Chen-Yu (Oscar) Lin

Hi! I am a PhD student at National Taiwan University, working in the NTU Robot Learning Lab under the supervision of Prof. Shao-Hua Sun. I also received my M.S. and B.S. from NTU.

My research focuses on enabling robots to learn complex behaviors through interaction with the physical world. I believe robots should actively interact with their environment to gather the information needed to learn effective, generalizable skills.

Google Scholar / GitHub / X / LinkedIn

Chen-Yu (Oscar) Lin

News

Research Interests

🔬

Physics-Informed Robot Learning

Enabling robots to infer latent physical properties, such as mass and stiffness, through interaction and to use them for manipulation.

🤖

Agentic Robot System

Building LLM/VLM-based agent systems that plan, explore, and write code to solve long-horizon robot tasks.

Research

PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration

Chen-Yu Lin*, Jing-Wen Chen*, Hsueh-En Chang, Hung-An Chen, Sheng-Hsun Chang, Chi-Pin Huang, Fu-En Yang, Min-Hung Chen, Yi-Ting Chen, Yu-Chiang Frank Wang, Shao-Hua Sun

Robot Learning Workshop @ NeurIPS 2026

project page / arXiv

A physics-informed code-as-policy agent system that actively explores to infer hidden physical properties (mass, stiffness) from robot proprioception, using a Planner and a Prioritizer to explore only when it is worth it.

* Equal contribution

Service

Teaching