2 papers
cs.LG2025
The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards
Sukai Huang, Shu-Wei Liu, Nir Lipovetzky +1
While Vision-Language Models (VLMs) are increasingly used to generate reward signals for training embodied agents to follow instructions, our research reveals that agents guided by…
cs.CL2024
Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation
Sukai Huang, Trevor Cohn, Nir Lipovetzky
The capability of Large Language Models (LLMs) to plan remains a topic of debate. Some critics argue that strategies to boost LLMs' reasoning skills are ineffective in planning tas…