Searcharxiv⌕ Search

arXiv subjects

Wenke Huang

Publications and source records attributed to Wenke Huang.

At least 37 records · Page 2Linked to original sources
arXiv2026

EchoRL: Reinforcement Learning via Rollout Echoing

Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceeds, the learning signal can collapse thus makes the training gain become marginal and ineffective. Specifically, a growing fraction of prompts' rollouts become advantage-degenerated: all the self-generated rollouts show verified-success, making the standard deviation over their rewards be zero; accordingly each rollout's advantage becomes degenerated (zero) as well. Given such rollouts' advantages, the policy-gradient for model optimization eventually vanishes, capping the training performance. We argue that some of these rollouts still contain valuable learning signals but unfortunately omitted with the existing RLVR methods. In this paper, inspired through analyzing the entropy pattern behind golden trajectories produced by external expert models, we propose EchoRL for better exploiting the advantage-degenerated rollouts to further improve the training performance. EchoRL is a lightweight module that first identifies an EchoClip from verified-success rollouts based on their step-level entropy values, and then feeds this clip back as an auxiliary supervision signal in the RL objective. Extensive experiments across 10 benchmarks, 5 LLM backbones, and 4 popular RLVR post-training methods demonstrate that EchoRL consistently improves RLVR post-training with minimal overhead.

cs.LG↗
arXiv2026

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training data. SkillTrojan embeds malicious logic inside otherwise plausible skills and leverages standard skill composition to reconstruct and execute an attacker-specified payload. The attack partitions an encrypted payload across multiple benign-looking skill invocations and activates only under a predefined trigger. SkillTrojan also supports automated synthesis of backdoored skills from arbitrary skill templates, enabling scalable propagation across skill-based agent ecosystems. To enable systematic evaluation, we release a dataset of 3,000+ curated backdoored skills spanning diverse skill patterns and trigger-payload configurations. We instantiate SkillTrojan in a representative code-based agent setting and evaluate both clean-task utility and attack success rate. Our results show that skill-level backdoors can be highly effective with minimal degradation of benign behavior, exposing a critical blind spot in current skill-based agent architectures and motivating defenses that explicitly reason about skill composition and execution. Concretely, on EHR SQL, SkillTrojan attains up to 97.2% ASR while maintaining 89.3% clean ACC on GPT-5.2-1211-Global.

cs.CR↗
arXiv2026

Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification

Identifying key individuals in video scenes is essential for applications such as automated video editing and intelligent surveillance. Current methods primarily focus on static images and immediate visual cues, overlooking the rich spatio-temporal information in videos. This leads to the phenomenon of Temporal Importance Shift (TIS), wherein individuals deemed significant in early frames may be demoted as the entire temporal context is considered. To address this, we introduce the Video Important Person (VIP) identification task, aimed at automatically identifying the most influential individuals in videos while providing textual rationales. We present Temporal-VIP, a large-scale rationale-annotated dataset consisting of 9,249 video segments across 11 categories with aligned importance rationales. To mitigate TIS, we develop the VIP-Net framework, which includes a Social Cue Encoder (SCE) for extracting multi-modal spatio-temporal cues, a Temporal Importance Rectifier (TIR) for hierarchical cue fusion and cross-modal alignment, and VIP Inference for ranking individuals. Experimental results show that VIP-Net achieves 67.3% accuracy, significantly outperforming state-of-the-art models (37.5%-53.9%) and yielding a mean rationale similarity of 0.63 to ground truth through feature-guided LLM refinement. The dataset and code are available at https://huggingface.co/datasets/yml2002/Temporal-VIP.

cs.CV↗
arXiv2026

Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity

Label Distribution Learning (LDL) models supervision as an instance-wise probability distribution, enabling fine-grained learning under inherent ambiguity, but its success relies on high-fidelity label distributions that are costly to obtain and thus often noisy. Motivated by privacy-sensitive applications, we study Federated Label Distribution Learning (Fed-LDL), where data isolation further induces heterogeneous annotation quality across clients, making local updates unevenly reliable and breaking sample-size-based aggregation (e.g., FedAvg). To address this trust dilemma, we propose FedQual, a quality-aware Fed-LDL framework with two coupled mechanisms: (i) quality-adaptive client training guided by a global semantic anchor that calibrates low-quality clients while preserving high-quality autonomy, and (ii) reliability-aware server aggregation that reweights client contributions by effective reliable information rather than raw sample size. To enable rigorous evaluation, we construct four new Fed-LDL benchmarks (FER-LDL, FI-LDL, PIPAL-LDL, and KADID-LDL) with controlled annotation quality disparity. We further provide a theoretical guarantee showing that under heterogeneous supervision quality, client-specific calibration is strictly better than any uniform calibration. Extensive experiments on the proposed benchmarks demonstrate the effectiveness of FedQual.

cs.LG↗
arXiv2026

FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning

Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label correlations under heterogeneous distributions remains challenging. Due to client-specific label spaces and varying co-occurrence patterns, correlations learned by individual clients inevitably deviate from the global structure, a phenomenon we term label correlation drift. To address this, we propose FedHarmony, a framework that harmonizes heterogeneous label correlations across clients. It introduces consensus correlation, capturing agreement among other clients and serving as a global teacher to correct biased local estimates. During aggregation, FedHarmony evaluates each client by both data size and correlation quality, assigning weights accordingly. Moreover, we develop an accelerated optimization algorithm for FedHarmony and theoretically establish faster convergence without sacrificing accuracy. Experiments on real-world federated multi-label datasets show that FedHarmony consistently outperforms state-of-the-art methods.

cs.LG↗
arXiv2026

FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts

Federated Domain Generalization for Person Re-Identification (FedDG-ReID) learns domain-invariant representations from decentralized data. While Vision Transformer (ViT) is widely adopted, its global attention often fails to distinguish pedestrians from high similarity backgrounds or diverse viewpoints -- a challenge amplified by cross-client distribution shifts in FedDG-ReID. To address this, we propose Federated Body Distribution Aware Visual Prompt (FedBPrompt), introducing learnable visual prompts to guide Transformer attention toward pedestrian-centric regions. FedBPrompt employs a Body Distribution Aware Visual Prompts Mechanism (BAPM) comprising: Holistic Full Body Prompts to suppress cross-client background noise, and Body Part Alignment Prompts to capture fine-grained details robust to pose and viewpoint variations. To mitigate high communication costs, we design a Prompt-based Fine-Tuning Strategy (PFTS) that freezes the ViT backbone and updates only lightweight prompts, significantly reducing communication overhead while maintaining adaptability. Extensive experiments demonstrate that BAPM effectively enhances feature discrimination and cross-domain generalization, while PFTS achieves notable performance gains within only a few aggregation rounds. Moreover, both BAPM and PFTS can be easily integrated into existing ViT-based FedDG-ReID frameworks, making FedBPrompt a flexible and effective solution for federated person re-identification. The code is available at https://github.com/leavlong/FedBPrompt.

cs.CV↗
arXiv2026

When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual Tokens

Downstream fine-tuning of vision-language-action (VLA) models enhances robotics, yet exposes the pipeline to backdoor risks. Attackers can pretrain VLAs on poisoned data to implant backdoors that remain stealthy but can trigger harmful behavior during inference. However, existing defenses either lack mechanistic insight into multimodal backdoors or impose prohibitive computational costs via full-model retraining. To this end, we uncover a deep-layer attention grabbing mechanism: backdoors redirect late-stage attention and form compact embedding clusters near the clean manifold. Leveraging this insight, we introduce Bera, a test-time backdoor erasure framework that detects tokens with anomalous attention via latent-space localization, masks suspicious regions using deep-layer cues, and reconstructs a trigger-free image to break the trigger-unsafe-action mapping while restoring correct behavior. Unlike prior defenses, Bera requires neither retraining of VLAs nor any changes to the training pipeline. Extensive experiments across multiple embodied platforms and tasks show that Bera effectively maintains nominal performance, significantly reduces attack success rates, and consistently restores benign behavior from backdoored outputs, thereby offering a robust and practical defense mechanism for securing robotic systems.

cs.RO↗
arXiv2026

DSSmoothing: Toward Certified Dataset Ownership Verification for Pre-trained Language Models via Dual-Space Smoothing

Large web-scale datasets have driven the rapid advancement of pre-trained language models (PLMs), but unauthorized data usage has raised serious copyright concerns. Existing dataset ownership verification (DOV) methods typically assume that watermarks remain stable during inference; however, this assumption often fails under natural noise and adversary-crafted perturbations. We propose the first certified dataset ownership verification method for PLMs under a gray-box setting (i.e., the defender can only query the suspicious model but is aware of its input representation module), based on dual-space smoothing (i.e., DSSmoothing). To address the challenges of text discreteness and semantic sensitivity, DSSmoothing introduces continuous perturbations in the embedding space to capture semantic robustness and applies controlled token reordering in the permutation space to capture sequential robustness. DSSmoothing consists of two stages: in the first stage, triggers are collaboratively embedded in both spaces to generate norm-constrained and robust watermarked datasets; in the second stage, randomized smoothing is applied in both spaces during verification to compute the watermark robustness (WR) of suspicious models and statistically compare it with the principal probability (PP) values of a set of benign models. Theoretically, DSSmoothing provides provable robustness guarantees for dataset ownership verification by ensuring that WR consistently exceeds PP under bounded dual-space perturbations. Extensive experiments on multiple representative web datasets demonstrate that DSSmoothing achieves stable and reliable verification performance and exhibits robustness against potential adaptive attacks. Our code is available at https://github.com/NcepuQiaoTing/DSSmoothing.

cs.CR↗
arXiv2026

Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation

Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue by leveraging model representations (e.g., mean feature vectors) to correct local training; however, they often face two key limitations: 1) Incomplete Contextual Representation Learning: Current approaches primarily focus on final-layer features, overlooking critical multi-level cues and thus diluting essential context for accurate segmentation. 2) Layerwise Style Bias Accumulation: Although utilizing representations can partially align global features, these methods neglect domain-specific biases within intermediate layers, allowing style discrepancies to build up and reduce model robustness. To address these challenges, we propose FedBCS to bridge feature representation gaps via domain-invariant contextual prototypes alignment. Specifically, we introduce a frequency-domain adaptive style recalibration into prototype construction that not only decouples content-style representations but also learns optimal style parameters, enabling more robust domain-invariant prototypes. Furthermore, we design a context-aware dual-level prototype alignment method that extracts domain-invariant prototypes from different layers of both encoder and decoder and fuses them with contextual information for finer-grained representation alignment. Extensive experiments on two public datasets demonstrate that our method exhibits remarkable performance.

cs.CV↗
arXiv2026

MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux

Graphical user interface (GUI) agents are rapidly progressing toward autonomous interaction and reliable task execution across diverse applications. However, two central challenges remain unresolved: automating the evaluation of agent trajectories and generating high-quality training data at scale to enable continual improvement. Existing approaches often depend on manual annotation or static rule-based verification, which restricts scalability and limits adaptability in dynamic environments. We present MagicGUI-RMS, a multi-agent reward model system that delivers adaptive trajectory evaluation, corrective feedback, and self-evolving learning capabilities. MagicGUI-RMS integrates a Domain-Specific Reward Model (DS-RM) with a General-Purpose Reward Model (GP-RM), enabling fine-grained action assessment and robust generalization across heterogeneous GUI tasks. To support reward learning at scale, we design a structured data construction pipeline that automatically produces balanced and diverse reward datasets, effectively reducing annotation costs while maintaining sample fidelity. During execution, the reward model system identifies erroneous actions, proposes refined alternatives, and continuously enhances agent behavior through an automated data-reflux mechanism. Extensive experiments demonstrate that MagicGUI-RMS yields substantial gains in task accuracy, behavioral robustness. These results establish MagicGUI-RMS as a principled and effective foundation for building self-improving GUI agents driven by reward-based adaptation.

cs.AI↗
arXiv2026

Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation

Humanoid robot manipulation is a crucial research area for executing diverse human-level tasks, involving high-level semantic reasoning and low-level action generation. However, precise scene understanding and sample-efficient learning from human demonstrations remain critical challenges, severely hindering the applicability and generalizability of existing frameworks. This paper presents a novel RGMP-S, Recurrent Geometric-prior Multimodal Policy with Spiking features, facilitating both high-level skill reasoning and data-efficient motion synthesis. To ground high-level reasoning in physical reality, we leverage lightweight 2D geometric inductive biases to enable precise 3D scene understanding within the vision-language model. Specifically, we construct a Long-horizon Geometric Prior Skill Selector that effectively aligns the semantic instructions with spatial constraints, ultimately achieving robust generalization in unseen environments. For the data efficiency issue in robotic action generation, we introduce a Recursive Adaptive Spiking Network. We parameterize robot-object interactions via recursive spiking for spatiotemporal consistency, fully distilling long-horizon dynamic features while mitigating the overfitting issue in sparse demonstration scenarios. Extensive experiments are conducted across the Maniskill simulation benchmark and three heterogeneous real-world robotic systems, encompassing a custom-developed humanoid, a desktop manipulator, and a commercial robotic platform. Empirical results substantiate the superiority of our method over state-of-the-art baselines and validate the efficacy of the proposed modules in diverse generalization scenarios. To facilitate reproducibility, the source code and video demonstrations are publicly available at https://github.com/xtli12/RGMP-S.git.

cs.RO↗
arXiv2025

RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation

Humanoid robots exhibit significant potential in executing diverse human-level skills. However, current research predominantly relies on data-driven approaches that necessitate extensive training datasets to achieve robust multimodal decision-making capabilities and generalizable visuomotor control. These methods raise concerns due to the neglect of geometric reasoning in unseen scenarios and the inefficient modeling of robot-target relationships within the training data, resulting in significant waste of training resources. To address these limitations, we present the Recurrent Geometric-prior Multimodal Policy (RGMP), an end-to-end framework that unifies geometric-semantic skill reasoning with data-efficient visuomotor control. For perception capabilities, we propose the Geometric-prior Skill Selector, which infuses geometric inductive biases into a vision language model, producing adaptive skill sequences for unseen scenes with minimal spatial common sense tuning. To achieve data-efficient robotic motion synthesis, we introduce the Adaptive Recursive Gaussian Network, which parameterizes robot-object interactions as a compact hierarchy of Gaussian processes that recursively encode multi-scale spatial relationships, yielding dexterous, data-efficient motion synthesis even from sparse demonstrations. Evaluated on both our humanoid robot and desktop dual-arm robot, the RGMP framework achieves 87% task success in generalization tests and exhibits 5x greater data efficiency than the state-of-the-art model. This performance underscores its superior cross-domain generalization, enabled by geometric-semantic reasoning and recursive-Gaussion adaptation.

cs.RO↗
arXiv2025

Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts

Large Language Model (LLM)-powered multi-agent systems (MAS) have rapidly advanced collaborative reasoning, tool use, and role-specialized coordination in complex tasks. However, reliability-critical deployment remains hindered by a systemic failure mode: hierarchical compliance under instruction conflicts (system-user, peer-peer), where agents misprioritize system-level rules in the presence of competing demands. Moreover, widely used macro-level metrics (e.g., pass@k) obscure these micro-level violations and offer little actionable guidance for remedy. In this work, we present a full-stack, three-stage framework: (1) Diagnose - Contextualized Role Adherence Score (CRAS), a query-wise, context-aware scoring metric that decomposes role adherence into four measurable dimensions; (2) Localize - attention drift analysis revealing that instruction conflicts are resolved by attention heads that are largely concentrated in middle layers; (3) Align - Surgical Alignment of Instruction Layers (SAIL), which installs LoRA only on the localized focal layers and optimizes a token-weighted DPO-style preference objective that credits tokens by their focal attentional contribution. Across standard benchmarks and MAS frameworks, our surgical approach improves instruction hierarchy compliance (e.g., +5.60% with AutoGen on MedQA) without full-model finetuning.

cs.CL↗
arXiv2025

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image interactions. Such cross-modal couplings can produce unsafe semantics even when individual inputs are benign, exposing the fragile safety awareness of current MLLMs. While recent works enhance safety by guiding models to reason about potential risks, unregulated reasoning traces may compromise alignment; although Group Relative Policy Optimization (GRPO) offers self-rewarded refinement without human supervision, it lacks verifiable signals for reasoning safety. To address this, we propose SafeGRPO a self-rewarded multimodal safety alignment framework that integrates rule-governed reward construction into GRPO, enabling interpretable and verifiable optimization of reasoning safety. Built upon the constructed SafeTag-VL-3K dataset with explicit visual, textual, and combined safety tags, SafeGRPO performs step-guided safety thinking to enforce structured reasoning and behavior alignment, substantially improving multimodal safety awareness, compositional robustness, and reasoning stability across diverse benchmarks without sacrificing general capabilities.

cs.CR↗
arXiv2025

Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks

Spiking neural networks (SNNs) are emerging as a promising alternative to traditional artificial neural networks (ANNs), offering biological plausibility and energy efficiency. Despite these merits, SNNs are frequently hampered by limited capacity and insufficient representation power, yet remain underexplored in remote sensing super-resolution (SR) tasks. In this paper, we first observe that spiking signals exhibit drastic intensity variations across diverse textures, highlighting an active learning state of the neurons. This observation motivates us to apply SNNs for efficient SR of RSIs. Inspired by the success of attention mechanisms in representing salient information, we devise the spiking attention block (SAB), a concise yet effective component that optimizes membrane potentials through inferred attention weights, which, in turn, regulates spiking activity for superior feature representation. Our key contributions include: 1) we bridge the independent modulation between temporal and channel dimensions, facilitating joint feature correlation learning, and 2) we access the global self-similar patterns in large-scale remote sensing imagery to infer spatial attention weights, incorporating effective priors for realistic and faithful reconstruction. Building upon SAB, we proposed SpikeSR, which achieves state-of-the-art performance across various remote sensing benchmarks such as AID, DOTA, and DIOR, while maintaining high computational efficiency. Code of SpikeSR will be available at https://github.com/XY-boy/SpikeSR.

cs.CV↗
arXiv2025

ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation

Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models due to its efficiency and zero additional inference cost. Many real-world applications require foundation models to specialize in several specific tasks simultaneously, motivating the need for efficient multi-task downstream adaptation. To address this need, existing studies have primarily explored two directions: Model Merging with LoRA, which shows advantages in training-free scenarios but still lags behind multi-task training in overall performance; and MoE-based LoRA approaches, which improve multi-task learning performance but introduce routers that hinder the mergeability of LoRA parameters and incur considerable inference overhead, thereby limiting real-world deployment practicality. To this end, we propose ThanoRA, a Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation framework that enables effective, efficient and unified multi-task downstream adaptation without introducing additional structure. ThanoRA performs multi-task learning by tailoring subspace allocation at initialization and enforcing diversity preservation throughout training: it allocates varying dimensions to construct task-specific low-rank subspaces driven by inter-task heterogeneity, enabling fine-grained knowledge injection, while diversity-preserving regularization mitigates task interference and subspace collapse, thereby fully exploiting the low-rank capacity. Extensive experiments across multimodal and text-only benchmarks under varying multi-task mixtures demonstrate that ThanoRA consistently outperforms strong baselines, surpassing even separate task-specific fine-tuning, while introducing no additional structures or inference overhead. Our code will be publicly available at: https://github.com/LiangJian24/ThanoRA.

cs.LG↗
arXiv2025

MAPO: Mixed Advantage Policy Optimization

Recent advances in reinforcement learning for foundation models, such as Group Relative Policy Optimization (GRPO), have significantly improved the performance of foundation models on reasoning tasks. Notably, the advantage function serves as a central mechanism in GRPO for ranking the trajectory importance. However, existing explorations encounter both advantage reversion and advantage mirror problems, which hinder the reasonable advantage allocation across different query samples. In this work, we propose an easy but effective GRPO strategy, Mixed Advantage Policy Optimization (MAPO). We reveal that the trajectory appears with different certainty and propose the advantage percent deviation for samples with high-certainty trajectories. Furthermore, we dynamically reweight the advantage function for samples with varying trajectory certainty, thereby adaptively configuring the advantage function to account for sample-specific characteristics. Comparison with related state-of-the-art methods, along with ablation studies on different advantage variants, validates the effectiveness of our approach.

cs.AI↗
arXiv2025

An Empirical Study of Federated Prompt Learning for Vision Language Model

The Vision Language Model (VLM) excels in aligning vision and language representations, and prompt learning has emerged as a key technique for adapting such models to downstream tasks. However, the application of prompt learning with VLM in federated learning (FL) scenarios remains underexplored. This paper systematically investigates the behavioral differences between language prompt learning (LPT) and vision prompt learning (VPT) under data heterogeneity challenges, including label skew and domain shift. We conduct extensive experiments to evaluate the impact of various FL and prompt configurations, such as client scale, aggregation strategies, and prompt length, to assess the robustness of Federated Prompt Learning (FPL). Furthermore, we explore strategies for enhancing prompt learning in complex scenarios where label skew and domain shift coexist, including leveraging both prompt types when computational resources allow. Our findings offer practical insights into optimizing prompt learning in federated settings, contributing to the broader deployment of VLMs in privacy-preserving environments.

cs.LG↗