Searcharxiv⌕ Search

arXiv subjects

Yue Wang

Publications and source records attributed to Yue Wang.

At least 91 records · Page 5Linked to original sources
arXiv2026

Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR

Reinforcement learning with verifiable rewards (RLVR) improves vision-language models (VLMs) by optimizing outcome rewards derived from final answers. However, such outcome-only rewards do not tell the model which image regions justify an answer. For questions that require visual grounding, these rewards cannot distinguish responses supported by relevant visual evidence from those produced by language-prior shortcuts or lucky guesses. We introduce EASE (Evidence-Anchored Spatial Attention), which augments multimodal RLVR with visual-evidence process supervision. EASE converts annotated evidence regions into a smoothed visual-token target and uses it to guide response-to-image attention during RL training, but only on high-reward trajectories. The annotations are used solely as privileged training labels, while inference requires only the original image and question. Across Qwen2.5-VL-7B, Qwen3-VL-4B, and Qwen3-VL-8B, EASE raises average scores over DAPO by 2.5 to 3.1 points on perception, hallucination, visual math, and multimodal reasoning benchmarks. Diagnostics and ablations show that EASE better aligns visual attention with annotated evidence regions.

cs.CV↗
arXiv2026

Revisiting Topological Graphs for Macro Action based Closed-loop Reinforcement Learning of Vision Language Navigation in Continuous Environment

Vision-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow natural language instructions through unseen environments. Existing imitation learning (IL) pipelines struggle in this closed-loop setting: behavior cloning suffers from distribution shift, and DAgger's expert actions become ambiguous upon trajectory deviation. While Reinforcement Learning (RL) offers a natural paradigm to address this, directly applying RL to micro action spaces is sample-inefficient due to reward sparsity. To overcome this bottleneck, we reformulate VLN-CE as a Hierarchical Markov Decision Process (MDP), explicitly decoupling high-level planning from low-level control. By abstracting the environment into a topological graph, our high-level policy operates on a macro action space of frontier nodes, with a training-free low-level controller acting as its state transition, which significantly compresses the decision horizon and makes closed-loop RL tractable. To support RL optimization on the macro MDP, we propose an action-aware value head to effectively evaluate state values under the dynamic frontier action space, powering a graph-based PPO. Extensive experiments demonstrate the effectiveness of our architecture. Finally, our model achieves state-of-the-art performance on the R2R-CE and RxR-CE benchmarks.

cs.RO↗
arXiv2026

RuleMem: Active Rule Memory for Long-Term Conversational Agents

Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechanisms primarily treat past information as \textit{passively} stored facts, leading to semantic gaps and unreliable reasoning. To address this limitation, we propose RuleMem, a rule-based memory framework that induces reusable logical rules from historical interactions to \textit{actively} guide both evidence retrieval and reasoning. Specifically, RuleMem constructs natural-language Horn clauses from conversations and validates them via a Rule Perplexity Consistency (RPC) mechanism. These induced rules enable the retrieval of semantically distant evidence while providing an explicit logical structure for answer generation. We conducted a comprehensive evaluation of RuleMem on two long-term conversational benchmarks, LoCoMo and LongMemEval_s*. In a rigorous comparison against 14 baselines on LoCoMo, RuleMem achieved the highest accuracy, exceeding the baseline average by 27.47 points (a 54.3% relative improvement).

cs.CL↗
arXiv2026

Structured Edge-Aware Graph Attention Network for Transmitter-Resolved Pointwise Radio Map Estimation

Transmitter-resolved radio map estimation (RME) from sparse measurements is essential for obtaining source-specific received-power information in wireless networks. This paper proposes SeaGAT, a Structured Edge-Aware Graph Attention Network for transmitter-resolved pointwise RME. For each target--transmitter query, SeaGAT constructs a target-centered graph from a bounded transmitter-specific reference set. Reference representations generate messages and provide measurement context to attention scoring, whereas structured edge representations encode explicit query--reference relations and enter only the scoring procedure. Within a fixed sampled support, we derive a differential identity that decomposes local variation of the evidence aggregate into attention-weighted message changes and score-induced weight redistribution; edge-relation perturbations act only through the latter, whereas a reference-RSS perturbation can affect both pathways. The bounded star graph yields graph-side computation linear in the selected reference count $K$, while support-truncation analysis bounds deviation from the same-parameter full-support aggregate by the product of omitted attention mass and cross-support message diameter. Extensive computer simulations evaluated with ray-tracing dataset show that SeaGAT achieves the lowest mean RMSE compared with baselines; replacing learned attention with uniform weights increases RMSE by $1.58$--$2.14$~dB. It also maintains stable transfer across the tested urban-layout and carrier-frequency shifts.

eess.SP↗
arXiv2026

Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks

Leak localization is usually evaluated as forced-choice prediction, although sparse hydraulic observations may not justify excavation. Here, we quantify a pressure-information limit and use it to recast localization as selective, evidence-gated decision-making. A physics-grounded executor falsifies competing leak, demand, sensor and valve hypotheses in a hydraulic twin. Deterministic code computes every number and every acceptance predicate; an independent large language model auditor may add a rejection but never overturn a failed check. Forced retrieval placed only 95 of 300 leaks in the correct zone. Across 550 mixed events, the gate acted on 223 (214 correct); on a third-party 33-leak benchmark, all four accepted events were correct. In a replay of 194 audited City D repairs, the pressure tier authorized five excavation recommendations, three matching the repaired district, while the district-inflow tier returned the correct district for 85 events. Observability limits with machine-checkable abstention enable auditable utility intervention.

cs.AI↗
arXiv2026

GAFT: Geo-Anchored Fine-Tuning for Hazard Identification from Rare Failures

Off-road navigation can fail when physical structures induce irrecoverable states such as high-centering or entrapment, requiring human interventions. Identifying these structures is crucial, yet challenging. Such failure events are rare and costly to collect, resulting in limited training data. Moreover, the collected data associate frames with outcomes, but do not indicate the visual cues responsible for the failure. Learning directly from these data can therefore exploit scenario-specific visual cues, leading to poor generalization. We propose \textbf{Geo-Anchored Fine-Tuning (GAFT)}, a parameter-efficient method that adapts a vision foundation model with a geometry-derived prior. It guides LoRA adaptation by aligning a spatial attention-rollout map with the geometry prior, while preserving pretrained representations. On an intervention-verified forest hazard benchmark, across ten independently trained adaptations, GAFT consistently outperforms frozen DINOv2 and supervised PEFT baselines, improving the repeated leave-one-scenario-out mean $F_2$ from 0.0607 to 0.3757 with statistical significance under paired analysis. Within these independently trained models, the best-performing GAFT model achieves a repeated-LOSO $F_2$ of 0.570. Code and benchmark: https://github.com/Xu-Yanran/geo_anchored_fine_tuning

cs.RO↗
arXiv2026

Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification

Imbalanced time series classification is often addressed by changing the training distribution, objective, logits, or final threshold. These interventions address important biases, yet leave a representation-level question unmeasured: after minority support is reduced, does a learned feature space remain locally reliable around minority regions? We identify a training-local geometry failure: under imbalance, minority cases can lie in sparse, rest-dominated, or mixed feature-space neighborhoods, even when the representation retains useful global class structure. To diagnose and repair this failure, we propose Local Reference Geometry (LRG), a lightweight post-hoc feature augmentation module applied between a fixed feature extractor and the classifier head. Using training features only, LRG measures local exposure and class-mixture risk, then augments each fixed feature with a standardized signed displacement from nearby training geometry and an LDA-projected residual summary. On controlled UCR/Bake Off Redux imbalance benchmarks, paired raw-versus-LRG comparisons show gains for learned, pretrained, and fixed representations, including when LRG is combined with training-level interventions and post-encoder classifier corrections. Ablations show that the gain comes from the signed local residual appended to the original feature, rather than from generic prototype distances, affinity features, scalar statistics, or VLAD-style codes. Further analyses support the proposed local-geometry failure hypothesis: minority neighborhoods become increasingly rest-exposed under imbalance, training-local risk identifies error-prone regions, and LRG gains concentrate in those high-risk regions.

cs.LG↗
arXiv2026

MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning

Multi-objective discrete optimization problems, such as molecular design, pose significant challenges due to their vast and unstructured combinatorial spaces. Traditional evolutionary algorithms often get trapped in local optima, while expert knowledge can provide crucial guidance for accelerating convergence. Large language models (LLMs) offer powerful priors and reasoning ability, making them natural optimizers when expert knowledge matters. However, closed-source LLMs, though strong in exploration, cannot update their parameters and thus cannot internalize experience. Conversely, smaller open models can be continually fine-tuned but lack broad knowledge and reasoning strength. We introduce Multi-LLM Collaborative Co-evolution (MCCE), a hybrid framework that unites a frozen closed-source LLM with a lightweight trainable model. The system maintains a trajectory memory of past search processes; the small model is progressively refined via reinforcement learning, with the two models jointly supporting and complementing each other in global exploration. Unlike model distillation, this process enhances the capabilities of both models through mutual inspiration. Experiments on multi-objective drug design benchmarks show that MCCE achieves state-of-the-art Pareto front quality and consistently outperforms baselines. These results highlight a new paradigm for enabling continual evolution in hybrid LLM systems, combining knowledge-driven exploration with experience-driven learning.

cs.LG↗
arXiv2026

Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees

Random feature methods provide a scalable approximation to kernel ridge regression (KRR), but the regularization parameter that yields the oracle learning rate depends on unknown smoothness and capacity parameters. In this work, we propose a neighboring early-stopping rule for adaptive regularization in KRR with random features (KRR-RF). The method uses a grid that is uniform in inverse regularization and compares only adjacent estimators, reducing the number of discrepancy comparisons relative to standard all-pairs Lepskii-type procedures. Both the neighboring discrepancy and its empirical complexity term can be computed directly in the random feature space, without constructing the exact kernel Gram matrix. We establish a high-probability comparison bound for neighboring KRR-RF estimators and show that, under standard source and capacity conditions together with suitable grid and random feature budget conditions, the selected estimator attains the oracle polynomial learning rate up to logarithmic factors. The result allows the regularization parameter to be selected without prior knowledge of the source and capacity exponents and covers both well-specified and partially misspecified regimes. Our analysis is based on an empirical random feature effective dimension that connects the observable stopping threshold with the population complexity of the random feature model. Simulation and real-data experiments illustrate the prediction performance and computational behavior of the proposed method in comparison with standard tuning procedures.

stat.ML↗
arXiv2026

MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection

Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution channel for malicious behavior, yet existing malicious-Skill datasets are fragmented across sources, artifact formats, evidence regimes, and benign coverage; duplicated and structurally related content further complicates direct aggregation and evaluation. We present MaliciousSkillBench, a comprehensive benchmark for malicious Agent Skill detection. We consolidate 13 public sources, 11 of which contribute Core malicious artifacts, and reduce 8,414 raw malicious records to 7,539 normalized-unique identities in 4,588 operational structural families. After conservative cross-label conflict exclusion, the primary benchmark contains 9,740 Skills: 7,505 malicious and 2,235 benign. To characterize its coverage, we harmonize 11 attack categories for 4,983 malicious identities with supported source-native mappings and find substantial differences in threat composition across sources. We then evaluate three learned text detectors and three off-the-shelf Skill scanners. Learned detectors achieve 0.882-0.932 Random Macro-F1 but only 0.653-0.665 under Source-Disjoint evaluation; the strongest word TF-IDF SVM scores 0.932/0.916/0.665 on Random/structural-disjoint/Source-Disjoint while retaining 95.6% malicious recall but producing 62.4% benign FPR on held-out sources. Off-the-shelf scanners occupy different but also unsatisfactory operating regimes, reducing false positives only at the cost of sharply lower malicious recall. Together, these results show that reliable malicious-Skill detection requires both broader cross-source benchmark coverage and evaluation that jointly measures attack detection and benign over-flagging.

cs.CR↗
arXiv2026

Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model

Vision-language-action (VLA) models can follow natural-language (NL) task instructions, but such instructions may not precisely specify safety-critical or spatiotemporal requirements on the resulting behavior. We introduce Logic-VLA, a formal-requirement-aware VLA that conditions on Signal Temporal Logic (STL) specifications supplied at inference time. Logic-VLA uses a syntax-graph-based STL encoder pre-trained to capture temporal logic semantics. Policy adaptation proceeds in two stages: STL-conditioned supervised fine-tuning on satisfying demonstrations is followed by trajectory-level preference optimization over matched satisfying-violating rollout pairs using a flow-matching surrogate for Identity Preference Optimization. This formulation improves formal requirement satisfaction while preserving the nominal NL task. We evaluate Logic-VLA in closed-loop quadcopter navigation simulation across randomized photorealistic environments and test generalization to STL formulas unseen during training. Across the evaluation benchmarks, Logic-VLA improves STL satisfaction rate over an STL-blind base policy by 24.8 to 40.7 percentage points (pp) while reducing nominal NL task success by at most 1.8 pp, showing that a single VLA can adapt its behavior to varying formal requirements without requiring a separate policy for each specification.

cs.RO↗
arXiv2026

Calibrated Predictive Safety for Heterogeneous Robots: An Action-Conditioned JEPA Framework with Model-Based Safety Shields

Vision-language-action policies generalize broadly but provide no execution-time guarantees; classical model-based planners respect kinematic and geometric constraints but generalize poorly. We study whether an action-conditioned Joint-Embedding Predictive Architecture (JEPA) world model can predict, before execution, both task progress and physical risk for candidate action chunks, and whether coupling these predictions to an embodiment-specific model-based safety shield yields a deployable pipeline for heterogeneous robots. We propose a receding-horizon decision pipeline: (1) a proposer produces K candidate action chunks; (2) an action-conditioned JEPA rolls each candidate forward in a frozen-encoder latent space conditioned on an embodiment embedding; (3) calibrated risk and progress heads score each rollout and report uncertainty; (4) a deterministic per-embodiment safety shield filters inadmissible candidates; (5) a fallback ladder handles empty-admissible-set cases. The learned ranking only reorders admissible candidates; enforcement guarantees come from the deterministic shield and fallback ladder. We evaluate with a pre-registered protocol in simulation (LIBERO-Long). In 600-episode configurations the full framework improved success over a shield-only baseline and reduced collision false negatives at matched recall. Deployment-efficiency measurements on target on-robot and edge accelerators are included. Real-robot experiments and an offline reranking significance test remain future work; see the paper for disclosures.

cs.RO↗
arXiv2026

Evidence of self-organized criticality in the prompt emission of a bright gamma-ray burst

Gamma-ray bursts (GRBs) are the most energetic explosive events in the Universe, yet the physical mechanism of their prompt emission remains a mystery. Especially, it is unclear whether the energy dissipation mechanism in the GRB jet is dominated by kinetic energy or magnetic energy. Here, we studied the pulses in the prompt emission of the second brightest GRB to date, GRB 230307A, which was accurately measured by the Gravitational wave high-energy electromagnetic counterpart all-sky monitor (GECAM), with focus on the cumulative distributions of peak counts and duration of pulses as well as the waiting time between pulses. We find that these cumulative distributions show scale-invariant behavior, well consistent with the prediction of the self-organized criticality (SOC) theory. This is the first robust evidence of an SOC feature in the prompt emission of a single GRB. Moreover, the statistical properties of pulses in the prompt emission of GRB 230307A are very similar to those of solar flares. Our findings suggest that the prompt emission of GRB is powered by the dissipation of magnetic energy in the ultra-relativistic jet, supporting the Poynting-flux-dominated prompt models.

astro-ph.HE↗
arXiv2026

VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models

Task-success confidence estimation for Vision-Language-Action (VLA) models provides a crucial task-level signal for monitoring manipulation in open-world environments and supporting downstream decision-making. Existing methods typically construct task-success confidence from action-token probabilities. However, such probabilities are not naturally available in flow-matching policies, limiting their applicability to mainstream flow-matching VLAs. To address this issue, we propose VLAConf, a two-stage representation-level confidence framework that operates on frozen pretrained VLA representations. A step-conditioned Coin-Flip Network learns an uncalibrated inverse success-support score from successful demonstrations, while a low-capacity calibrator fitted on outcome-labeled successful and failed rollouts maps the aggregated score to task-success probability. Experimental results on the LIBERO benchmark demonstrate that VLAConf improves online task-success confidence estimation over alternative approaches. We further demonstrate its utility in selective expert assistance, where confidence-triggered handoffs improve task success over no intervention. Its applicability is also evaluated in real-robot experiments. To access the source code and supplementary videos, visit https://sites.google.com/view/vlaconf.

cs.RO↗
arXiv2026

Self-Synchronized Terahertz and X-Ray Free-Electron Lasers from a Single Pre-Bunched Electron Beam

Ultrafast pump-probe spectroscopy combining intense terahertz (THz) and X-ray pulses is a critical tool for investigating complex structural and electronic dynamics in materials. However, current setups combining THz sources and X-ray free-electron lasers (FELs) often suffer from high system complexity, inherent timing jitter, or limited THz pulse properties. Here, we experimentally demonstrate the generation of intrinsically synchronized, strong-field, narrow-band THz and X-ray FELs from a single pre-bunched electron beam. Sequentially passing the beam through X-ray and THz amplifiers reveals a highly synergistic process: the initial periodic THz density modulation notably boosts the X-ray FEL pulse energy, while robustly surviving the intense X-ray emission to drive high-power, narrow-band THz radiation. Originating from the same electron bunch, the two pulses inherently maintain a precise, constant time delay. This jitter-free scheme establishes a highly reliable platform tailored for both X-ray-pump/THz-probe and THz-pump/X-ray-probe experiments.

physics.acc-ph↗
arXiv2026

When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series

Modeling multivariate time series by representing them as graphs, where individual series act as nodes and pairwise temporal corre- lations serve as edges, has gained significant traction. Recent advances in Graph Neural Networks (GNNs) have demonstrated strong perfor- mance by assuming a static graph topology and aggregating information from neighboring series. In this work, we investigate the representa- tional power of GNNs for forecasting under both static and dynamic settings (i.e., when pairwise correlations evolve drastically over time) and identify critical limitations in current architectures. To formalize this, we first propose Temporal Correlation Volatility (TCV), a model- agnostic metric designed to quantify the distributional evolution of these latent structures. We establish a clear connection between TCV and performance degradation, demonstrating that many popular models, including Transformers, generalize poorly in high-TCV settings and are often outperformed by simple structure-agnostic baselines. To address these limitations, we propose Graph Layer for Inference in Dynamic En- vironments (GLIDE), a novel GNN layer enhanced by two theoretically grounded design mechanisms: (D1) Path-based Message Passing, which captures path-based neighborhoods and (D2) Static and Dynamic Propagation Separation, which identifies optimal dynamics via local static approximation. These components significantly improve learning under dynamic topology while preserving robustness in static scenarios. Ex- tensive experiments on synthetic and real-world benchmarks show that GLIDE improves average performance by up to 45.6% across static and dynamic settings, with the largest gain reaching 85.7%. The source code is available at https://github.com/ChenS676/GLIDE.

cs.LG↗
arXiv2026

Beyond Static Forecasting: Unleashing the Power of World Models for Mobile Traffic Extrapolation

Mobile traffic prediction is a fundamental yet challenging problem for wireless network planning and optimization. Conventional models mainly learn static long-term temporal patterns and cannot capture the dynamics under network-parameter adjustments. Leveraging the advantage of world models in learning underlying dynamics, we propose MobiWM, a mobile network world model that treats cell traffic as states and antenna parameters as actions. MobiWM combines factorized spatio-temporal modelling with multimodal environmental context aligned through shared spatial semantics. Its learned action-state transitions enable iterative rollout over specified adjustment trajectories for counterfactual planning. Extensive experiments on massive variable-parameter mobile traffic datasets demonstrate that MobiWM outperforms baselines by at least 16.40% on average. A model-based Actor-critic case study further demonstrates its potential as a learned surrogate for network optimization.

cs.NI↗
arXiv2026

Online Security Learning in Cooperative Multi-Agent Systems under Hidden Byzantine Attacks

We study online cooperative control of a multi-agent system under Byzantine attacks. Namely, an unknown, fixed subset of agents are Byzantine comprised and can stealthily overwrite its own coordinates of the team's planned joint action after observing that plan. The learner observes planned actions, public rewards, and public states, but neither the overwrite nor the executed joint action. Our objective is security: to optimize the team performance against the worst overwrites and achieve the optimal security value. We first show that the attacker's information determines the geometry. An attacker that observes the planned action induces an exact $(s,a)$-rectangular robust Markov decision process (MDP) whose rows are convex hulls of overwrite-induced public-outcome laws, whereas a blind attacker induces an $s$-rectangular model. We then identify the information-theoretic limit of security learning, showing that the security regret decomposes exactly into return regret against the response generating the data and a cumulative response gap $D_K$. Two indistinguishable horizon-one instances force $Ω(K)$ expected security regret while return regret is zero, showing that dependence on $D_K$ is unavoidable. Finally, we develop a stage-tied robust estimation-to-decisions learner and prove a regret bound of $\widetilde{\mathcal O}\!\left(H^2S\sqrt{AK}\right)+\mathbb E[D_K]$. Our studies thus provide comprehensive theoretical and algorithmic foundations of reliable multi-agent systems under Byzantine attacks.

cs.LG↗