Search arXiv⌕ Search

arXiv subjects

Peng Wu

Publications and source records attributed to Peng Wu.

At least 19 recordsLinked to original sources
arXiv2026

Exact Fusion and Coordinated Exploration in Multi-Robot Active Inference

Robot teams that learn a common environment model exchange belief summaries and plan by the expected information gain of their actions. Under conjugate exponential-family beliefs the shared belief is counted once per robot at two points: at fusion, the product of local posteriors counts the common prior $n$ times, and at planning, every robot scores its plan under the same belief and the team converges on the same unknown. Both errors are removed by adding evidence increments to the shared natural parameter, realized increments at fusion and expected increments at planning. The expected increment of a committed teammate gives the next robot its conditional gain; corrected gains sum to the joint gain, the redundancy removed equals the total correlation of the planned observation streams, and sequential commitment keeps the $1/2$ greedy guarantee. The expected increment is exact for Gaussian beliefs with fixed sampling paths and for Dirichlet beliefs under the novelty approximation of discrete active inference, whose team objective has a closed concave form within an explicit bound of the exact mutual information, and fails for finite hypothesis classes, where a short exact enumeration replaces it. Experiments on cooperative RockSample, foraging, and field monitoring show that fusion correction leaves exploration redundancy unchanged, anticipated evidence removes it, and sequential commitment recovers most of the value of centralized joint planning at cost linear in the team size.

cs.RO↗
arXiv2026

AnomalyCraft-700K: Component-Level Controllable and Verifiable Synthetic Anomalies for Fine-Grained Video Anomaly Understanding

Progress in video anomaly understanding (VAU) has long been limited by inherent deficiencies of real-world anomaly videos, which are hard to collect and offer little control over their content. Synthetic anomaly approaches partially alleviate data scarcity, yet their generation remains largely controlled at the category or prompt level. They also lack component-level verification of video-text consistency and provide insufficient hard normal samples near the normal-anomaly boundary. To address this, we present AnomalyCraft-700K, a component-controllable synthetic anomaly dataset for fine-grained VAU, containing over 40K videos and over 700K task-level textual annotations. From fine-grained semantic components and a progressive three-stage pipeline, we craft anomaly events that are richly detailed, semantically controlled, and temporally structured, and additionally construct per-category hard normal samples to prompt the model to discriminate based on anomaly semantics rather than surface visual cues. Moreover, using the components as verification units, AnomalyCraft-700K further performs component-wise correction of video-text discrepancies introduced during generation, providing reliable annotations with verified cross-modal alignment for six tasks that progress from anomaly detection, through anomaly retrieval and captioning, to fine-grained anomaly reasoning. Evaluations of widely used methods under both traditional and MLLM-based protocols demonstrate that AnomalyCraft-700K serves as an effective source of supervision, from anomaly detection to fine-grained anomaly understanding.

cs.CV↗
arXiv2026

Machine Learning for Scheduling Decision Systems: A Critical Review of Architecture, Assurance, and Deployment

Machine learning supports scheduling through prediction, search guidance, or schedule formation, but model-level evaluations obscure the downstream work, technical authority, and controls needed to release decisions. We conduct a critical integrative review combining structured candidate identification and purposive full-text synthesis, treating the complete reported scheduling decision system (from problem specification to release and conditional recovery) as the unit of analysis. Our system-level taxonomy distinguishes the function of learned outputs, schedule formation, and binding control along the normal release path. It separates learning and adaptation from decision assurance, and technical authority from organizational decision rights. Reported timing and solver guarantees depend on downstream work and the decision space left after learned commitments; transfer of retained capability differs from architectural reuse, and operational maturity from automated release. Evidence supports selected quality-computation-time trade-offs, bounded transfer of retained capability, performance within specified regimes, and operating use in several configurations. It does not support a system-equivalent ranking of learning and optimization, general cross-task transfer, or common conclusions about lifecycle economics and long-run field performance. Four operations-management propositions link lifecycle value to effective reuse, technical authority to forms of change, deadline-feasible assurance and recovery, and organizational rights to information and accountability. Solver-led, shared-authority, and model-led configurations are alternative designs, not maturity stages; model performance alone does not justify greater release authority.

math.OC↗
arXiv2026

GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks

Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Existing slice discovery approaches largely model slices as clusters in representation space or combinations of predefined attributes. While effective for image-level classification, such formulations are insufficient for instance-level tasks such as object detection and segmentation, where failures often arise from contextual relational and spatially grounded visual patterns. We propose GH-ESD (Grounded Hypothesis-Driven Error Slice Discovery), a generate and verify framework that reformulates slice discovery as grounded hypothesis generation and statistical verification. GH-ESD constructs relational failure hypotheses using LLM priors and grounded visual evidence, discovers hypothesis slices at the instance level via Vision Language Models, and verifies them through statistical trend analysis over instance-level errors. We also introduce GESD (Grounded Error Slice Dataset), a new benchmark for instance-level error slice discovery, providing expert-defined and spatially grounded slices derived from detection and segmentation failures. Extensive experiments demonstrate that GH-ESD consistently outperforms baselines, improving Precision@10 by 0.10 (0.73 vs. 0.63) on the GESD benchmark for detection tasks, while also supporting segmentation scenarios. GH-ESD identifies interpretable slices that facilitate actionable model improvements.GESD is publicly available at https://github.com/apple/ml-fine-grained-error-slice-discovery-dataset.

cs.CV↗
arXiv2026

DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration

All-in-One Image Restoration (AiOIR) aims to handle diverse degradations within a unified model. However, existing methods often overlook image semantics in degradation modeling and lack low-level visual priors during reconstruction, leading to structural distortions and semantic inconsistencies. To address these issues, we propose a novel Dual-Prior Collaborative Network (DPC-Net), which achieves high-quality restoration by jointly exploiting degradation-semantic coupled priors and low-level visual priors. Specifically, degraded images are fed into a Degradation-Aware Network (DAN) to extract degradation-semantic coupled features. To this end, a Vision-Language Model (VLM) supervises DAN by constraining its features distribution, introducing image semantics into the encoding of degradation patterns. A Degradation-Semantic Modulation Module (DSMM) further translates this guidance into degradation-semantic coupling and propagates coupled representations to the decoder. During decoding, knowledge bases provide low-level visual priors, and the Dual-Prior Collaborative Reconstruction Module (DPCR) integrates dual-prior information to guide degradation removal while preserving structure and semantics, producing high-fidelity restored images. Extensive experiments on multiple restoration benchmarks demonstrate that DPC-Net achieves superior performance against state-of-the-art AiOIR methods.

cs.CV↗
arXiv2026

A Forward Simulation-Based Hierarchy of Linearizable Concurrent Objects

In this paper, we systematically investigate the connection between linearizable objects and forward simulation. We prove that the sets of linearizable objects satisfying wait-freedom (resp., lock-freedom or obstruction-freedom) form a bounded join-semilattice under the forward simulation relation, and that the sets of linearizable objects without liveness constraints form a bounded lattice under the same relation. Thus, forward simulation is not only a proof technique for linearizability but also induces an algebraic hierarchy of linearizable objects. As part of our lattice result, we propose an equivalent characterization of linearizability by reducing checking linearizability w.r.t. sequential specification $Spec$ into checking forward simulation w.r.t. an object $\mathcal{U}_{Spec}$.

cs.DC↗
arXiv2026

Rethinking Auxiliary Modalities in Multimodal Zero-shot Anomaly Detection: From Semantic Fusion to Conditional Modulation

Recent foundation model-based methods have endowed RGB images with strong zero-shot anomaly detection (ZSAD) through vision-language pretraining. However, RGB observations alone remain limited in perceiving anomalies dominated by geometric deformation, depth variation, or subtle surface changes. Auxiliary modalities can provide complementary structural information, but existing multimodal methods typically fuse them directly into a shared semantic space, which may disturb the text-aligned anomaly semantics established by RGB foundation models and often requires modality-specific architectures. To address this issue, we propose a plug-and-play auxiliary-conditioned enhancement framework for zero-shot anomaly detection. Instead of reconstructing a joint multimodal anomaly semantic space, our framework preserves the original RGB image-text anomaly matching pathway and uses auxiliary observations as conditional signals for RGB feature refinement, allowing auxiliary modalities to seamlessly enhance existing RGB-based zero-shot anomaly detectors. Specifically, a lightweight meta-learning module takes global RGB and auxiliary representations as input and generates sample-adaptive low-rank residual updates to determine how RGB features should be refined. We further construct uncertainty-aware spatial modulation from the initial RGB anomaly response and auxiliary reliability, which determines where local residual updates are strengthened or suppressed. This global-to-local conditional modulation enables selective multimodal enhancement while preserving the original RGB anomaly semantics. Extensive experiments on MVTec 3D-AD and Eyecandies demonstrate that our framework consistently improves multiple popular RGB-based zero-shot anomaly detectors, achieving state-of-the-art performance for multimodal zero-shot anomaly detection.

cs.CV↗
arXiv2026

Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs

Existing vision-language model (VLM) backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets before victim training. This assumption substantially underestimates the threat. We show that a single poisoning phase can implant a programmable backdoor into a VLM, allowing an attacker to choose previously unseen target-caption semantics at inference time and synthesize corresponding stealthy triggers on demand. Unlike fixed-mapping attacks, the proposed any-to-any caption-control paradigm decouples post-training target selection from poisoning, enabling dynamic control of target captions without retraining the VLM. Our method has two components. First, a heuristic poisoning strategy exposes the model to diverse trigger-caption pairs, encouraging it to learn a general trigger-as-instruction rule rather than memorize a specific backdoor pattern. Second, a feature-space trigger steganography method maps any attacker-specified target caption to a stealthy visual trigger, implemented as either a norm-controlled perturbation or a non-semantic patch. Once inserted into arbitrary images, these triggers cause the poisoned VLM to generate outputs semantically aligned with the chosen target caption, even when the target was unseen during poisoning. Extensive experiments show that our attack achieves high any-to-any caption-control success rates, preserves clean model utility, and remains effective under several classical backdoor defenses.

cs.CV↗
arXiv2026

Quark matter at finite temperature and proto-quark stars with the axion effects in SU(3) Nambu-Jona-Lasinio model

We investigate the thermodynamical properties of strange quark matter (SQM) and proto-quark stars (PQSs) within the SU(3) Nambu-Jona-Lasinio (NJL) model at finite temperature, specifically incorporating the effects of axion fields and vector interactions. Our results demonstrate that these interactions significantly influence the equation of state (EoS), constituent quark masses, entropy density, and the maximum star mass of PQSs at the isentropic stages along the star evolution line. Furthermore, we reveal a distinct thermodynamic signature in the early evolution: the presence of trapped neutrinos leads to a substantial increase in electron number density while simultaneously suppressing the core temperature compared to the neutrino-free case. These findings may highlight the crucial role of the axion effects, flavor-dependent vector interactions, and particle composition in determining the observable properties of compact stars at finite temperature.

nucl-th↗
arXiv2026

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

Omni-modal large language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks, but processing long and highly redundant visual and audio token sequences incurs substantial computational overhead, demanding aggressive token compression for efficient deployment. Existing methods often degrade at low token budgets: pre-LLM compression may discard structurally important and globally distributed evidence, whereas inner-LLM compression often underexploits query-conditioned audio-visual collaboration. To address these limitations, we propose OmniPack, a training-free framework that coordinates structural compression before the LLM with task-relevant semantic refinement within the LLM. Before the LLM, OmniPack removes structural redundancy through modality-specific importance, global coverage, and similarity-aware merging. After sufficient multimodal interaction, it further consolidates diverse, task-relevant representations through textual guidance and audio-visual collaboration. Extensive experiments on five benchmarks with three Omni-LLM backbones demonstrate that OmniPack consistently achieves the best performance-efficiency trade-off across diverse retention ratios, outperforming all existing methods. Notably, on Qwen2.5-Omni-7B, OmniPack preserves 98.0% of the original performance while reducing FLOPs to 16.7%, and still retains 92.9% of the original performance with only 6.8% of the original FLOPs.

cs.CV↗
arXiv2026

A black-box-model-enhanced interaction method for water-wave scattering by large group of arbitrary-shaped ice floes in Arctic route planning

This study develops an enhanced interaction (EI) method for efficient prediction of the water-wave field among a large group of ice floes in Arctic route planning. A novel black-box model, termed the wave component detection (WCD) method, is proposed for constructing the diffraction transfer matrix (DTM) within the framework of interaction theory. The DTM, which is conventionally mathematically intractable for three-dimensional ice floes with arbitrarily complex geometry, can now be determined using this readily implementable and universally applicable approach. Without loss of generality, four ice-floe shapes are taken as example models to demonstrate the capability of the EI method. Operation rules are recommended for the practical implementation of the EI method. The error range of the EI method is identified in scenarios with multiple ice floes of different sizes and distances.The super-high efficiency of the EI method is demonstrated in cases involving an ultra-large group of ice floes. It takes less than 1.5 hours to calculate wave amplitudes at 160,000 locations in the wave field of 1,800 ice floes (based on 1,440,000 boundary elements) on an ordinary personal computer with a 2017-released CPU. Based on the wave field predicted by the EI method, users can take advantage of the wave-sheltering effect of the ice floes to optimize routes. For demonstration, the dynamic programming strategy is used to recommend optimized navigation routes among 1561 ice floes of mixed shapes. The average wave amplitude the ship encounters can be reduced to about half of the incident wave amplitude.

physics.ao-ph↗
arXiv2026

A Distributional Perspective on Pearl's Causal Hierarchy: From Marginal to Joint and Individualized Potential Outcomes

Pearl's causal hierarchy is a foundational lens for formulating causal questions and is most often discussed within the framework of structural causal models. We recast the hierarchy in potential outcomes language and make its information ordering operational at the level of causal estimands. Specifically, we classify an estimand according to whether it requires marginal potential outcome distributions, their joint distribution or nested cross-world quantities, or individual-level counterfactual outcomes. We apply this criterion systematically to a broad range of estimands, including cases whose classification depends on the formulation of the scientific question. We then clarify what additional assumptions are needed when an estimand depends not only on the marginal distributions of potential outcomes, but also on their unobserved joint distribution. In particular, randomization identifies the marginals, whereas monotonicity, copula restrictions, rank preservation, and partial identification restrict or characterize the remaining uncertainty about the joint distribution. The resulting framework provides a practical map from a scientific question to an estimand, the probabilistic object it requires, and the assumptions needed for identification.

stat.OT↗
arXiv2026

Temperature fluctuations in a realistic Polyakov-loop extended Nambu--Jona-Lasinio Model along the freeze-out line

We extend and reparameterize the Polyakov--Nambu--Jona-Lasinio (PNJL) model to reproduce lattice simulation data at zero baryon chemical potential and to position its critical endpoint (CEP) within the BES-II experimental energy range. Using this realistic PNJL model, we investigate the behavior of the second-order temperature cumulant $C_2$ along the freeze-out line, aiming to understand the non-monotonic energy dependence of the two-particle transverse momentum correlation $C_{p_T}$ observed by the STAR Collaboration. Our results show a distinct dip structure in $C_2$ near the CEP and the first-order phase boundary on the phase diagram. Along the experimentally extracted freeze-out line, the dip minimum occurs around 7.7 GeV, and its trend is consistent with that observed by STAR, suggesting that the non-monotonic dependence of $C_{p_T}$ may be related to the CEP. Our results also indicate that cumulant ratios such as $C_3/C_2^2$ or $C_4/C_2^3$ eliminate the influence of initial volume fluctuations and may better reveal the underlying critical fluctuations. Further verification could be pursued through hydrodynamic or transport simulations that incorporate critical dynamics. These results and predictions might provide an a priori theoretical basis for future experimental measurements of higher-order event-mean transverse momentum fluctuations.

nucl-th↗
arXiv2026

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction

Pre-trained Latent Diffusion Models (LDMs) have recently shown strong perceptual priors for low-level vision tasks, making them a promising direction for multi-exposure High Dynamic Range (HDR) reconstruction. However, directly applying LDMs to HDR remains challenging due to: (1) limited dynamic-range representation caused by 8-bit latent compression, (2) high inference cost from multi-step denoising, and (3) content hallucination inherent to their generative nature. To address these challenges, we introduce GMODiff, a gain map-driven one-step diffusion framework for multi-exposure HDR reconstruction. Instead of reconstructing full HDR content, we reformulate HDR reconstruction as a degradation-aware Gain Map (GM) refinement problem, where the GM encodes the extended dynamic range while retaining the same bit depth as LDR images. We initialize the denoising process from an informative regression-based estimate rather than pure noise, allowing the model to generate high-quality GMs in a single denoising step. Furthermore, recognizing that regression-based models excel in content fidelity while LDMs favor perceptual quality, we leverage regression priors to guide both the denoising process and latent decoding of the LDM, suppressing hallucinations while preserving structural accuracy. Extensive experiments demonstrate that GMODiff performs favorably against several state-of-the-art methods and is 100x faster than previous LDM-based methods. Code is available at https://github.com/gbymat/GMODiff.

cs.CV↗
arXiv2026

Perturbation Effects on Robustness and Individual Fairness

Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Robust Biased and Unrobust Fair behaviors. RIFair}reliably exposes these hidden vulnerabilities, supporting RIF as a necessary criterion for trustworthy model assessment. The experimental code is publicly available at https://github.com/Xuran-LI/RIFair.

cs.LG↗
arXiv2026

Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets

Event-based vision, characterized by low redundancy, focus on dynamic motion, and inherent privacy-preserving properties, naturally fits the demands of video anomaly detection (VAD). However, the absence of dedicated event-stream anomaly detection datasets and effective modeling strategies has significantly hindered progress in this field. In this work, we take the first major step toward establishing event-based VAD as a unified research direction. We first construct multiple event-stream based benchmarks for video anomaly detection, featuring synchronized event and RGB recordings. Leveraging the unique properties of events, we then propose an EVent-centric spatiotemporal Video Anomaly Detection framework, namely EWAD, with three key innovations: an event density aware dynamic sampling strategy to select temporally informative segments; a density-modulated temporal modeling approach that captures contextual relations from sparse event streams; and an RGB-to-event knowledge distillation mechanism to enhance event-based representations under weak supervision. Extensive experiments on three benchmarks demonstrate that our EWAD achieves significant improvements over existing approaches, highlighting the potential and effectiveness of event-driven modeling for video anomaly detection. The benchmark datasets will be made publicly available.

cs.CV↗
arXiv2026

Model Merging to Evolution: Parameter Space Exploration for Expert Models

Model merging integrates the capabilities of multiple expert models to create strong models for multiple tasks without additional training, thereby reducing computational resource requirements. However, existing methods operate within the convex combination space of expert models, failing to explore high-performance regions outside this space. This paper proposes the MERGEvolve framework, which unifies model merging and evolution within an evolution strategy by treating the merged model as the initialization for evolutionary exploration of the parameter space. During the merging phase, expert models act as deterministic sources to build a strong initial point. The evolution phase then explores the parameter space using random noise. Theoretical analysis shows that MERGEvolve explores regions outside the convex combination space. Extensive experiments on single-task and multi-task benchmarks demonstrate that MERGEvolve consistently achieves performance competitive with advanced model merging baselines. Ablation studies confirm that a high-quality initial point is critical for efficient exploration of the parameter space.

cs.NE↗
arXiv2026

PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates

Neural operator models trained on simulation data often lose accuracy when applied to experimental measurements due to the sim-to-real gap. Standard fine-tuning with limited real data can reduce this gap, but it may also damage the core physics-relevant representations learned during pretraining. Although knowledge-preserving adaptation has been widely investigated in vision or language tasks, it remains unclear whether these methods are suitable for neural operators whose architectures and protected knowledge are fundamentally different. Neural operators need to preserve core-scale physical structures rather than semantic or visual features. We propose PhysGuard, a physics-preserving framework for accurate sim-to-real adaptation of neural operators. Specifically, PhysGuard uses the empirical Fisher Information Matrix computed on simulation data to identify physics-critical parameter directions, then restricts fine-tuning updates to directions that do not interfere with them. A layer-wise Gram-matrix formulation makes this efficient for models with millions of parameters, while an adaptive threshold automatically determines the protected subspace size. A spectral probe experiment shows that the dominant Fisher directions are strongly associated with low-frequency output structures. Experiments on benchmark across four neural operator architectures and different physical systems show that PhysGuard performs strongly on most evaluation metrics compared to baselines. The benefits are most evident under severe domain shift, where it reduces low-frequency error by up to 32\% compared to standard fine-tuning while maintaining adaptability. Our code is available at https://github.com/ZhouChaunge/PhysGuard.

cs.LG↗