8 citations · 15 across the 5 of their papers we have counts for
5 papers
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
Jialei Chen, Kai Wang, Kang Chen +9
Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change th…
On Designing Effective RL Reward at Training Time for LLM Reasoning
Jiaxuan Gao, Shusheng Xu, Wenjie Ye +6
Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve…
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
Shusheng Xu, Wei Fu, Jiaxuan Gao +6
Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can b…
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
Chao Yu, Jiaxuan Gao, Weilin Liu +5
There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data.…
Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward
Weilin Liu, Ye Mu, Chao Yu +6
Discovering hazardous scenarios is crucial in testing and further improving driving policies. However, conducting efficient driving policy testing faces two key challenges. On the…