4 papers
The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models
Yan Wang, Yitao Xu, Nanhan Shen +3
Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumption by introducing COMMITTEEAUDIT, a pos…
FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
Han Zhao, Jingbo Wang, Wenxuan Song +5
Enabling VLA models to predict environmental dynamics, known as world modeling, has been recognized as essential for improving robotic reasoning and generalization. However, curren…
Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
Min Cai, Yu Liang, Longzheng Wang +6
Reinforcement learning (RL) has played a central role in recent advances in large reasoning models (LRMs), yielding strong gains in verifiable and open-ended reasoning. However, tr…
TRE: Encouraging Exploration in the Trust Region
Chao Huang, Yujing Lu, Quangang Li +8
Entropy regularization is a standard technique in reinforcement learning (RL) to enhance exploration, yet it yields negligible effects or even degrades performance in Large Languag…