Hung-Chieh Fang

I am a senior undergrad majoring in Computer Science at National Taiwan University, where I am fortunate to be advised by Professors Hsuan-Tien Lin, Yun-Nung (Vivian) Chen and Shao-Hua Sun.

Currently, I am a visiting research intern at Stanford University, working with Prof. Dorsa Sadigh and Amber Xie.

Previously, I was a visiting student at The Chinese University of Hong Kong, where I had the privilege of working with Dr. Yifei Zhang and Prof. Irwin King.

Email  /  CV  /  Google Scholar  /  Github  /  Twitter  /  Linkedin

Research

I am broadly interested in robotics, machine learning and reinforcement learning. My research goal is to develope robots capable of performing complex tasks at or beyond human-level proficiency. I am particularly interested in the following areas:

• Adaptation to distribution shift (e.g., DC-UniDA, SSD): For robots to be readily used in the real world, they must have almost perfect success rate (> 99%). This requires the ability to adapt (or safely explore) in environments with distribution shifts. I am interested in algorithms that enable test-time adaptation/exploration.
• Dexterous manipulation: To fully unlock the potential of robots in complex tasks such as in-hand manipulation and tool use, fine-grained control is essential. I am interested in how to scale up RL/IL for these tasks.

We explore how to improve representation uniformity under highly non-IID client distributions where representations are non-shared (hence no direct cross-client separation loss). We propose soft separation, which regularizes each client toward a distinct subspace to improve inter-client uniformity while preserving structure.

We found that partial alignment loss fails to outperform the simplest baseline—training only on source data—when there is a source-target label imbalance, due to dimensional collapse in target representations. We address this using de-collapse techniques from self-supervised learning, advancing toward more comprehensive universal domain adaptation.

We propose combining the signal from historical answers with the noise-reduction ability of knowledge distillation to improve information retrieval and question answering.

Projects

We propose using vision as a surrogate for paired transcripts to enrich the semantic information in self-supervised speech models.

We propose a method for retrieving task-relevant data for imitation learning without requiring expert demonstrations. Our approach leverages text descriptions in combination with a vision-language model to enable zero-shot behavior retrieval.

Teaching

This template is adapted from here.