Kuan-Hsun Tu

I am a research assistant working with Prof. Tsung-Wei Ke at National Taiwan University. My research goal is to build general-purpose robots, focusing on how reinforcement learning can develop reusable physical skills for novel tasks. My research experience spans flow matching, behavioral foundation models, and dexterous robot manipulation. I also collaborate with Alberta Longhini and Tyler Ga Wei Lum in Prof. Jeannette Bohg's group (IPRL) at Stanford University. I am applying to PhD programs for Fall 2027.

Kuan-Hsun Tu playing an acoustic guitar

Publications ( * Equal contribution, † Corresponding author)

BLS reconstructs a flat low reward and a sharp high reward, so the zero-shot policy concentrates on high-reward states where OLS does not

Task Inference Beyond Least Squares in Behavioral Foundation Models

Kuan-Hsun Tu*, Chien-Sheng Chiang†*, Hsin-Wei Chen, Tsung-Wei Ke

NeurIPS 2026 PTA Workshop (Oral).

CNP-Flow couples noise across frames for temporally consistent video prediction and collision-free motion planning

Learning Conditional Source Distribution via Flow Reversal for Temporal Flow Matching

Kuan-Hsun Tu*, Hsuan-Chi Liu†*, Jia-Wei Liao*, Chien-Sheng Chiang, Cheng-Fu Chou, Tsung-Wei Ke

Under review, 2026.

COT-FM comparison of transport paths on 5-Gaussians and Two Moons distributions

COT-FM: Cluster-wise Optimal Transport Flow Matching

Chien-Sheng Chiang*, Kuan-Hsun Tu†*, Jia-Wei Liao*, Cheng-Fu Chou, Tsung-Wei Ke

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

RobotArena translates real videos into simulated environments for robot policy evaluation

RobotArena ∞: Scalable Robot Benchmarking via Real-to-Sim Translation

Yash Jangir, Yidi Zhang*, Kashu Yamazaki*, Chenyu Zhang*, Kuan-Hsun Tu, Tsung-Wei Ke, Lei Ke, Yonatan Bisk, Katerina Fragkiadaki

International Conference on Learning Representations (ICLR), 2026.

DexMan pairs human demonstrations with bimanual robot manipulation of everyday objects

DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos

Jhen Hsieh, Kuan-Hsun Tu, Kuo-Han Hung, Tsung-Wei Ke

Under review, 2026.

Honors and Awards

Work and Teaching Experience

Spring 2026

Advanced Network Administration and System Administration

TA

Spring & Fall 2025

Network Administration and System Administration

Lead TA

Fall 2025

Parallel Programming

TA