collaborators

12 papers

cs.RO2026

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…

cs.CV2026

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

Xingyue Zhao, Wenke Huang, Xingguang Wang +5

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…

cs.LG2025

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

Jian Liang, Wenke Huang, Xianda Guo +3

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…

cs.AI2025

MAPO: Mixed Advantage Policy Optimization

Wenke Huang, Quan Zhang, Yiyang Fang +11

Recent advances in reinforcement learning for foundation models, such as Group Relative Policy Optimization (GRPO), have significantly improved the performance of foundation models…

cs.LG2025

An Empirical Study of Federated Prompt Learning for Vision Language Model

Zhihao Wang, Wenke Huang, Tian Chen +7

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 ta…

cs.CV2025

Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency

Yanbiao Ma, Wei Dai, Bowei Liu +5

Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for…