Yixiao HUANG

prof_pic.jpg

Berkeley, CA, United States

yixiaoh@berkeley.edu
How to pronounce?
My first name can be pronounced as “e-/ɕjɑʊ/”:

I’m Yixiao HUANG (Chinese name: 黄一笑) and I’m a second-year PhD student at UC Berkeley EECS supervised by Prof. Somayeh Sojoudi. I also work closely with Prof. Song Mei. I’m interested in establishing the theoretical foundations for generative models to enhance their efficiency and reliability.

I received my Bachelor’s degree in Informaton Engineering in June, 2023 from Department of Electrical Engineering, City University of Hong Kong. I was fortunate to work with Prof. Rosa CHAN who patiently guided me to start my research adventure. I also had a great time at University of Michigan, working with Prof. Samet Oymak on the theoretical foundations of self-attention and hybrid models.

news

Jun 12, 2026 Introducing Agent’s Last Exam, a large-scale benchmark evaluating AI agents on long-horizon, economically valuable professional tasks. Check out what we find on the importance of the harness vs. models, and how we confirm the downgrade of Claude Fable 5.
Jun 12, 2026 Two papers are accepted by ICML 2026:
Jun 12, 2026 A new preprint on implicit Chain-of-Thought is out!

selected publications

* indicates equal contribution
  1. Preprint
    Transformers Provably Learn to Internalize Chain-of-Thought
    Yixiao HuangHanlin Zhu, Zixuan Wang, Jiantao Jiao, Stuart Russell, and 2 more authors
    arXiv preprint arXiv:2605.28600, 2026
  2. ICML 2026
    Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
    Ziheng Cheng*Yixiao Huang*Hanlin Zhu, Haoran Geng, Somayeh Sojoudi, and 3 more authors
    International Conference on Machine Learning (ICML), 2026
  3. ICML 2026
    Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge
    Xutao Ma*, Yixiao Huang*Hanlin Zhu, and Somayeh Sojoudi
    International Conference on Machine Learning (ICML), Spotlight, 2026
  4. NeurIPS 2025
    Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
    Yixiao Huang*Hanlin Zhu*Tianyu Guo*, Jiantao Jiao, Somayeh Sojoudi, and 3 more authors
    Advances in Neural Information Processing Systems (NeurIPS), 2025
  5. NeurIPS D&B
    OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
    Ziheng Cheng*Yixiao Huang*, Hui Xu, Somayeh Sojoudi, Xuandong Zhao, and 2 more authors
    Advances in Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS D&B), 2025
  6. AISTATS 2024
    Mechanics of Next Token Prediction with Self-Attention
    Yingcong Li*, Yixiao Huang*M. Emrullah IldizAnkit Singh Rawat, and Samet Oymak
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
Flag Counter