arXiv subjects

Wei Wang

Publications and source records attributed to Wei Wang.

At least 73 records · Page 4Linked to original sources

arXiv2026

CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent Cockpits

LLM multi-agent systems suffer from Correctness Collapse, where high task-level accuracy conceals severe process-level failures. This is especially hazardous in safety-critical embodied settings such as automotive cockpits, where lexically correct utterances may trigger dangerous physical operations. Existing attribution methods rely on text traces alone, missing dependency structure, multi-channel evidence, and safety-aware evaluation. We introduce CockpitHAT, a hierarchical attribution framework that replaces positional windows with dependency-distance thresholds from interaction DAGs, integrates multi-channel evidence via an embodied adapter, and applies a safety-uplift to high-risk failures during confidence-weighted analyst consensus. We further release CockpitBench, a benchmark of 212 annotated failure traces spanning dialogue, vehicle-state, environmental, and memory channels, each labeled with ISO 26262 ASIL severity via three-expert consensus. On the public Who&When benchmark, CockpitHAT achieves agent-level / step-exact accuracies of 77.9% / 37.8% on the Hand-Crafted split and 86.5% / 46.0% on the Algorithm-Generated split, surpassing the text-only SOTA ECHO by up to 17.6 / 16.7 points. On CockpitBench, it attains 78.3% agent-level and 38.2% step-exact accuracy. These results establish dependency-aware, multi-channel, risk-calibrated attribution as an effective paradigm for reliable failure diagnosis in real-world embodied LLM multi-agent systems.

cs.AI↗

arXiv2026

MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning

Medical reasoning can reach a plausible answer while overlooking an unsafe or unsupported intermediate step. Process-Level Reward Models (PRMs) can verify such steps, yet existing PRM benchmarks largely target mathematics rather than patient-specific clinical errors. We introduce \textbf{MedPRMBench}, a step-level medical reasoning benchmark with 14 clinical error types, including five new and two clinically re-scoped types, and rule-defined severity grades. Built from seven medical QA sources via structured error construction and review by 86 physicians from Grade-A tertiary hospitals, it provides 6{,}500 evaluation questions, 13{,}000 reasoning chains, and 113{,}910 step labels, plus a leakage-clean 6{,}870-question training split. The best of 20 prompted critics reaches only 75.4\% PRMScore, and critics differ sharply in error-type profiles and operating points. A Qwen3-8B PRM trained on the split reaches 86.6\% PRMScore and 89.0\% strict first-error localization; in matched ablations, physician review raises error recall by 6.55 points and cuts clean-chain false alarms from 5.6\% to 2.1\%. The training signal replicates across model families; without further training, the PRM transfers to ProcessBench and PRMBench, exceeding six of nine math-trained PRMs on each.

cs.CL↗

arXiv2026

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere

Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large-scale annotations or task-specific training procedures, severely limiting their rapid deployment to novel scenes. We observe that intermediate-layer features of pre-trained multimodal large language models (MLLMs) already encode rich anomaly semantics, yet existing approaches rely on the language output pathway and fail to exploit the geometric discriminability latent in these representations. Based on this finding, we propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere, unleashing latent discriminability through principled geometric reasoning rather than learning new representations. Specifically, SphereVAD first applies Frechet mean centering to unfold feature distributions and eliminate domain biases, then employs Holistic Scene Attention (HSA) to reinforce feature consistency using cross-video priors, and finally performs vMF-guided Spherical Geodesic Pulling (SGP) to align ambiguous segments with directional prototypes on the spherical manifold. This training-free pipeline requires only minimal synthetic images for calibration. SphereVAD establishes new state-of-the-art results among training-free approaches on three major benchmarks and remains competitive with fully supervised baselines. Code will be available upon acceptance.

cs.CV↗

arXiv2026

Stereo-Planner: Learning Stereo-to-Trajectory Planning for Zero-Shot Sim-to-Real Quadrotor Navigation

Existing navigation systems commonly rely on dedicated depth sensors or explicit depth reconstruction, while learning to generate trajectories directly from RGB images remains challenging due to the sim-to-real domain gap. In this work, we propose Stereo-Planner, an end-to-end vision-to-trajectory framework that enables zero-shot sim-to-real planning from stereo RGB observations. The key idea is to formulate trajectory generation as state- and scale-conditioned querying of latent stereo geometry. A Scene Representor incorporates a pretrained vision grounding foundation model to extract geometric cues shared across simulated and real-world environments, supporting generalization across visual domains. A lightweight Trajectory Decoder then translates these representations into trajectories through interleaved attention, separating trajectory-state interaction from scene-feature retrieval and incorporating the stereo baseline as a metric-scale cue. With these designs, Stereo-Planner is trained entirely on simulated data by minimizing differentiable trajectory costs and deployed directly in real-world environments without fine-tuning. Benchmark results demonstrate strong cross-scene generalization, with a 95% success rate in simulation environments at a commanded speed of 8 m/s, and competitive performance against depth-based planners using only stereo RGB observations for scene perception. Furthermore, deployment on a compact quadrotor equipped with an NVIDIA Orin NX enables autonomous flight at speeds of up to 7 m/s, with a mean onboard vision-to-action inference time of 24.27 ms. The software, simulation environments, and hardware designs will be open-sourced at https://github.com/Stereo-Planner/Stereo-Planner.

cs.RO↗

arXiv2026

Mapping the Contracting Corona in GS 1354-64 with Insight-HXMT and XRISM: Evolving X-ray Lags and Quenched Reflection across a Complete State Transition

We present a comprehensive broadband spectro-temporal analysis of the dynamically confirmed Galactic black hole transient GS 1354-64 during its 2025-26 outburst, using near-simultaneous observations from Insight-HXMT and XRISM. The high spectral resolution of the XRISM-Resolve microcalorimeter, coupled with the high-cadence broadband coverage of Insight-HXMT, reveals a dramatic evolution in the inner accretion geometry. During the early hard-intermediate state, the spectrum was dominated by a hot Comptonizing corona accompanied by relativistically broadened reflection features. As the outburst progressed, the corona cooled efficiently, the photon index steepened (Gamma >~ 2.5), and the reflection signatures, including the broad Fe K-alpha emission, were quenched, yielding a featureless, disk-dominated continuum. Concurrently, Type-C quasi-periodic oscillations (QPOs) evolved from 0.25 Hz to 6.52 Hz. Cross-spectral timing analysis revealed that the broadband X-ray time lags changed from pronounced positive (hard) delays (~160 ms) at low frequencies to near zero as the source softened. However, a statistical analysis incorporating the measurement uncertainties shows that the broadband lags lack a significant monotonic correlation with the QPO frequency, photon index, or fractional rms. Instead, the scattered lag behavior suggests a competition between positive Comptonization delays and negative thermal reverberation. While the spectral softening and QPO acceleration provide strong evidence for a geometric contraction of the corona (whether interpreted via Lense-Thirring precession or the Two-Component Advective Flow (TCAF) paradigm), the broadband timing properties underscore the turbulent and inhomogeneous nature of the inner flow as the advancing Keplerian disk drives the source into the soft state.

astro-ph.HE↗

arXiv2026

Exploring Motion-Language Alignment for Text-driven Motion Generation

Text-driven human motion generation aims to synthesize realistic motion sequences that follow textual descriptions. Despite recent advances, accurately aligning motion dynamics with textual semantics remains a fundamental challenge. In this paper, we revisit text-to-motion generation from the perspective of motion-language alignment and propose MLA-Gen, a framework that integrates global motion priors with fine-grained local conditioning. This design enables the model to capture common motion patterns, while establishing detailed alignment between texts and motions. Furthermore, we identify a previously overlooked attention sink phenomenon in human motion generation, where attention disproportionately concentrates on the start text token, limiting the utilization of informative textual cues and leading to degraded semantic grounding. To analyze this issue, we introduce SinkRatio, a metric for measuring attention concentration, and develop alignment-aware masking and control strategies to regulate attention during generation. Extensive experiments demonstrate that our approach consistently improves both motion quality and motion-language alignment over strong baselines.

cs.CV↗

arXiv2026

ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood. Existing evaluation paradigms primarily focus on single-step reasoning or static knowledge editing, which fail to capture the temporal dynamics of knowledge retention and degradation during continual model modification. In this work, we propose \textbf{ForgetBench}, a benchmark for measuring forgetting dynamics in the long-term parametric memory of LLMs under continual knowledge editing. ForgetBench introduces two complementary evaluation paradigms, namely concept-based QA and scenario-based QA, to probe the retention of isolated facts and structured relational knowledge. Building upon a sequential editing framework, we construct temporally ordered knowledge streams and evaluate model behavior across multiple editing stages. To quantify these dynamics, we introduce a unified evaluation framework that indexes memory age by the number of subsequent edits and measures temporal decay, retention strength, and cross-instance stability. Extensive experiments across diverse models and editing methods reveal distinct forgetting trajectories and a recurring tension between long-term retention and generalization quality. Our findings highlight the need for more robust memory mechanisms that can effectively acquire, update, and preserve knowledge over time in future LLMs.

cs.CL↗

arXiv2026

EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent

Vision-language-action (VLA) policies generate executable robot actions, but plausible proposals can have different consequences for the task. We present EmbodiedSkills, a skill-based agent framework that augments frozen VLA policies with world action models for consequence-aware action selection. The framework defines reusable skills for scene observation, context encoding, candidate generation, consequence prediction, outcome evaluation, candidate comparison, and action execution. Five stages organize their input-output dependencies in a shared feedback loop, accommodating both continuous action chunks and pick-and-place primitives. At each decision point, independently trained world action models predict the latent consequences of a common set of policy proposals. Selection combines their outcome scores and prediction disagreement with a lightweight comparator that estimates the benefit of an alternative from agreement in its predicted effects. The predictive and comparison modules learn from matched-state candidate branches, while the action policy and pretrained observation encoders remain frozen. On MetaWorld MT50 and CLIPort, EmbodiedSkills improves success rates from 76.28% to 78.64% and from 33.94% to 36.83%, respectively. An additional CALVIN evaluation with the frozen FLOWER policy increases five-task-chain success from 77.10% to 77.90%. These results demonstrate the applicability of consequence-aware selection across different policy backends and action representations.

cs.RO↗

arXiv2026

Photonic Chips for Universal Quantum Computing: Retrospective and Prospective

Integrated photonic quantum chips have emerged as a promising platform for realizing fault-tolerant photonic quantum computers. Compared with bulk-optics systems, integrated photonics offer compact device footprints, enhanced programmability, and exceptional stability, attributes that are essential for executing large-scale and computationally demanding quantum tasks. In this review, we provide a comprehensive overview of recent advances in both discrete-variable and continuous-variable universal photonic quantum computation. We survey progress in fault-tolerant architectures and state-of-the-art integrated platforms and highlight the key challenges that must be addressed to scale photonic systems toward full fault tolerance. Finally, we outline future opportunities and research directions aimed at bridging the gap between current proof-of-principle demonstrations and fully scalable quantum microprocessors.

quant-ph↗

arXiv2026

Toward Service-Balanced ISAC: From Coupled RAN to De-Coupled RAN

Sixth-generation (6G) applications require radio access networks (RANs) to support reliable communication and seamless sensing across their operating regions. In coupled RAN deployments, shared downlink transmitting and uplink receiving sites constrain the network's ability to accommodate asymmetric links and different sensing geometries. De-Coupled RAN (DC-RAN) separates these functions, allowing independently deployed and coordinated base stations to extend uplink and downlink communication and sensing coverage. How this flexibility translates into balanced communication and sensing services, however, remains insufficiently explored. This article revisits the evolution from coupled to DC-RAN from the perspective of service-balanced integrated sensing and communication (ISAC). It examines how architectural choices affect the availability of both services, with communication-sensing coverage symmetry capturing their spatial alignment under application-specific quality requirements. Practical challenges include preserving communication consistency, maintaining sensing continuity, and coordinating distributed resources. Two case studies illustrate how DC-RAN can support coverage symmetry alongside consistent communication, and how complementary observations can sustain continuous and accurate sensing. These examples inform a discussion of future research toward service-balanced ISAC.

eess.SP↗

arXiv2026

CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model Engineering

Geometric and Spectral Alignment (GSA) characterizes trained networks through spectral concentration, physical-channel alignment, support structure, and changes in singular bases. In this paper, we propose CHASE (Channel-Aligned Structure Exploitation) to use these structures in practical model design. CHASE covers six applications across model modification, reconfiguration, and compression. CORA, COEC, and CORAM apply GSA to parameter-efficient finetuning, structured-pruning compensation, and model merging. We further develop three new methods. CAGA uses GSA to identify multi-head attention heads that can share a KV representation and constructs the shared key and value heads through geometric alignment and low-rank subspace extraction. SAKV uses GSA to determine which adjacent layers can share a low-rank KV-cache representation and the retained rank for each layer group. CAPS uses GSA spectral structure to group output neurons and selects retained input channels separately for each group. Results from CORA, COEC, and CORAM establish the effectiveness of GSA for adaptation, pruning compensation, and model merging. Experiments on CAGA show that geometric shared-head construction substantially improves MHA-to-GQA conversion, and SAKV and CAPS improve over representative baselines for KV-cache compression and structured pruning. These results show that the structures identified by GSA can be used directly to design methods for a range of model operations.

cs.LG↗

arXiv2026

Short-Range Correlation Scaling of Nuclear Parton Modifications: Consistency Tests and Recoil-Tagged Charm-Production DIS

We investigate short-range correlation (SRC) scaling of nuclear gluon modifications using nCTEQ SRC abundances and EPPS21 gluon distributions. Rescaling the EPPS21 central modifications by these abundances yields an approximately common curve for six nuclei from carbon to lead over $0.1\leq x\leq0.4$ at $Q^2=10$ and $100\,\mathrm{GeV}^2$. The SRC interpretation is supported by the broad agreement between the fitted abundances and high-momentum proton fractions from variational Monte Carlo calculations. Using an SRC proton fraction of approximately $20\%$ in carbon, the measured EMC-SRC correlation also gives a pure-SRC EMC slope of $1.94\pm0.12$, consistent with the nCTEQ estimate $2.02\pm0.20$. To test the connection between this scaling and SRC configurations, we propose recoil-tagged charm-production in deuteron deep-inelastic scattering (DIS), combining a backward high-momentum proton tag with a gluon-sensitive hard process. We formulate leading-power collinear factorization through an extended fracture function, which reduces within the plane-wave impulse approximation to a deuteron light-front spectral factor times a recoil-conditioned neutron gluon distribution. The tagged charm reduced cross section and its ratio to inclusive tagged DIS provide complementary observables for comparing gluon modifications in SRC-enriched configurations with the scaling inferred from inclusive nPDFs.

hep-ph↗

arXiv2026

Understanding the Identity-Transformation Approach in OIDC-Compatible Privacy-Preserving SSO Services

Single sign-on (SSO) enables a user to log into multiple websites, called relying parties (RPs), by her username and credential set up in another trusted web system, called the identity provider (IdP). Identity transformations are proposed in UppreSSO to provide privacy-preserving SSO services, preventing both IdP-based login tracing and RP-based identity linkage. While the security and privacy guarantees of UppreSSO have been proved, several essential issues on the identity-transformation approach are not well studied. In this paper, we comprehensively investigate this approach as below. Firstly, several suggestions to efficiently integrate identity transformations into OpenID Connect (OIDC) are explained. Then, we uncover the relationship between identity transformations in SSO and oblivious pseudo-random functions (OPRFs), and present two variations of the properties required for SSO security as well as other requirements, to analyze existing OPRF protocols. Finally, new identity transformations different from those proposed in UppreSSO, are constructed based on some OPRFs. To the best of our knowledge, this is the first time to uncover the relationship between identity transformations in SSO services and OPRFs, and prove the SSO-related properties (i.e., output uniqueness, key-identifier freeness, and collision resistance on 1st/2nd-input) of typical OPRFs.

cs.CR↗

arXiv2026

Shadow-Free Scattering with Complex Frequency Excitations

The optical theorem dictates that the wave scattering of an object in the forward direction is proportional to the total power extinguished from the excitation. For passive objects, this relationship is a by-product of the intuitive notion that scattering and absorption necessarily create shadows, and that zero forward scattering, i.e., no shadow, can only be obtained if the object is fully transparent, i.e., it neither scatters nor absorbs. Materials with gain can be in principle leveraged to suppress forward scattering while preserving a large scattering signature in other directions. However, sufficient optical gain is challenging to realize, and it inherently leads to instabilities and nonlinearities. Here, we experimentally demonstrate shadow-free \ scattering from a passive high-index dielectric sphere by exciting it with a complex frequency signal tailored to mimic the presence of material gain. We achieve as much as 26dB suppression of the forward scattering when compared with optimal monochromatic excitations, while preserving strong scattering in other directions. More broadly, our results demonstrate how complex frequencies offer a natural pathway to enhance control over the scattering signature of passive objects, with implications for a range of photonic applications.

physics.optics↗

arXiv2026

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers

Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce \emph{false negatives} (rejecting correct answers) and \emph{false positives} (accepting incorrect ones). We formalize verifier unreliability as a stochastic reward channel with asymmetric noise rates $ρ_0$ and $ρ_1$ -- the FP rate and the FN rate, respectively. From this abstraction we derive two lightweight corrections: (i) a \emph{backward} correction that yields an unbiased surrogate reward and thus an unbiased policy-gradient estimator in expectation, and (ii) a \emph{forward} correction that reweights score-function terms so the expected update aligns with the clean gradient direction and requires only the FN rate. We implement both as lightweight hooks in a group relative policy optimization pipeline, both corrections improve RLVR for math reasoning under synthetic and real verifier noise, with the forward variant being more stable under heavier noise. Finally, an appeals mechanism with a lightweight LLM verifier estimates the FN rate online and further improves performance.

cs.LG↗

arXiv2026

Projection of purification performance for the RELICS experiment

The RELICS (REactor neutrino LIquid xenon Coherent elastic Scattering) experiment employs a dual-phase liquid xenon time projection chamber to search for Coherent Elastic Neutrino-Nucleus Scattering (CE$ν$NS) induced by reactor neutrinos. To detect these sub-keV nuclear recoils and minimize signal attenuation, it is critical to maintain a sufficiently low impurity concentration in the detector. This work presents a comprehensive purity evolution model developed to describe impurity migration inside the detector. Utilizing measured material outgassing rates as input parameters, the model incorporates non-uniform transport mechanisms of the impurities, including circulation, vaporization, and condensation. The model is validated using data from a dedicated prototype detector. Based on this validated model, projections for the purification performance of the upcoming RELICS-10 and RELICS-50 detectors are provided.

physics.ins-det↗

arXiv2026

Number Theory of Decaying Turbulence 3: Comparing with Physical and Numerical Experiments

We compare the predictions of the Euler-ensemble solution of freely decaying incompressible turbulence with simulations and experiments: the scaling function of the energy spectrum, the index of the second-order structure function and the decay laws. The predictions have a fixed shape; only their normalization and scale are fitted. In the final $4096^3$ direct numerical simulations of Rodhiya and Sreenivasan, the turbulent attractor is selected by a parabola law for the growth of the bulk length. Along it the collapsed spectrum depends only on the instantaneous Reynolds number, identically for Saffman and Loitsyansky initial spectra; extrapolated to infinite Reynolds number, it agrees with the theory to 1% in the bulk of the enstrophy range, below the dissipation range. The energy balance holds exactly. The energy integral of the theory diverges in the infrared, so energy and enstrophy depend on how a finite flow cuts off the spectrum: with a sharp cutoff $k_0$, the decay laws, energy $\propto t^{-5/4}$ and enstrophy $\propto t^{-9/4}$, are reached only when the cutoff enters the $k^{-7/2}$ tail of the spectrum. Such a cutoff is only an estimate; the reliable test is the bulk of the spectrum. Fitted to the simulations, the cutoff lies at the lower edge of the bulk, where the spectrum still carries the initial data, and the decay exponents depend on the initial infrared spectrum. In the Max Planck wind tunnel at $Re_λ$ up to 5779, the longitudinal index extrapolated to infinite Reynolds number matches the odd ensemble with one scale parameter at large separations, where standard crossover forms fail. The freely decaying turbulent blob of Matsuzawa et al. is too small, too inhomogeneous and too weak to display the attractor. The theory is derived in the first two papers of this series.

physics.flu-dyn↗

arXiv2026

Approximation of Random Differential Equations Driven by Physical Brownian Motion with Fast Oscillating Noise

We investigate approximation of random differential equations driven by semimartingales satisfying a singularly perturbed Langevin equation with scaled mixing random force. By a diffusion approximation approach, we explore the limit of the rough path lift of this semimartingale, and a universal limit theorem is applied to identify the limit of random differential equation. A structurally parallel proof also applies to establish an iterated weak invariance principle for the mixing random force, which is itself an independent interesting result. We find that, the limit of both of the second-level processes, have the form of iterated integral of Stratonovich form plus an anti-symmetric part which is proportional to the time increment.

math.PR↗