloading and Caching for Secure UAV Assisted Vehicular Consumer Electronics | 2026-08-18 | 展开Vehicular consumer electronics increasingly support computation-intensive and latency-sensitive services, imposing stringent efficiency, reliability, and security requirements on vehicular edge computing (VEC) systems. In dynamic vehicular environments, inference-based information leakage and anomalous communication behaviors further threaten system performance and data privacy. To address these challenges, this paper proposes a UAV-assisted cooperative VEC architecture that integrates threat-aware task offloading with intelligent spatiotemporal caching across roadside units (RSUs) and UAV edge nodes. A security-aware uplink transmission model is developed to capture potential information leakage risks and abnormal communication patterns, enabling adaptive offloading decisions. We formulate a joint optimization problem to minimize end-to-end task execution delay while improving cache utilization under limited computing and storage resources. To efficiently solve this problem, a Threat-Aware Joint Optimization (TAGO) framework is designed by combining proximal policy optimization for adaptive task offloading and a gradient-based caching update derived from the Frank-Wolfe algorithm to capture spatiotemporal service popularity. Simulation results demonstrate that the proposed approach significantly reduces task delay and improves cache efficiency compared with several baseline strategies, showing its effectiveness for secure and efficient UAV-assisted vehicular consumer electronics systems. |
| 3 | Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference | 2026-08-10 | 展开The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests. In multi-tenant deployments this cache is shared across tenants, creating a timing side channel: an adversarial tenant can reconstruct another tenant's private prompt by probing cache-hit latency. Three published attacks exploit it -- PROMPTPEEK, EarlyBird and InputSnatch -- reaching up to 100% attack success rate against unprotected vLLM and SGLang, with rates varying by cache architecture and prompt structure. We present KVGov, a governance layer addressing all three attack families' prefix-cache paths under one mechanism. A per-principal salt sigma_p = HMAC_K(secret, principal_id) seeds the block-hash chain, making cache keys cryptographically disjoint across principals. An ablation (N=1000 trials, seed 2026, deterministic judges) isolates this salt as the necessary and sufficient component. KVGov adds ORIGAMI, a Stackelberg water-filling audit scheduler that reduces adversary expected utility by 12.6% at realistic tenant heterogeneity (Gini 0.63), and an evolutionary stability analysis giving a 31.6% adversary-prevalence tipping point below which global caching remains stable. On real hardware (Qwen2.5-7B-Instruct, vLLM 0.26.0, NVIDIA A100) we measure a gate-verified cold/cached TTFT ratio of 0.22, confirming the channel is exploitable at production scale; the defense itself is evaluated in simulation calibrated to those measurements. We replicate the channel on an independent stack (llama.cpp on Apple Metal, ratio 0.093). Finally, isolation and cache efficiency need not conflict: identifying information resides only where prompts diverge, so injecting the salt at that boundary rather than the chain root retains an estimated 93% of the prefix-cache benefit with no cross-principal signal. |
| 4 | String Matching in (Block) Graphs: A Full Classification by Walk Length | 2026-07-30 | 展开We consider directed graphs in which the nodes are labeled with strings. A walk in such a graph naturally corresponds to the concatenation of the visited nodes' labels. These graphs are widely used in bioinformatics to compactly describe large collections of highly similar genomes. Given such a graph |
| 5 | $\tilde{O}$ptimal Algorithm for 2-Approximate All Pair Shortest Paths -- almost | 2026-07-21 | 展开Given an undirected, unweighted graph |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers | 2026-08-31 | 展开Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and length generalization benchmarks. We present a provably correct, transformer parameterization (with only 280 learnable parameters for Boolean algebra tasks) capable of learning and evaluating problems of any depth or length. We assume inputs are fully parenthesized, well-formed expressions. Our approach conceptualizes algorithmic tasks as circuit models embedded in transformers, enabling depth-1 circuit reduction in a single forward pass. To achieve depth generalization, we introduce a positional encoding that tracks each gate's depth within the circuit, enabling the model to identify evaluable subexpressions at each iteration via masked hard attention, with |
| 2 | Can Video World Models Track Unobserved World States? | 2026-08-31 | 展开Video world models are increasingly used as simulators, yet visual fidelity alone does not show that a model maintains the hidden state of the world. We examine this gap with an action-conditioned video Shell Game, a visual analog of |
| 3 | Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware | 2026-08-31 | 展开Inference with transformer-based large language models (LLMs) is often limited by the memory-bound KV cache and quadratic attention cost. State-space models (SSMs) mitigate this through linear attention and fixed-size recurrent states, but their large dense linear projections remain computationally expensive even after quantization. We introduce a method that induces sparse neural activity in heavily quantized linear-attention models with minimal performance loss. Activations below a per-projection trainable threshold ( |
| 4 | DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving | 2026-08-31 | 展开Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substantially reducing key/value (KV) cache growth. However, their in-place recurrent-state updates complicate cache management: prefix reuse requires state checkpoints alongside full-attention KV, while storing state checkpoints in full increases memory pressure, leading to more evictions and repeated prefill. By analyzing the decay structure of Gated DeltaNet (GDN) and Kimi Delta Attention (KDA), we find that different heads and channels retain prefix information over markedly different timescales, which we term \emph{retention horizons}. This variation suggests substantial compression potential in persistent state checkpoints. Building on this observation, we introduce \emph{Decay-Aware State Compression} (DASC), which derives retention horizons from model weights, selects long-horizon state units, and packs them into a ragged state checkpoint layout. To integrate efficiently with tensor-parallel inference engines, DASC furtherly balances compressed state checkpoints across TP ranks. On reuse, DASC either zero-fills omitted units or refreshes them from a bounded suffix with additional compute cost. Across retrieval and end-to-end reasoning benchmarks on Kimi-Linear, conservative DASC configurations remain close to full caching while compressing KDA recurrent state checkpoints by |
| 5 | FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control | 2026-04-21 | 展开Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advances such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA) have demonstrated that the delta rule, an online gradient descent update, enables superior associative recall compared to simple additive updates. While KDA refined the coarse head-wise decay gate into channel-wise decay, the learning rate |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution | 2026-08-31 | 展开Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details. However, existing Real-ISR methods largely optimize fidelity and perceptual quality within a shared network, causing the two objectives to interfere throughout training and making their balance difficult to control. Recent one-step methods reduce sampling steps, yet often inherit both this coupled optimization behavior and the expensive high-resolution backbone of their multi-step predecessors. We argue that efficient Real-ISR requires not only a shorter sampling trajectory, but also specialized modeling of faithful reconstruction and perceptual detail synthesis. Based on this insight, we propose PixelIR, a fidelity-perception decoupling framework built upon pixel-space image-residual flow matching. PixelIR first learns an image flow that maps the degraded observation to a faithful reconstruction. Then, a residual flow synthesizes the missing perceptual details from noise without repeatedly relearning or overwriting the complete restoration solution. We further distill the teacher into a deployment-oriented one-step student within a coarse-to-fine pyramid architecture. Extensive experiments show that PixelIR achieves leading PSNR, SSIM, and LPIPS on both RealSR and DRealSR. The final model completes pixel-space restoration in a single evaluation with only 32.9M parameters, 89.7G MACs, and 8.5ms latency, demonstrating a strong practical fidelity-perception-efficiency balance. |
| 2 | Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution | 2026-08-26 | 展开The perception-distortion trade-off poses a fundamental challenge in single-image super-resolution (SR). Although diffusion-based SR methods excel at generating perceptually realistic images, achieving high fidelity remains a key limitation. Recent advances in diffusion-based SR have shown promise in improving fidelity, but these methods often compromise perceptual quality due to their high reliance on a high-fidelity image. To address this, we introduce UGDiff, a novel diffusion guidance paradigm designed to further improve the perception-distortion balance. In particular, we first estimate the reconstruction uncertainty of the latent features corresponding to a high-fidelity image. This uncertainty is then used to guide the diffusion process to selectively restore high-frequency details in high-uncertainty regions, while preserving fidelity elsewhere. Furthermore, our guidance method adaptively identifies the high-uncertainty regions by considering not only the estimated uncertainty but also the posterior variance of the diffusion sampler at each timestep. This relaxes the reliance on the high-fidelity image in the later stages of sampling, thereby achieving a better perception-distortion balance. Extensive experimental results demonstrate that our method performs favorably against state-of-the-art diffusion-based SR methods. |
| 3 | P-K-GCN: Physics-augmented Koopman-enhanced Graph Convolutional Network for Deep Spatiotemporal Super-resolution | 2026-06-17 | 展开High-fidelity simulation of spatiotemporal dynamics is computationally prohibitive, necessitating efficient super-resolution techniques to reconstruct high-resolution data from coarse-grained inputs. Traditional data-driven methods often lack physical constraints, and simple physics-informed learning struggles with irregular spatial geometries and intricately evolving temporal dynamics. To tackle these challenges, we propose a Physics-augmented Koopman-enhanced Graph Convolutional Network (P-K-GCN) for spatiotemporal super-resolution on irregular geometries. Specifically, a continuous spline-based GCN is first designed to extract spatial dependencies directly from coarse graph, and Koopman operator theory is incorporated to project the nonlinear dynamics into a compact latent space where temporal progression is linearized. Second, we augment the optimization objective with a physics-based loss to force the data-driven reconstructions to adhere to physical laws for improving predictive fidelity and robustness. Finally, we provide a rigorous theoretical analysis, establishing that the physics augmentation and Koopman regularization mathematically guarantees a reduction in super-resolution error by diminishing Rademacher complexity and tightening generalization bounds. We evaluate our framework on reconstructing spatially high-resolution cardiac electrodynamics across a 3D heart geometry from sparse low-resolution measurements. Numerical experiments demonstrate that our method achieves superior accuracy compared to baseline models. |
| 4 | Spatial-Frequency Gated Swin Transformer for Cross-Sensor Remote Sensing Super-Resolution | 2026-05-10 | 展开Remote sensing single-image super-resolution aims to generate high-resolution imagery from low-resolution observations while preserving fine structures such as roads, building boundaries, field edges, and land-cover transitions. Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling through shifted-window self-attention, but their feed-forward networks remain generic channelmixing modules that do not explicitly distinguish low-frequency structure from residual details. We propose SFG-SwinSR, which replaces the standard Swin2SR feed-forward network with a lightweight SpatialFrequency Gated Feed-Forward Network. The module estimates a smoothed feature component through a depthwise low-pass branch, derives residual details by subtraction, refines them spatially, and adaptively reinjects useful details through a bottleneck gate. Experiments on the real crosssensor SEN2VENμS, OLI2MSI, and SEN2NAIP benchmarks, together with an auxiliary synthetic SpaceNet Challenge 3 setting, show consistent improvements across most evaluation settings and competitive performance against recent Swin-based baselines. The results indicate that spatial-frequency transformation within transformer feed-forward networks provides an effective lightweight inductive bias for structure-aware cross-sensor remote sensing super-resolution. Source code is available at https://github.com/aminurhossain/SFG-SwinSR |
| 5 | Semi-Supervised Neural Super-Resolution for Mesh-Based Simulations | 2026-05-10 | 展开Mesh-based simulations provide high-fidelity solutions to partial differential equations (PDEs), but achieving such accuracy typically requires fine meshes, leading to substantial computational overhead. Super-resolution techniques aim to mitigate this cost by reconstructing high-resolution (HR), high-fidelity solutions from low-cost, low-resolution (LR) counterparts. However, training neural networks for super-resolution often demands large amounts of expensive HR supervision data. To address this challenge, we propose SuperMeshNet, an HR data-efficient super-resolution framework for mesh-based simulations aided by message passing neural networks (MPNNs). At its core, SuperMeshNet introduces complementary learning, a semi-supervised approach that effectively leverages both 1) a small amount of paired LR-HR data and 2) abundant unpaired LR data via two jointly trained, complementary MPNN-based models. Additionally, our model is enriched by inductive biases, which are empirically shown to further improve super-resolution performance. Extensive experiments demonstrate that SuperMeshNet requires 90% less HR data to achieve even lower root mean square error (RMSE) than that of the fully supervised benchmark without the inductive biases. The source code and datasets are available at https://github.com/jykim-git/SuperMeshNet.git. |
拉取失败：尝试 3 次后仍未成功获取非空结果，最后一次错误: 所有子关键词请求都失败: video super resolution: arXiv API 返回非成功状态 429 Too Many Requests，响应前缀: "Rate exceeded."
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Praxist: From Experimental Artifacts to Solution Lineages | 2026-08-26 | 展开Autonomous R&D agents now write, run, and improve executable artifacts under automated evaluation---but largely as laboratory instruments: shown on curated benchmarks, with gains that are hard to trace to a cause and costs well above what sustained engineering practice absorbs. The limitation is structural. Most systems treat each attempt as nearly self-contained, so logs, memories, and search trees record what happened without establishing which design element produced an improvement, whether its evidence survived validation, or how it recombines with others. Long campaigns therefore keep re-learning the same lessons. We introduce Praxist, a lineage-centered generational system that converts reproducible artifacts and evaluator outcomes into a typed evidence graph of findings, lane-structured frontiers, and agendas. Separating local artifact construction from cohort-level evidence synthesis lets later attempts inherit validated mechanisms, unresolved claims, and useful constraints, and leaves results attached to an inspectable lineage. On the standardized 75-task MLE-bench suite, the finalized official-grader results give Praxist 60 medals (80.0%), 49 of them gold, against 55 medals (73.3%) and 34 gold for a Claude Code baseline on Claude Opus 4.8---at a recorded model spend of US$3,054 versus US$38,370, roughly a twelfth of the cost. Four case studies---quantitative trading, LiDAR-inertial-visual SLAM, tokamak magnetic control, and rocket landing---carry the same process into open-ended engineering problems, improving on each task-native baseline in headline accuracy, survival, or resource cost, with the discovery path on record. Stronger artifacts at an order of magnitude less spend, each backed by an auditable lineage, are, to our knowledge, first brought together here: the operating profile production research requires, not the one a benchmark demonstration establishes. |
| 2 | Data-Driven Stochastic Optimal Control for Intraday Electricity Trading by Renewable Producers | 2026-04-30 | 展开The rapid growth of weather-dependent renewable generation increases price volatility and imbalance penalty risk in power markets, creating the need for advanced quantitative trading strategies. We develop a data-driven continuous-time stochastic optimal control framework for intraday electricity trading using stochastic differential equations with drift terms ensuring mean reversion to deterministic forecast trajectories. Production follows a Jacobi diffusion, while prices follow an asymmetric jump-diffusion to reflect the heavy-tailed behavior observed in intraday markets. The framework accounts for realistic market features by incorporating gate closure and energy-based imbalance settlement over the delivery window, where the path-dependent imbalance cost is handled by state augmentation to preserve the Markovian structure. The value function is characterized via the dynamic programming principle by a three-stage sequence of two linear Kolmogorov backward equations and a nonlinear Hamilton-Jacobi-Bellman partial integro-differential equation. To solve this problem efficiently, we propose a monotone IMEX finite-difference scheme with operator splitting, semi-implicit linearization, and a differential formulation for the jump operator. Numerical experiments based on German market data indicate that, under the provided forecasts, the computed strategy outperforms the TWAP benchmark and approaches the perfect-foresight benchmark. Sensitivity experiments further show how jump intensity, delivery-window length, and trading horizon affect the trading policy and the resulting profit-and-loss distribution. |
| 3 | When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies | 2026-04-13 | 展开Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming unstructured daily news and filings into a fixed-dimensional vector consumed by a downstream PPO agent. We introduce an automated prompt-optimization loop that treats the extraction prompt as a discrete hyperparameter and tunes it directly against the Information Coefficient - the Spearman rank correlation between predicted and realized returns - rather than NLP losses. The optimized prompt discovers genuinely predictive features (IC above 0.15 on held-out data). However, these valid intermediate representations do not automatically translate into downstream task performance: during a distribution shift caused by a macroeconomic shock, LLM-derived features add noise, and the augmented agent under-performs a price-only baseline. In a calmer test regime the agent recovers, yet macroeconomic state variables remain the most robust driver of policy improvement. Our findings highlight a gap between feature-level validity and policy-level robustness that parallels known challenges in transfer learning under distribution shift. |
| 4 | Optimality Robustness in Koopman-Based Control | 2026-04-07 | 展开The Koopman operator enables simplified representations for nonlinear systems in data-driven optimal control, but the accompanying uncertainties inevitably induce deviations in the optimal controller and associated value function. This naturally raises the question of how such uncertainty-induced optimality deviation can be quantified and mitigated. To address this problem, we adopt a unified analysis-to-design perspective that connects the characterization of optimality robustness with its improvement through controller design. At the analysis level, we establish a unified treatment of multiple uncertainty sources in Koopman-based control, where approximation error and noisy data are incorporated into a common robustness analysis through a norm-bounded representation. At the design level, we develop a robustness-aware optimal control methodology that provably reduces such optimality deviations, thereby enhancing robustness while explicitly revealing a quantitative trade-off between nominal optimality and robustness. As for practical implementation aspect, we further propose a tractable policy iteration algorithm, whose well-posedness and convergence are established via vanishing viscosity regularization and elliptic partial differential equation (PDE) techniques. Numerical examples validate the theoretical findings and demonstrate the effectiveness of proposed methodology. |
| 5 | Deep reinforcement learning for optimal trading with partial information | 2025-10-31 | 展开Reinforcement Learning (RL) applied to financial problems has been the subject of a lively area of research. The use of RL for optimal trading strategies that exploit latent information in the market is, to the best of our knowledge, not widely tackled. In this paper we study an optimal trading problem, where a trading signal follows an Ornstein-Uhlenbeck process with regime-switching dynamics. We employ a blend of RL and Recurrent Neural Networks (RNN) in order to make the most at extracting underlying information from the trading signal with latent parameters. The latent parameters driving mean reversion, speed, and volatility are filtered from observations of the signal, and trading strategies are derived via RL. To address this problem, we propose three Deep Deterministic Policy Gradient (DDPG)-based algorithms that integrate Gated Recurrent Unit (GRU) networks to capture temporal dependencies in the signal. The first, a one -step approach (hid-DDPG), directly encodes hidden states from the GRU into the RL trader. The second and third are two-step methods: one (prob-DDPG) makes use of posterior regime probability estimates, while the other (reg-DDPG) relies on forecasts of the next signal value. Through extensive simulations with increasingly complex Markovian regime dynamics for the trading signal's parameters, as well as an empirical application to equity pair trading, we find that prob-DDPG achieves superior cumulative rewards and exhibits more interpretable strategies. By contrast, reg-DDPG provides limited benefits, while hid-DDPG offers intermediate performance with less interpretable strategies. Our results show that the quality and structure of the information supplied to the agent are crucial: embedding probabilistic insights into latent regimes substantially improves both profitability and robustness of reinforcement learning-based trading strategies. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Redefining Stablecoins from Nominal to Real Value: A Maximum Likelihood Approach | 2026-08-31 | 展开Stablecoins, typically pegged to fiat currencies, cannot achieve true stability because they inherit fluctuations in the underlying unit of account. To overcome this limitation, we introduce a stablecoin pegged to the Maximum Likelihood Value (MLV), a newly defined unit of account derived as the most probable configuration of latent real-value movements that explains observed nominal-value (price) changes. Grounded in inferential statistics and modern portfolio theory, MLV represents the most stable unit of account, as it enforces a zero real return on the minimum-variance portfolio. Empirical results confirm the operational viability of an MLV-pegged stablecoin: MLV can be computed in real time from 500 asset price series and improves annualized returns and Sharpe ratios while substantially reducing turnover in portfolio optimization. |
| 2 | Titans-QFWP: A Regime-Aware Hybrid Quantum Fast Weight Programmer for Portfolio Optimization | 2026-08-29 | 展开We propose Titans-QFWP, a hybrid reinforcement learning architecture integrating a Quantum Fast Weight Programmer with Titans-style memory (Persistence, Surprise, and Forgetting) for adaptive portfolio optimization. To address high-dimensional market features, we introduce an enhanced A3C^2 framework with Hungarian-aligned K-means clustering and scaled log-return rewards. Evaluated on 468 S&P 500 stocks under an Equal-Parameter-Count (EPC) benchmark with approximately 3,000 trainable parameters, Titans-QFWP achieves strong performance (median ARR 0.4260, Calmar 8.5504, IR 0.8427). Ablation results reveal that quantum gating fundamentally reshapes memory component roles, with Persistence supporting drawdown control, Surprise contributing to return generation, and Forgetting providing additional stabilization. By stabilizing these quantum representations, the model enables defensive allocation during market drawdowns while preserving upside potential. |
| 3 | B$^3$-PWL: GPU-Batched Branch-and-Bound for Piecewise-Linear Optimization with SOS2 Constraints | 2026-08-29 | 展开Piecewise-linear (PWL) optimization problems arise in many mixed-integer programming (MIP) optimization applications, including portfolio optimization, workforce scheduling, and resource allocation. But solving them to global optimality remains computationally expensive because branch-and-bound repeatedly solves LP relaxation subproblems. Existing solvers are largely CPU-centric, leaving the scalability of modern GPUs underutilized. Few prior GPU-accelerated branch-and-bound either targets neural network which is not suitable for general PWL optimization, or accelerates only auxiliary subroutines such as strong branching heuristics within CPU-centric MIP solvers. To bridge this gap, we propose B$^3$-PWL, a GPU-centric batched branch-and-bound framework for piecewise-linear optimization with Special Ordered Set of type 2 (SOS2) constraints. Our method solves batches of LP relaxation subproblems concurrently on the GPU using a first-order primal-dual solver, enabled by a specialized batched block-tiled sparse matrix kernel. To complement bound computation, we further introduce a unified feasibility search module that combines an SOS2 repair primal heuristic with a batched feasibility pump to rapidly obtain feasible incumbents and improve pruning efficiency. On a benchmark of 43 PWL-MIP instances, B$^3$-PWL achieves a 9.25x geometric-mean speedup over NVIDIA cuOpt while reaching high-quality feasible incumbents on every tested instance. On a public valve-point unit-commitment benchmark, it further outperforms NVIDIA cuOpt and the open-source CPU solvers SCIP and HiGHS, demonstrating the potential of first-order LP methods as the central engine of GPU-accelerated branch-and-bound. |
| 4 | Generalizing Markowitz Portfolio Optimization by a Quadratic Risk Measure | 2026-08-25 | 展开We show that the key optimization results of the classical Markowitz portfolio selection theory, originally formulated for variance as the risk measure, remain available in explicit closed form under a broader class of strictly convex quadratic risk measures. The proposed framework replaces the covariance matrix with an arbitrary symmetric positive definite matrix and allows additional linear and constant terms, thereby containing various models arising in transaction cost optimization, benchmark relative optimization, covariance regularization, and factor models. Closed-form formulas are obtained for the efficient frontier, the global minimum risk portfolio, the maximum Sharpe ratio portfolio, the Capital Market Curve, the tangency portfolio, and the maximum utility portfolio. In contrast to the classical Markowitz model, the tangency portfolio does not coincide with the maximum Sharpe ratio portfolio, revealing a new geometric phenomenon. A numerical example confirms the derived formulas. |
| 5 | Frontiers in FinTech: Multimodal Foundation Models for Financial Reporting and Decision Science | 2026-08-24 | 展开Financial information no longer arrives in a single format. Research reports come as PDFs, financial statements live in spreadsheets, market trends are captured in images, and policy documents reach analysts as scans, each carrying part of the picture the others cannot supply. Accounting information systems built around single-modality extraction pipelines and rule-based tools therefore struggle to assemble the full picture, slowing financial statement analysis, complicating audit evidence corroboration, and limiting investment decision support. This study presents FinVision, a multimodal large language model that unites vision-language models with domain-specific financial reasoning. Instead of processing documents in isolation, FinVision reads text, tables, and images together, converts them into consistent structured data, and verifies cross-modal agreement, in the same spirit as auditors corroborating evidence from independent sources. The model is trained in two stages, pre-trained on large-scale public financial corpora and fine-tuned on institution-specific investment data, so it can apply established valuation methodologies and audit risk assessment frameworks while outperforming zero-shot and single-stage baselines. A natural-language decision pipeline lets users describe what they need and turns those descriptions into executable workflows, supporting portfolio optimization, real-time risk monitoring, and refinement through multi-turn dialogue. Across 200 listed companies, FinVision reduced valuation error by 19 percent relative to the strongest baseline; a user study with 48 accounting and investment professionals reported a 51 percent reduction in task completion time. These results carry implications for audit automation, financial reporting quality, and more inclusive access to expert-level financial analysis. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | A MOF-reinforced self-foaming sponge for mechanically robust triboelectric membranes with improved resistance to humidity | 2026-08-31 | 展开Porous triboelectric materials offer significant potential for enhancing the performance of triboelectric nanogenerators, yet their practical application is limited by structural instability and humidity-induced performance degradation. In this work, a bio-derived, sustainable polyamide containing disulfide linkages was developed to enable spontaneous formation of a porous dielectric without external templating. Hydrophilic MOF fillers comprising HKUST-1 crystals are incorporated within the porous matrix to reinforce the membrane structure and regulate moisture effects. Mechanical characterization demonstrates that HKUST-1 suppresses pore collapse and improves structural robustness under repeated deformation, while analysis of stress-strain behaviour reveals the critical role of pore stability in achieving stable triboelectric output. In addition, HKUST-1 mitigates humidity-induced charge dissipation by confining water molecules within its framework, giving enhanced triboelectric output stability and reduced performance degradation under increasing relative humidity compared to the neat porous system. This work demonstrates a strategy that integrates self-foamed porous structures, sustainable polymer design, and functional filler reinforcement to engineer mechanically robust and environmentally stable triboelectric systems. |
| 2 | Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates | 2026-08-27 | 展开In neuroevolution, indirect encoding generates neural network connectivity from a compact genome rather than specifying each connection. ES-HyperNEAT automatically discovers where to place hidden nodes by examining CPPN output patterns: it recursively subdivides space using a quadtree, expanding regions where CPPN outputs show high variance. This adaptive approach discovers network topology without manual substrate specification, extending the fixed-grid HyperNEAT framework built on NEAT. However, the quadtree resists tensorization. Each depth level depends on the parent's variance, forcing sequential evaluation. Different CPPNs produce different subdivision patterns, preventing batching. And variable leaf counts are incompatible with JAX's static shape requirement for JIT compilation. Our prior work confirmed these limits at depths exceeding 5, and a JAX reimplementation of the quadtree yielded only marginal speedup despite batched optimizations, motivating the eager reformulation presented here. We present EMR-HyperNEAT, which evaluates all positions at all resolutions up front, then filters using the same variance criterion: ES-HyperNEAT's subdivide_if(var > |
| 3 | Balanced and neat elements in quasi-reductive Lie superalgebras | 2026-08-24 | 展开Let |
| 4 | The Infinite, in Finite Time | 2026-08-24 | 展开Linear-time temporal properties, such as those described by Linear-time Temporal Logic, are typically modelled as sets of infinite traces. Yet, in a run-time verification context, such as when testing or monitoring a system, only a finite prefix of the system's behaviour can be observed. For some properties, these finite prefixes may be definitive---a yes or no answer can be given without further observation. By enriching the semantics of LTL with these definitive prefixes, we give a proper inductive accounting of the semantics of LTL$_3$, a multi-valued variant of Linear-time Temporal Logic for run-time verification applications. The semantic descriptions of LTL$_3$ in previous work are given only in terms of their relationship to conventional LTL. We show that the semantics of LTL and of LTL$_3$ are isomorphic. In addition, we formalise the formula progression evaluation technique, popularly used in runtime verification contexts, and show its soundness and completeness up to finite traces with respect to our semantics. Then, we turn to linear-time properties more generally: using our theory of definitive prefixes, we re-prove the well-known safety-liveness decomposition theorem, and reconstruct the topology of infinite traces. We define monitorability for properties, providing neat topological characterisations for various monitorability classes, and arrange them into a hierarchy. All of our definitions and proofs are mechanised in Isabelle/HOL. |
| 5 | Uncovering Cellular Resolution in scRNAseq via Unbiased Cell and Gene Network Analysis | 2026-08-24 | 展开Conventional annotation of single-cell RNA-sequencing (scRNA-seq) data relies heavily on manual, marker-based thresholding, an approach that can obscure subtle transcriptomic gradients and collapse functionally distinct cell states into broad, heterogeneous populations. Here we apply the Gaussian multi-Graphical Model (GmGM) framework, which jointly infers cell-cell and gene-gene dependency structure from a single scRNA-seq data matrix, to a 10x Genomics PBMC dataset. Ten independent GMGM-Leiden clustering runs were integrated into a robust consensus partition using a soft cluster ensemble approach and benchmarked against reference cell-type annotations. This strategy yielded stable cluster partitions that resolve biologically meaningful sub-populations not distinguished by the reference annotation. In parallel, for each cluster, gene co-expression modules were extracted from the fitted model via consensus Leiden clustering across resolutions, evaluated using standard network metrics, and validated functionally with the Network Enrichment Analysis Test (NEAT), which confirmed non-random enrichment signal. A module-scoring procedure linked network topology to per-cell, per-cluster expression signatures, and a novel extension of GmGM, recovering a shared cell-cell network together with population-specific gene networks in a single model run, was demonstrated in a case study on the CD4+ T-cell population. These results indicate that GmGM provides a unified, reproducible framework for joint cell clustering and gene-network inference, capable of revealing cellular structure beyond that captured by conventional pipelines. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Structure Aware Neural Architecture Search for Mixture of Experts | 2026-08-30 | 展开Neural Architecture Search (NAS) has so far rarely been applied to Mixture-of-Experts (MoE) models, and existing MoE designs leave the alignment between experts and the structure of the data to emerge on its own. We propose an architecture search framework that makes this alignment an explicit search variable: the assignment of data clusters to experts is optimised jointly with the per-expert architectures. We cast the joint problem as a cluster-aware likelihood maximisation, show that it coincides with the incomplete-data maximum likelihood of a latent-variable mixture, and solve it by a generalised Expectation-Maximisation procedure whose otherwise intractable expert-quality term is supplied by an adaptively refined surrogate. We prove that the iterates converge whenever the surrogate errors are summable, and that at every limit point no candidate the search produces improves the true objective. On a heterogeneous image-classification mixture the method recovers the underlying domain partition on 95% of clusters without ever observing domain labels, and on that benchmark and a four-domain time-series forecasting one alike it outperforms the MoE and NAS baselines that likewise use no label information. |
| 2 | NepScript Genesis: Neural Architecture Search for Handwritten Devanagari Digit Synthesis | 2026-08-30 | 展开This paper introduces NepScript Genesis, a Neural Architecture Search (NAS) framework for automated Generative Adversarial Network (GAN) discovery, applied to conditional Devanagari handwritten digit synthesis. We compare five NAS strategies against a carefully constructed Deep Convolutional GAN (DCGAN) baseline (FID=332.28). Architecture selection utilizes a two-stage pipeline guided by a novel domain-aware evaluation metric (Enhanced Score). Results demonstrate that Adaptive Exploration achieves the optimal quality-efficiency trade-off, attaining an FID of 79.12 -- a 76.19% improvement over the baseline -- and the highest mode coverage among the NAS strategies (Recall=0.531) in under one GPU-hour. Furthermore, we demonstrate that incorporating script-specific structural heuristics into the search phase prevents early-stage mode collapse. In a downstream low-resource evaluation, augmenting 250 real training samples per class with GAN-generated digits from the best NAS model improves CNN classification accuracy from 91.0% to 96.5% (+5.5 percentage points), demonstrating that NAS-optimized synthesis produces digits of sufficient quality to benefit practical recognition pipelines when real data is scarce. |
| 3 | Node-wise Feature Encoding for Neural Performance Prediction | 2026-08-28 | 展开As neural networks are increasingly deployed on resource constrained edge devices, accurate prediction of latency and energy is critical for efficient neural architecture search. Existing GNN and transformer based predictors achieve strong results but largely ignore node-level computational cost, limiting their ability to model performance critical operations. To address this, we introduce FeatureFormer, a neural performance predictor that incorporates explicit node-wise encodings of FLOPs, parameter counts, and memory proxies within a gated graph attention architecture. We also present NNEQ, a new large-scale energy consumption dataset that enables unified evaluation of latency and energy prediction. Extensive experiments demonstrate that FeatureFormer achieves state-of-the-art performance across both metrics, including challenging out-of-domain settings. Finally, we show that the proposed encoding is broadly applicable and consistently improves existing predictors with negligible overhead. |
| 4 | Rethinking Expressibility-Trainability Trade-off in Hybrid Quantum Neural Networks | 2026-05-25 | 展开Hybrid quantum neural networks (HQNNs) integrate parameterized quantum circuits (PQCs) within classical networks, where the behavior of the underlying PQCs is often the primary focus of analysis. In this context, expressibility and trainability are widely used to characterize PQC's performance and are commonly assumed to exhibit a trade-off, where highly expressive circuits are more susceptible to barren plateaus. However, the validity of this relationship in HQNNs remains unclear. In this paper, we systematically analyze the expressibility--trainability relationship in HQNNs across varying circuit depths, qubit counts, entanglement topologies. We consider different training configurations, including pure PQCs, quantum-only training in hybrid setting, and full end-to-end training of hybrid models. Our results show that pure PQCs exhibit only a weak and regime-dependent trade-off, while hybrid architectures increasingly disrupt and can eliminate this relationship under full hybrid training. This indicates that classical components reshape the optimization landscape, decoupling trainability from PQC expressibility. We further propose a multi-objective neural architecture search (NAS) framework that jointly optimizes expressibility, trainability, and task performance over a combined classical--quantum design space, revealing different Pareto-optimal solutions under full end-to-end and quantum only training in hybrid setting. different trainability definitions. Our results suggest that hybridization is not just an implementation detail, but a defining factor in the performance of quantum machine learning models. |
| 5 | Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting | 2026-01-30 | 展开We introduce Green-NAS, a multi-objective NAS (neural architecture search) framework designed for low-resource environments using weather forecasting as a case study. By adhering to 'Green AI' principles, the framework explicitly minimizes computational energy costs and carbon footprints, prioritizing sustainable deployment over raw computational scale. The Green-NAS architecture search method is optimized for both model accuracy and efficiency to find lightweight models with high accuracy and very few model parameters; this is accomplished through an optimization process that simultaneously optimizes multiple objectives. Our best-performing model, Green-NAS-A, achieved an RMSE of 0.0988 (i.e., within 1.4% of our manually tuned baseline) using only 153k model parameters, which is 239 times fewer than other globally applied weather forecasting models, such as GraphCast. In addition, we also describe how the use of transfer learning will improve the weather forecasting accuracy by approximately 5.2%, in comparison to a naive approach of training a new model for each city, when there is limited historical weather data available for that city. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Autonomously Acquiring Robot Manipulation Skills with Language-Driven Quality-Diversity | 2026-08-31 | 展开Quality-diversity (QD) algorithms have been gaining traction in robot learning, where diverse motion primitive libraries allow robots to adapt zero-shot to constraints at deployment time. However, such methods typically require expert designers to write the success condition, fitness and diversity metrics, and this strongly limits the robot's autonomy. On the other hand, existing LLM-based reward-shaping techniques allow robots to learn autonomously but only output single high-performing solutions, limiting the robot's adaptability. In this paper, we propose an approach designed to output diverse motion primitive archives by autonomously leveraging quality-diversity algorithms, only requiring a free-form description of the task in common language. To address the difficulty of designing relevant fitness and diversity metrics, we propose an autonomous exploration mechanism able to reliably output sets of functionals covering the fitness and behavior descriptor (BD) space. First, we pose policy exploration as a functional design problem, where the functional spaces are lower-dimensional than the full BD and fitness spaces, and propose an LLM-based exploration scheme to sample from these low-dimensional spaces without any task-specific prompts, fine-tuning or expert intervention. We adapt a multi-BD variant of the MAP-Elites success (MES) algorithm, designed to leverage the heterogeneous BD samples. Finally, through experiments based on the genesis simulator, we show that our method effectively generates archives of diverse motion primitives, outperforming classical QD algorithms with inferred and hand-written parametrizations on a set of |
| 2 | Adaptive Strategy Generation for Boundary Value Exploration Beyond Numeric Inputs | 2026-08-28 | 展开Software behavior often changes abruptly at boundaries between input regions, and these transitions are known to be fault-prone. Boundary Value Exploration (BVE) automates boundary discovery by searching for pairs of similar inputs that nevertheless trigger different program behaviors. Existing automated BVE techniques rely on mutation operators hand-engineered for each input type, or even for each function under test, which has confined their use to numeric inputs. We present ABEX, an agentic LLM-based framework that replaces operator engineering with adaptive strategy generation: specialized LLM agents propose, select, and execute boundary-exploration strategies, guided by execution feedback and a quality-diversity (QD) archive. Because strategies are expressed in natural language, they can encode both type-level and function-specific knowledge, and effective strategies can even be stored and reused. We evaluate ABEX in a black-box setting on 20 functions with numeric, string, array, and mixed inputs. On numeric functions, ABEX outperforms a state-of-the-art QD method on 10 of 11 functions, with average QD-scores 11.7x higher. On non-numeric functions, addressed here for the first time in automated black-box BVE, ABEX discovers domain-aligned boundary behaviors for all subjects. Mutation testing shows the discovered boundaries are fault-revealing: with equally sized test suites, ABEX reaches an average mutation score of 86.2% versus 61.9% for the QD baseline, and kills nine times as many hard-to-detect stubborn mutants. An ablation study identifies adaptive strategy generation as the primary driver of these gains. |
| 3 | TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation | 2026-08-25 | 展开Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the long sampling trajectories and heterogeneous multimodal computation of large models make inference prohibitively expensive. We present TurboT2VA, a distillation and inference framework for accelerating a 19B-parameter joint video-audio model. Large-scale T2VA distillation is challenged by modality-imbalanced optimization, the difficulty of continuous-time consistency training at scale, and the quality--diversity trade-off. TurboT2VA addresses these issues with per-modality normalization and a progressive curriculum comprising discrete consistency warm-up, continuous consistency refinement, and joint consistency--distribution matching. The curriculum first establishes a stable, diverse generation trajectory and only then introduces distribution-level refinement. On LTX-2, four-step distillation reduces generator latency from 50.52s to 2.51s at the standard evaluation resolution of 512$\times$768, achieving a 20.1$\times$ speedup while maintaining strong visual quality, audio fidelity, diversity, and video-audio synchronization. We further develop an architecture-aware inference stack that combines guarded W8A8 and fused operators, padded-text compaction, and modality-aware sparse attention while preserving dense cross-modal and text-conditioning paths. Under the high-resolution deployment setting at 1024$\times$1792, the complete stack reduces generator latency from 318.74s to 5.83s on one NVIDIA H20, achieving a 54.67$\times$ generator-only speedup. Inference code and generation demos are available at https://github.com/thu-ml/TurboDiffusion/tree/main/turbot2va. |
| 4 | Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation | 2026-08-24 | 展开Text-driven human motion synthesis has made substantial development with two core modules of motion representation and generative architecture. For representation, Vector Quantization (VQ)-based methods compress motion data into discrete tokens while latent-based models operate directly in continuous space. However, both of these representations exhibit significant limitations. VQ-based methods suffer from inherent information loss, which compromises the quality, diversity, and generalization of generated motions, while continuous representation on holistic whole-body motion hinders part-level flexibility. For architecture, diffusion and autoregressive diffusion models have demonstrated their superiority, yet the fine-grained controllability over individual body parts is also limited. Thus, we propose a unified spatiotemporally decoupled framework named DeMoDiff, which jointly redesigns representation and architecture. To enhance representation extraction capabilities and offer greater part-level controllability, we present a spatial-temporal VAE that encodes each body joint rather than compressing the whole-body motion into a single latent space. Then, we incorporate spatial-temporal masking and attention mechanisms into an autoregressive diffusion generator, achieving both generative capability and controllable editability. Extensive experiments on the HumanML3D and KIT-ML datasets demonstrate that our model achieves state-of-the-art reconstruction performance and compelling motion generation results. Moreover, our framework demonstrates strong temporal and spatial editing capabilities, further validating its effectiveness. Our project page: https://rex0191.github.io/DeMoDiff/ |
| 5 | Grounded world models in biological organisms and future embodied AI | 2026-07-15 | 展开Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems remain largely based on passive training regimes where linguistic regularities create the scaffold onto which information from other modalities is attached. Conversely, neuroscience and cognitive science suggest that biological intelligence is organized in the opposite way, where grounded world models acquired through interaction with the environment provide the semantic scaffold to which language is attached. Here, we illustrate five examples of neural circuits supporting grounded world modelling, which underlie navigation in physical and conceptual spaces, affordance-based perception and interaction with objects, active perception and exploratory learning, allostatic control and emotion, and the distinction between self- and world-generated outcomes. These examples highlight several features largely missing from current embodied AI, including the role of intrinsic dynamics as a foundation for learning, the centrality of action in aligning these dynamics with the external world, the prominence of autonomous experience and open-ended learning over passive assimilation of externally provided data, and the fact that early predictive and control mechanisms scaffold higher cognitive abilities such as reasoning, conceptual navigation, planning, imagination, understanding others' minds, and communication. Finally, we discuss whether and how principles derived from biological systems may inform future embodied AI, including training regimes based on social interaction to construct world models that are not only grounded but also socially shared and aligned with human norms and values. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs | 2026-08-31 | 展开This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers. Each target is a directed acyclic graph (DAG) of conditional actions with parallel branches, hit-first fallback chains, and per-branch Boolean predicates, encoded in the JSON dialect of a commercial routing platform. We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models. Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the number of interdependent nodes emitted in one pass grows. We therefore move combinatorial graph construction from the model into a deterministic compiler driven by a compact intermediate representation, with a learned registry-selection front end that focuses generation on relevant vocabulary. Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt. On GPT-5.3-chat, the method improves judge validity by 24 percentage points and achieves statistical equivalence to a reasoning model's out-of-the-box quality, although an approximately 8-point frontier gap remains. We also present a deployment path and transferable lessons for structured-generation applications. |
| 2 | POLYFLOW: A Neuro-Symbolic Framework for Static Cross-Language Information Flow Analysis | 2026-08-30 | 展开Modern software systems are commonly constructed in multiple, interacting programming languages. This construction leads to additional, often stealthy vulnerabilities buried in complex information flow due to language interactions. Existing static analyzers are impeded by the heterogeneous semantics of different languages, whereas dynamic approaches suffer from the limited coverage of (available and/or generated) test inputs. In this paper, we develop PolyFlow, a neural-symbolic framework for statically reasoning about information flow across language boundaries, combining large language models (LLMs) and static analysis synergistically. Governed by the control-flow representation of a given multi-language system, PolyFlow leverages LLMs to identify implicit flow facts due to challenging language features, hence augmenting the base representation and then propagating data flow through the system. It tackles inherent barriers (e.g., token limit and hallucination) of LLMs by putting them under careful guidance (e.g., static-analysis-guided scoping, context management, and fact checking), along with a multi-LLM expert panel for negotiated validation. Our experiments on real-world Python-C and Java-C systems show that PolyFlow is cost-effective and superior to various kinds of state-of-the-art baselines, revealing previously unknown cross-language vulnerabilities that are missed by all the baselines. |
| 3 | SYNAPSE: Neuro-Symbolic Visual Thought-to-Text Decoding via Topological Semantic Denoising | 2026-05-27 | 展开Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded during visual perception is translated into coherent natural language descriptions of viewed stimuli. However, existing systems remain highly vulnerable to biological noise, where corrupted neural projections induce hallucinated or semantically unstable generation in frozen language models. We introduce SYNAPSE (Symbolic Neural Alignment for Precise Semantic Extraction), a lightweight neuro-symbolic framework that stabilizes neural text generation through inference-time symbolic regularization. By purifying EEG-derived semantic candidates using commonsense graph structure and latent exemplars, SYNAPSE improves semantic stability without end-to-end LLM fine-tuning. Experiments across popular EEG decoding benchmarks and multiple frozen LLM backends demonstrate consistent gains over unconstrained prompting baselines, robustness under object-label ablation, and performance commensurate with substantially more resource-intensive fine-tuned systems, while preserving biometric privacy by localizing raw EEG processing entirely within the encoder stack. |
| 4 | Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning | 2026-05-11 | 展开Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of works focus on plane geometry while usually fail in solid geometry due to 3D spatial diagrams and complex reasoning. To bridge this gap, we introduce Hilbert-Geo, the first unified formal language framework for solid geometry, including an extensive predicate library and a dedicated theorem bank. Based on this framework, we propose a Parse2Reason method containing two steps of first parsing then reasoning. In the parsing step, we utilize conditional description language (CDL), a formalized language composed of predicates specifically designed to construct geometric conditions, to represent both problem description (natural text) and solid diagrams (visual image). In the reasoning step, we leverage those formal CDL and the theorem bank to perform relational inference and algebraic computation, generating strictly correct, verifiable, and human-readable reasoning processes. Notably, our proposed Hilbert-Geo is also applicable to plane geometry. To advance geometric reasoning, we curate two expert-annotated dataset SolidFGeo2k and PlaneFGeo3k, which are furnished with geometric formal language annotations, solutions and answers. Extensive experiments show that our proposed method achieves the state-of-the-art (SOTA) performance 77.3% in SolidFGeo2k and 84.1% in MathVerse-Solid (one small subset in MathVerse dedicated to solid geometry), substantially outperforming leading MLLMs, such as Gemini-2.5-pro (54.2% on SolidFGeo2k) and GPT-5 (62.9% on MathVerse-Solid). In addition, our method achieves the SOTA accuracy 80.2% in PlaneFGeo3k, demonstrating the generality of the Hilbert-Geo in geometric reasoning. Our code and datasets are released at https://github.com/PremiLab-Math/Hilbert-Geo. |
| 5 | NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering | 2026-02-17 | 展开Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowledge-intensive queries that require precise, structured multi-hop inference. Knowledge graphs provide a compact symbolic substrate for factual grounding, but integrating graph structure with neural models is nontrivial: naively embedding graph facts into prompts leads to inefficiency and fragility, while purely symbolic or search-heavy approaches can be costly in retrievals and lack gradient-based refinement. We introduce NeuroSymActive, a modular framework that combines a differentiable neural-symbolic reasoning layer with an active, value-guided exploration controller for Knowledge Graph Question Answering. The method couples soft-unification style symbolic modules with a neural path evaluator and a Monte-Carlo style exploration policy that prioritizes high-value path expansions. Empirical results on standard KGQA benchmarks show that NeuroSymActive attains strong answer accuracy while reducing the number of expensive graph lookups and model calls compared to common retrieval-augmented baselines. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning | 2026-08-31 | 展开Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while preserving the ability to recognize all seen classes. Recently, pretrained-model-based approaches have become prevalent by adapting a frozen backbone with additional lightweight trainable modules. Existing methods, however, exhibit limitations: task-specific adapters learn explicit per-task representations but are parameter- and computation-inefficient, while LoRA-based merging methods combine per-task LoRA parameters into a single model whose static aggregated weights cause representation interference during inference. To address these problems, we present \textbf{FACET}: task-conditioned \textbf{F}e\textbf{A}ture transformation with \textbf{C}ondition\textbf{E}d feature consis\textbf{T}ency, achieving excellent parameter efficiency while producing highly discriminative features during inference. When continually trained on a task sequence, FACET learns a single shared adapter that employs a dynamic task-conditioned feature transformation, shaping the overall feature distribution of the adapter into a mixture of overlap-reduced task-specific components. On the other hand, we propose an efficient replay-free task-conditioned feature consistency loss, aiming to mitigate catastrophic forgetting of the learned mixture distribution in the adapter's feature space. Even when maintaining only a single adapter, FACET demonstrates robust scalability. On both very long task sequences (e.g., 200 tasks) and standard short task sequences (e.g., 20 tasks), our method achieves superior performance while using significantly fewer trainable parameters and GFLOPs. The code will be made open source upon acceptance. |
| 2 | Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security | 2026-08-30 | 展开Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-horizon tasks. While monolithic prompt engineering and stateless tool-calling paradigms struggle to scale, the field is rapidly converging toward \emph{agentic skills}: modular procedural abstractions that externalize execution knowledge into reusable, executable, and portable artifacts. This paper establishes a unified systems foundation and reference architecture for the agentic skills ecosystem. We formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environments, and systematically delineate the architecture across a nine-stage lifecycle: autonomous discovery, authoring and representation formats, memory storage, dynamic retrieval and routing, composition and orchestration, execution and repair, lifelong adaptation, empirical evaluation, and security governance. We further examine marketplace dynamics, public registries, and emerging adversarial threat vectors, alongside runtime verification and defense mechanisms. Finally, we categorize system implementations across software engineering, operating system navigation, embodied robotics, and scientific discovery, while highlighting critical open challenges in continual learning and benchmark realism. This work establishes agentic skills as a foundational paradigm for building scalable, robust, and verifiable autonomous language agents. |
| 3 | All You Need Is Non-Commutative Words | 2026-08-29 | 展开We represent lexical tokens as unitary matrices and encode each sentence as their ordered product. The noncommutativity of matrix product captures word order without positional encodings (PEs). The same algebra yields several capabilities, including antisymmetric self-attention with no query, key, or value projections, and parallel composition of variable-length text chunks at a reduced attention cost. Furthermore, it provides a canonical-coset readout layer that encodes all true unitary degrees of freedom compactly, while supporting continual learning through nested group extensions that enlarge the operator space with each new task preserving prior representations exactly. Across standard text-classification benchmarks, the method matches or exceeds bag-of-words baselines. Achieving higher accuracy on IMDB and comparable performance on AG News. Notably, this is accomplished by replacing the conventional $\sim$30,000-dimensional vocabulary space with a dense, 64-parameter real-valued encoding, highlighting the expressive efficiency of our parameterization. |
| 4 | Differentiating Minimal-Norm Solutions to Parametric Optimization Problems | 2026-08-28 | 展开Differentiating through parametric optimization problems is central to bilevel programming and meta-learning, often accomplished using approximate implicit differentiation. The implicit function theorem requires inverting a partial Jacobian of the optimality condition, which fails when there are many solutions. Nonetheless, in such cases it is possible to relax invertibility to a strictly weaker uniform range condition, under which it is shown that the minimal-norm solution mapping admits generalized derivatives by using a limiting Tikhonov regularization argument and conservative set-valued field theory. With additional control on the eigenvalues of the generalized Hessians, a pseudoinverse formula is justified. This is established for a class of smooth convex objectives and extended to nonsmooth composite problems. These assumptions are verified for Least-Squares, Huber regression and LASSO. The resulting extension of nonsmooth implicit differentiation to ill-posed settings is examined experimentally on data poisoning and data hypercleaning problems. |
| 5 | Enhancing Web Application Firewalls with Machine Learning for SQL Injection Detection | 2026-08-28 | 展开Detecting SQL Injection (SQLi) attacks ranks among the most critical challenges in web application security. This research conducted a systematic literature review to identify the research gaps in this domain and responsively designed and optimised a DistilBERT-Stacked Ensemble pipeline to improve detection efficiency and robustness while reducing false-positive and false-negative rates. Comprehensive pre-processing and tokenisation were performed, DistilBERT embeddings were extracted, and machine-learning and ensemble classifiers were trained and ranked on accuracy, precision, recall and F1-score. The three best performers (Logistic Regression, XGBoost and SVM) were combined through a neural meta-learner to form a stacked ensemble. The ensemble was hardened with adversarial examples generated by the Fast Gradient Sign Method (FGSM) and tuned with Optuna. The optimised ensemble achieved 99.81% across all reported metrics, closely comparable to the strongest single model (DistilBERT SVM, 99.82%). On the evaluation platform used in this study (Section 3.8), the ensemble classified the full test set in 0.0136s against 1.896s for DistilBERT-SVM, an approximately 140-fold reduction in measured inference latency, while retaining 99.77% accuracy under a single-step FGSM attack. The contribution is the design and validation of a SQLi detector performing with state-of-the-art accuracy at real-time speed and with demonstrated robustness to a single-step FGSM attack, rather than a marginal gain in accuracy. Sensitivity analysis further confirmed the stability of the model. These findings highlight the value of adversarial training and stacked meta-learning in building robust Web Application Firewalls (WAFs) for SQLi detection. For open validation, the dataset, test sets and models are made available at https://github.com/mlily2024/Final-project-SQL-injection-pipeline. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents | 2026-08-22 | 展开Humans have multiple levels of temporal abstractions on daily interaction and thinking, such as concept perception and strategic planning. Inspired by this nature, we propose a two-level hierarchical reinforcement learning (RL) framework for conversational agents, bridging the gap between previous token-level or utterance-level RL methods. Developed on a two-level MDP, the token-level response decoding is conditioned on the utterance-level action, the explicit textual strategies. Based on theoretical derivation and efficiency consideration, we use DQN to solve the high-level critic and PPO to solve the low-level actor-critic. To further alleviate the reward sparsity and facilitate the convergence, we also design the dual-granularity reward mechanism, in which the utterance-level satisfaction score is integrated with token-level intrinsic motivation and K-L penalty. Experiments on both daily and emotional support conversations show that our method outperforms versatile baselines in strategy determination and response quality. Our implementation is available at https://github.com/AaronJi/ToSCA. |
| 2 | tinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained Millirobots | 2026-08-18 | 展开In this study, we investigate developmental mechanisms that enable small, resource-constrained systems such as cm-sized millirobots to autonomously explore, learn, and adapt their capabilities throughout their lifespan. Reinforcement learning algorithms guide the agent's skill acquisition and adaptation through the interplay of our proposed tinyDSM, which integrates intrinsic motivation and fitness-based assessment. We strive for minimal, hard-wired skills while encouraging the open-ended development of new skills. A key emphasis in our approach is to encode minimal a-priori general knowledge, which serves as a foundational starting point for the system as it further learns system-specific dependencies from the initial knowledge provided. Thus, by design, our approach attempts to cover very generic application domains. The methodology is based on (a) developmental mechanism with intrinsic motivation, and (b) a cognitive architecture (knowledge, reasoning, learning), while (c) utilizing minimal resources. It uses a hierarchical knowledge graph and kinematic reasoners to model and evaluate simple and advanced motion related skills. In our experiments, we use a resource-constrained millirobot with a volume of 36 cm^3 with a Raspberry Pi Pico 32-bit microcontroller (RP2040) that integrates all described features and capabilities except the camera system in 9 kB. Starting with learning the most elementary motor skills the millirobot autonomously progresses from simple linear and angular movements to complex geometric patterns within 15 minutes. To complement the physical experiments, we perform a simulation-based analysis that enables systematic comparisons across learning algorithms and intrinsic motivation parameters. |
| 3 | Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation | 2026-08-11 | 展开Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences while keeping each client's data private during the learning of each client's policy. Many current methods for PFRL rely heavily on exploiting existing reinforcement learning reward signals to derive an optimal policy for each client, thereby neglecting exploration in non-stationary or sparse-reward environments. In this work, we introduce a new exploration-driven framework, Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation (EDPFRL-IM), that leverages an inherent curiosity-driven exploration at each client to promote local exploration and protect client privacy. Furthermore, to facilitate policy discovery via exploration in previously unexplored state spaces, clients add an intrinsic random network distillation (RND) signal to their extrinsic reward. Additionally, the server does not have access to clients' raw experiences or local gradient estimates; instead, the server sends global exploration priors and collects minimal novelty summaries from each client to enable both diverse and coordinated exploration among clients. Experiments in benchmark environments show that our framework outperforms average PFRL benchmarks in policy personalization and sample efficiency, primarily in delayed and sparse reward systems. Overall, EDPFRL-IM enables the integration of a flexible exploratory learning structure into federated reinforcement learning systems while preserving client privacy. |
| 4 | The Evolutionary Origin of Values: implications for AI alignment, sentience and existential risk | 2026-08-04 | 展开AI systems based on Large Language Models (LLMs) have prompted fears that they may harbor hidden goals, seek to dominate or eliminate humanity, or even suffer as sentient beings. We address these concerns by tracing the evolutionary origin of value in biological organisms. Values emerge from autopoiesis: living systems must actively maintain themselves against perturbation and dissipation. Natural selection has equipped them with hierarchies of "vicarious selectors" that guide their behavior toward fitness. LLMs, by contrast, are allopoietic and allotelic: they produce outputs for others, and their goals derive from user prompts rather than an autonomous drive. They lack the intrinsic motivation for self-preservation, dominance, or resource competition that underlies existential-risk scenarios, and the embodied vulnerability required for feeling or suffering. Still, because LLMs learn statistical patterns from human-generated text, they implicitly absorb human values as well as knowledge, allowing them to focus on what is relevant. That is why the "orthogonality thesis" separating intelligence from values does not apply to them. Such separation would in fact expose any intelligence to the frame problem: the combinatorial explosion of the search space that makes any realistic utility function physically uncomputable. That also precludes the convergence of instrumental values thesis. We conclude that the real alignment challenge lies not in preventing rogue AI agency, but in ensuring LLMs intelligently apply learned ethical values. |
| 5 | Producing Policy Recommendations: from Statistical Decision Theory to Empirical Practice | 2026-07-31 | 展开Applied research in economics is intrinsically motivated by broad normative objectives. However, it is not obvious how a researcher should direct their efforts to produce evidence toward such objectives. This paper reviews recent theoretical developments on research design for policy choice and provides new tools applied researchers can use to guide their design choices and communicate their policy recommendations. First, I focus on theoretical contributions in econometrics and provide a general framework that nests all the contexts and results reviewed using a coherent notation and narrative. Then, I present two diagrams applied researchers can use to navigate the theoretical literature starting from concrete scenarios to make thoughtful design choices. Finally, I introduce a new R package that produces one table and two figures applied researchers can plug in their `policy implications' section to provide evidence on the performance of different policy recommendations coming out of their study. The use of such tools is illustrated with an example in development economics. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Beyond Global Realism: Virtual Try-On Evaluation and Optimization with Dimension-wise Garment Fidelity Assessment | 2026-08-30 | 展开Virtual try-on (VTON) requires not only realistic generation but also faithful preservation of garment characteristics. However, existing evaluation metrics such as PSNR, SSIM, KID and FID struggle to measure the consistency between the generated and reference garments, particularly in capturing the multi-dimensional characteristics of garment fidelity. To address this, we propose DAT: a Dimension-wise Assessment framework for virtual Try-on, which decomposes garment consistency into seven interpretable dimensions: silhouette, color, neckline and sleeve shape, major decoration and structure, material texture, fine-detail fidelity, and logo preservation, each formulated as a discrete attribute-level prediction task. To train this specialized assessment model, we adopt a two-stage learning paradigm comprising large-scale weak supervision on 50K samples, followed by refinement on 10K higher-quality annotations obtained via multi-model voting. Furthermore, we employ weighted cross-entropy loss to mitigate the severe label imbalance inherent across evaluation dimensions. Beyond its role as an evaluation framework, the assessment model can be integrated into reinforcement learning optimization of Qwen-Image-Edit for VTON, where dimension-wise rewards are adaptively aggregated to emphasize under-optimized aspects during training. Experimental results show that our method (8B parameters) achieves state-of-the-art performance in terms of balanced accuracy, SROCC, and PLCC, outperforming strong proprietary models such as Gemini-3.1, Qwen3.7-plus, and GPT-5.5, while also serving as an effective optimization signal for reward-guided VTON generation |
| 2 | A Unified Perspective on Conformal Prediction and Wasserstein Distributionally Robust Optimization for Uncertainty Quantification | 2026-08-30 | 展开Uncertainty quantification from finite data is central to machine learning, optimization, and automation systems, where decisions must remain reliable under limited samples and test-time distribution shift. Conformal prediction (CP) and distributionally robust optimization (DRO) offer two complementary approaches: CP constructs data-dependent prediction sets with distribution-free finite-sample validity under exchangeability, while DRO optimizes worst-case performance over an ambiguity set around an empirical distribution. We develop a unified probabilistic perspective on CP and DRO by viewing both as ways to turn finite calibration data into a data-dependent quantile estimator that a test score falls below with high probability. From this perspective, CP and DRO correct the empirical quantile along two coordinates of the same family of estimators: CP inflates the quantile level, whereas DRO shifts the quantile value through an ambiguity radius. Both methods provide the same calibration-conditional guarantee for the true distribution, requiring the target coverage to hold with high probability over the calibration sample. Their constructions differ, however: CP uses a closed-form, distribution-free level correction, while DRO uses a value-space correction whose certified radius depends on properties of the unknown distribution and additionally guarantees coverage uniformly over the ambiguity set. This distinction emerges in the tails of the score distribution. Because CP relies on sparse upper-tail order statistics of the calibration samples, its level inflation barely moves the estimator when those samples are dense near the target quantile but overshoots when they are sparse, whereas a well-chosen DRO radius corrects in value space and may avoid this overshoot. |
| 3 | Learning-Augmented Heuristics: Simple, yet Smart, Robust and Interpretable Cache Eviction | 2026-08-28 | 展开Caching is widely used across the system stack to improve performance and efficiency, with eviction algorithms at its core. Existing cache eviction policies fall into two broad categories: static heuristics (e.g., 2Q, S3-FIFO) and smart algorithms (e.g., ARC, LRB). Smart caches can adapt to workloads and have the potential to achieve higher efficiency and robustness than static heuristics. However, we find that existing smart caches suffer from objective mismatches and instability. We introduce Learning-Augmented Heuristics (LAH), a framework that learns the cache-level parameters of static heuristics. By decoupling the data and control planes, LAH supports simple, high-speed data reads and writes on the data plane, while performing occasional asynchronous learning on the control plane using cache-level features. We demonstrate the effectiveness of LAH through S4-FIFO, a Smart S3-FIFO cache eviction algorithm. We pre-train a single model on 4,140 production traces and embed it in S4-FIFO to learn optimal cache parameters. On 1,035 evaluation traces, S4-FIFO improves the mean efficiency by 26% compared to S3-FIFO and by 8% compared to 3L-Cache, the best state-of-the-art algorithm. S4-FIFO is also robust---increasing miss ratio over FIFO by 0.8% on the worst trace, whereas 3L-Cache increases FIFO's miss ratio by 8.8%. Finally, S4-FIFO's decisions are also interpretable: a language model can provide a rationale for why a particular configuration was chosen. |
| 4 | Self-Supervised Auxiliary Task Discovery for Stable Reinforcement Learning in Stock Trading | 2026-08-16 | 展开Reinforcement learning has gained increasing attention as a data-driven approach for stock trading. However, learning a policy that is both profitable and stable remains challenging due to non-stationary market behaviour and noisy reward signals. Auxiliary tasks are often used to improve representation learning and stabilize training, yet they are usually designed manually and depend heavily on prior assumptions about targets and prediction horizons. Such fixed designs may not remain suitable across changing market regimes. In this work, we propose a self-supervised framework that automatically discovers auxiliary tasks to support reinforcement learning for stock trading. The auxiliary tasks are formulated as General Value Functions so that their predictions enrich the learned state representation and assist policy optimization. The framework consists of two networks. The main network learns the trading policy along with the auxiliary predictions, while the secondary network generates the definitions of auxiliary tasks through learned cumulants and discount factors. These tasks are updated using a meta gradient mechanism that accounts for their long-term impact on trading performance and improves training stability. We evaluate the proposed approach across four major equity indices: DJI, FTSE, Sensex, and TAIEX. The empirical results demonstrate that automatically discovered auxiliary tasks lead to more robust learning and improved trading performance compared to existing baselines. |
| 5 | Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization | 2026-08-13 | 展开Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. We develop an $\textbf{A}$DMM-$\textbf{I}$nspired $\textbf{M}$omentum (AIM) framework based on residual-penalty variable splitting, which interprets momentum as a multiplier-like correction driven by the splitting residual. AIM recovers the exponential moving average of gradients from an ADMM-style multiplier update and separates two mechanisms that are usually intertwined in practical optimizers: the residual penalty determines the update geometry, whereas the approximation of the objective-related subproblem determines the acceleration form. Building on AIM, we propose $\textbf{R}$elativistic $\textbf{A}$daptive gradient $\textbf{D}$escent with $\textbf{A}$ccelerated $\textbf{R}$esidual (RADAR), which combines relativistic adaptive geometry, decoupled residual correction, and second-order momentum filtering to improve the update direction and momentum estimation. We establish stochastic convergence through a variance-perturbed Lyapunov drift analysis. Experiments on supervised vision learning, language modeling, and reinforcement learning show that RADAR achieves consistent improvements over strong adaptive optimizer baselines. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | SurgSkill-Bench: A Benchmark for Multimodal Surgical Skill Assessment | 2026-08-31 | 展开Objective assessment of surgical technical skill is important for surgical training and structured feedback, but current workflows remain dependent on labor-intensive expert review. Existing automated approaches primarily focus on visual inputs and provide limited support for jointly studying operative performance, structured skill scores, and evaluator feedback. We introduce SurgSkill-Bench, an initial video-score-text benchmark-style dataset containing 214 surgical training simulation videos, six-dimensional OSATS scores, and expert free-text comments. We define two evaluation settings: video-only OSATS prediction for automated assessment and post hoc expert-comment-assisted prediction, where evaluator comments are available as auxiliary information. We provide controlled baseline experiments using representative frozen visual backbones, content-adaptive key-frame sampling, and a simple video-text co-attention fusion module. Under internal video-level validation, content-adaptive sampling improves video-only performance in this dataset, while evaluator comments provide additional score-related signal in the assisted setting. The best mean AUROC reaches 0.88 under dataset-specific median dichotomization. We further discuss evaluation constraints related to dataset scale, metadata completeness, and the interpretation of comment-assisted prediction. Code will be released publicly at a later date. |
| 2 | Event-Inference Reliability for Physical AI over Wireless Networks | 2026-08-31 | 展开Wireless-enabled physical artificial intelligence (physical AI) systems call for a shift from reliable data delivery to reliable inference of physical events. The relevant question is not only whether packets arrive, but whether the set of cues available at the decision node, i.e., the evidence, is sufficiently timely and informative to support reliable inference about the event. Accordingly, this paper develops a framework in which event-inference reliability (EIR) is determined jointly by cue informativeness, cue availability, and temporal admissibility. The latter is determined by the downstream task requirement and represented through the usefulness horizon. We define event-inference error ratio (EIER) as the normalised residual event uncertainty after incorporating admitted cues, and EIR as the corresponding normalised uncertainty reduction, both conditioned on decision-node context. We further distinguish the evidence-limited Bayes benchmark from operational performance of a particular inference engine and derive an entropy-based lower bound on the minimum achievable event error from the same decision-node information. The framework then enables an event-aware wireless design interface for cue prioritisation, cue-reliability allocation, and event-inference coverage characterisation. A multiclass indoor activity-inference study combining empirical cue likelihoods with wireless delivery instantiates the framework and demonstrates how it characterises EIR under finite usefulness horizons. |
| 3 | OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification | 2026-08-30 | 展开Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burdened by complex, multi-stage training pipelines and heavily rely on auxiliary regularization to prevent prototype collapse. To overcome these limitations, we introduce Orthonormal Prototype Alignment Learning (OPAL), a single-stage, end-to-end framework that simplifies interpretable classification. Our approach anchors the latent space using predefined orthonormal bases, embedding each class within a dedicated subspace spanned by fixed part-prototypes. To achieve precise part localization, OPAL enforces spatial competition across feature maps. This mechanism isolates sparse, discriminative regions, directing each prototype to consistently attend to the same semantic concept across different images. By framing classification as a direct representation alignment task, our method eliminates the need for auxiliary losses. Extensive experiments on fine-grained benchmarks demonstrate that OPAL outperforms both its non-interpretable counterparts and state-of-the-art part-prototype methods, delivering granular visual explanations by explicitly revealing the specific image regions driving every prediction. Code is available at https://github.com/ilancarretero/OPAL. |
| 4 | Blind Stereoscopic Omnidirectional Image Quality Assessment Using Predictive Coding Hierarchy | 2026-08-28 | 展开Stereoscopic omnidirectional images (SOIs) have provided users with newly immersive quality of experience in virtual reality environments. However, developing efficient and accurate perceptual quality assessment metrics for SOIs remains challenging due to many factors such as freely changeable field of views and binocular vision. In this paper, based on the characteristics of the human visual system (HVS), we propose a Predictive Coding Hierarchy-inspired metric (PCH) for blind/no-reference stereoscopic omnidirectional image quality assessment. Motivated by the viewing process of SOIs, the proposed PCH includes a local cyclopean perception module, a global predictive perception module, and a visual quality regressor. First, observers browse different spherical sceneries from viewports, and aggregate the local visual information to infer the perceptual quality of SOIs. Therefore, we extract various viewports, followed by cyclopean conversion and saliency detection to approach the perception and attention of the human brain. After the local aggregation, viewers then infer the global scene in their minds. Based on the binocular mechanism, we fuse left and right views to perform predictive coding hierarchy modelling. Finally, the visual quality regressor is exploited to obtain the ultimate quality score related to both local and global perceptual cues. Extensive experiments demonstrate that the proposed PCH achieves competitive and consistently improved performance compared with state-of-the-art quality assessment methods. |
| 5 | PredVLA: Predictive Sensorimotor Modeling for Sub-Million-Parameter Robot Manipulation | 2026-08-27 | 展开Large pretrained vision-language-action models achieve strong robot-manipulation performance, while compact alternatives have largely pursued efficiency by compressing the prevailing observation-to-action paradigm. We investigate whether predictive sensorimotor modeling can make more effective use of a limited parameter budget than direct observation-to-action mapping. We present PredVLA, a language-conditioned predictive-coding policy with only 0.68 million trainable network parameters and no robot-data pretraining. Its hierarchical recurrent dynamics predict visual features and proprioception, while observations influence latent state only through prediction-error-driven online inference. On LIBERO, PredVLA achieves an 86.9% mean success rate across the three short-horizon suites and 75.4% across all four suites. Under a controlled comparison using the same frozen front end, demonstrations, action decoder, and evaluation protocol, PredVLA achieves 3.7x and 7.4x the three-suite mean success rates of parameter-matched Transformer and LSTM behavior-cloning policies, respectively. A mechanism-by-mechanism transition to the recurrent behavior-cloning baseline shows that replacing the predictive pathway with direct observation input produces the largest single performance drop, accounting for approximately |
感谢原始项目 @zezhishao/DailyArXiv 提供的灵感。