← Search

Changwei Yao

2 accepted papers

2026

Reward Evolution with Graph-Of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning

ICRA 2026poster

Designing effective reward functions remains a major challenge in reinforcement learning (RL), often requiring considerable human expertise and iterative refinement. Recent advances leverage Large Language Models (LLMs) for automated reward design, but these approaches are limited by hallucinations,…

2026

SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation

RSS 2026poster

Robotic navigation in human environments requires a spatio-temporal semantic representation that can reconcile open-vocabulary perception with long-term environmental changes. While foundation models provide strong zero-shot recognition, their predictions are intermittent and view-dependent, and nai…

Cited by 0SourceScholar