← Search

Saehun Chun

2 accepted papers

2026

Efficient Skill Grounding via Code Refactoring with Small Language Models

ICML 2026poster

Effective skill grounding is essential for deploying reusable skills in embodied agents, as even minor embodiment or environmental differences can render an entire skill incompatible. This challenge is particularly pronounced in embodied settings, where agents must operate in dynamic, partially obse…

Cited by 0SourceScholar
2026

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents

ICML 2026poster

Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structured control programs. However, policy generation in open-domain embodied environments suffers from two fundamental limit…

Cited by 0SourceScholar