6 papers
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models
Xinyi Xie, Zican Hu, Zhanyu Liu +7
Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining, yet their generalization remains far more fragile than that of LLMs and VLM…
Diversity-Incentivized Exploration for Versatile Reasoning
Zican Hu, Shilin Zhang, Yafu Li +7
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a crucial paradigm for incentivizing reasoning capabilities in Large Language Models (LLMs). Due to vast state-…
Scalable In-Context Q-Learning
Jinmei Liu, Fuhong Liu, Zhenhong Sun +6
Recent advancements in language models have demonstrated remarkable in-context learning abilities, prompting the exploration of in-context reinforcement learning (ICRL) to extend t…
Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation
Jinmei Liu, Haoru Li, Zhenhong Sun +6
Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human prefere…
Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
Shilin Zhang, Zican Hu, Wenhao Wu +7
Offline meta-RL usually tackles generalization by inferring task beliefs from high-quality samples or warmup explorations. The restricted form limits their generality and usability…
Mixture-of-Experts Meets In-Context Reinforcement Learning
Wenhao Wu, Fuhong Liu, Haoru Li +4
In-context reinforcement learning (ICRL) has emerged as a promising paradigm for adapting RL agents to downstream tasks through prompt conditioning. However, two notable challenges…