activity
20242026
most citedLearn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning

1 citations · 1 across the 7 of their papers we have counts for

collaborators

13 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.CV2025

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.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.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…

cs.LG2025

S2FGL: Spatial Spectral Federated Graph Learning

Zihan Tan, Suyuan Huang, Guancheng Wan +3

Federated Graph Learning (FGL) combines the privacy-preserving capabilities of federated learning (FL) with the strong graph modeling capability of Graph Neural Networks (GNNs). Cu…

cs.AI2025

CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process

Jinhe Bi, Danqi Yan, Yifan Wang +8

Recent Large Reasoning Models significantly improve the reasoning ability of Large Language Models by learning to reason, exhibiting the promising performance in solving complex ta…