Hung-Chieh Fang

I am a senior undergraduate 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 student 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  /  Linkedin

Research

I am broadly interested in robust machine learning algorithm and robot learning.

We introduce SSD, a framework that enhances representation quality in federated learning by improving inter-client uniformity. SSD includes a dimension-scaled regularization term to softly separate client embeddings while preserving data structure and a projector distillation term to transfer optimization benefits from the projector to the encoder.

We identify the unsolved Extreme UniDA sub-task, highlighting the limitations of existing partial domain matching paradigms. We propose using self-supervised loss to tackle dimensional collapse in target representation and step toward more comprehensive UniDA.

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 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.

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

Teaching

This template is adapted from here.