Yunzhe Hu

yzhu [at] cs [dot] hku [dot] hk

I'm a PhD student at the School of Computing and Data Science, University of Hong Kong, advised by Prof. Dong Xu, and have worked with Prof. Difan Zou. Previously, I received my bachelor's degree from Shanghai Jiao Tong University in 2022, where I studied control science and engineering.

I’m currently working on empowering an agent to learn from play (suboptimal trajectory) without hand-crafted extrinsic rewards and adapt in few/zero-shot. I have also done research in bridging the gap and revealing the connections between energy-based learning and practical Transformer design.

Google Scholar / X / GitHub

Research

I'm interested in robot learning, deep reinforcement learning, and machine learning in general.

Below are first-authored papers during my PhD. See the full list on Google Scholar.

Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization
Yunzhe Hu, Difan Zou, Dong Xu
ICLR, 2026
project page / paper / arXiv / code / slides / poster / bibtex

@inproceedings{
  hu2026hyperset,
  title={Hyper-{SET}: Designing Transformers via Hyperspherical Energy Minimization},
  author={Yunzhe Hu and Difan Zou and Dong Xu},
  booktitle={The Fourteenth International Conference on Learning Representations},
  year={2026},
  url={https://openreview.net/forum?id=FinhjyDgYA}
}

A principled, top-down Transformer design grounded in energy-based interpretation: symmetric attention, feedforward, and RMS normalization all emerge from iterative constrained energy minimization on the hypersphere, yielding a compact recurrent-depth model competitive across reasoning, classification, and masked modeling tasks.

An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
Yunzhe Hu, Difan Zou, Dong Xu
NeurIPS, 2024
paper / arXiv / slides / poster / bibtex

@inproceedings{
  hu2024an,
  title={An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models},
  author={Yunzhe Hu and Difan Zou and Dong Xu},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year={2024},
  url={https://openreview.net/forum?id=CAC74VuMWX}
}

Miscellanea

Talks

Towards Understanding and Designing Transformers: From Sparse Rate Reduction to Generalized Hopfield Energy, CRF Yearly Workshop, HK Polytechnic University, June 2025

Academic Service (Reviewer)

ICML, 2025
NeurIPS, 2025
ICLR, 2026

Teaching

Teaching Assistant, COMP7404 Computational Intelligence and Machine Learning, Spring 2023
Teaching Assistant, COMP7404 Computational Intelligence and Machine Learning, Fall 2023
Teaching Assistant, COMP7404 Computational Intelligence and Machine Learning, Spring 2025
Teaching Assistant, COMP3314 Introduction to machine learning, Fall 2025

Last updated: April 25, 2026

Thanks for Jon Barron's website.