9 papers
Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
Hao Wu, Shoucheng Song, Chang Yao +4
Multi-Agent Debate (MAD) improves the reasoning performance of Large Language Models (LLMs) through multi-round interaction. However, LLMs in MAD are highly susceptible to blind co…
From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training
Jinwen Wang, Youfang Lin, Xiaobo Hu +4
Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL). Given t…
Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos
Jinwen Wang, Youfang Lin, Xiaobo Hu +2
Pre-training on large-scale videos to improve reinforcement learning efficiency is promising yet remains challenging. Existing methods typically treat the agent as an indivisible e…
Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization
Jinwen Wang, Youfang Lin, Xiaobo Hu +4
Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge…
DRFormer: A Dual-Regularized Bidirectional Transformer for Person Re-identification
Ying Shu, Pujian Zhan, Huiqi Yang +3
Both fine-grained discriminative details and global semantic features can contribute to solving person re-identification challenges, such as occlusion and pose variations. Vision f…
Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution
Hao Wu, Shoucheng Song, Chang Yao +4
In multi-agent systems, explicit cognition of teammates' decision logic serves as a critical factor in facilitating coordination. Communication (i.e., ``\textit{Tell}'') can assist…