8 citations · 15 across the 30 of their papers we have counts for
33 papers
Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation
Xingyue Zhao, Wenke Huang, Linghao Zhuang +11
Federated learning enables medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains challenging. Exis…
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi +9
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…
DriveCache: Action-Aware Caching for Driving World Model Inference
Jianchun Yang, Jian Liang, Xianda Guo +5
Driving video generation models support autonomous-driving development by predicting controllable future scenes for simulation, planning evaluation, and offline data generation. Di…
Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models
Wenwen He, Wenke Huang, Wei Yang Bryan Lim +1
Large language models (LLMs) are increasingly involved in group decision-making with other LLMs and humans. Yet it remains unclear whether their influence is driven by persuasion-o…
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…
Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning
Qianlong Yang, Bowen Ye, Xianda Guo +4
Despite the progress of multimodal large language models (MLLMs), they continue to exhibit deficiencies in visual perception. Following visual instruction tuning, internal MLLM rep…
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
Pinhan Fu, Xianda Guo, Xuetao Li +5
Vision-Language-Action (VLA) models are deployed through pipelines that end users cannot audit, and a poisoned VLA can behave normally on clean observations while a small visual tr…
Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models
Xuankun Rong, Wenke Huang, Bo Du +2
As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable be…
Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning
Yiyang Fang, Pei Fu, Jinjie Li +7
Multimodal Large Language Models (MLLMs) often follow a fixed Think-then-Answer paradigm, which is inefficient in heterogeneous multitask settings because simple inputs may not req…
Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance
Wenjie Qian, Bin Yang, Xiao Wang +4
Text-to-image person re-identification (TIPR) retrieves target persons using natural language descriptions. However, existing methods largely overlook resolution variance in real-w…
Co-policy: Responsive Human-Robot Co-Creation for Musical Performances
Xuetao Li, Wenke Huang, Mang Ye +4
Art has long stood as a pivotal expression of human creativity. Embodied artificial intelligence offers a route for generative models to participate in that creativity through phys…
StereoFactory: A Unified Merging Framework for Robust Stereo Matching
Xianda Guo, Pinhan Fu, Ruilin Wang +3
Stereo matching has advanced through foundation models trained on large-scale datasets, yet this paradigm suffers from a scalability bottleneck: incorporating new data requires cos…
Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
Xingyue Zhao, Wenke Huang, Linghao Zhuang +7
Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging. However, most federated LoRA methods adopt a uniform aggre…
BraveGuard: From Open-World Threats to Safer Computer-Use Agents
Yunhao Feng, Xiaohu Du, Xinhao Deng +13
Computer-use agents extend language models from text generation to sustained interaction with files, terminals, browsers, and external tools. This shift creates safety risks that a…
EchoRL: Reinforcement Learning via Rollout Echoing
Jinhe Bi, Aniri, Minglai Yang +9
Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceed…
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
Yunhao Feng, Yifan Ding, Yingshui Tan +6
Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We…
Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification
Xiao Wang, Minglei Yang, Bin Yang +4
Identifying key individuals in video scenes is essential for applications such as automated video editing and intelligent surveillance. Current methods primarily focus on static im…
Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
Junxiang Wu, Zhiqiang Kou, Hongwei Zeng +7
Label Distribution Learning (LDL) models supervision as an instance-wise probability distribution, enabling fine-grained learning under inherent ambiguity, but its success relies o…
ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis
Lubin Gan, Jing Zhang, Heng Zhang +4
Whole slide image (WSI) analysis heavily relies on multiple instance learning (MIL). While recent methods benefit from large-scale foundation models and advanced sequence modeling…
When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual Tokens
Xuetao Li, Pinhan Fu, Wenke Huang +7
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…
EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models
Yiyang Fang, Wenke Huang, Pei Fu +5
Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture the complexity and subjectivity of…
MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux
Zecheng Li, Zhihui Cao, Wenke Huang +17
Graphical user interface (GUI) agents are rapidly progressing toward autonomous interaction and reliable task execution across diverse applications. However, two central challenges…
Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target Recognition
Yuchao Hou, Zixuan Zhang, Jie Wang +9
As a critical application of computational intelligence in remote sensing, deep learning-based synthetic aperture radar (SAR) image target recognition facilitates intelligent perce…
DSSmoothing: Toward Certified Dataset Ownership Verification for Pre-trained Language Models via Dual-Space Smoothing
Ting Qiao, Xing Liu, Wenke Huang +3
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 datase…