Jiawei Zhou
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper introduces Capability Self-Assessment (CSA), a crucial ability for LLMs to recognize their limitations, and demonstrates that reinforcement learning is an effective method for teaching this skill without degrading the model's core capabilities.
GLOVES is a flow-based adaptation method that selectively corrects non-expert robot actions by guiding them toward a task-specific expert action distribution, thereby improving performance while maintaining agent autonomy.
Papers
Flow-based Policy Adaptation without Policy Updates
Luzhe Sun, Jingtian Ji, Haoran Chen, Jiawei Zhou +1 more
GLOVES is a flow-based adaptation method that selectively corrects non-expert robot actions by guiding them toward a task-specific expert action distribution, thereby improving performance while maint…