I am a second-year Ph.D. student at Stanford CS, advised by Professor James Zou and Stefano Ermon. Before that, I received my B.S. in Math and Computer Science at Yuanpei College, Peking University, under the advice of Professor Liwei Wang and Di He. I focus on advancing foundational generative AI through algorithm design and high-performance computing. If you’re interested in my work, please feel free to contact me!

News

• (Apr. 2025) I am currently working part-time at NVIDIA Deep Imagination Research and will join as full-time intern this summer in Santa Clara.
• (Apr. 2025) Google intern work LLM Constrained Decoding was accepted by AISTATS 2025, and ICV-Hallucination by ICLR 2025 (Spotlight). See you in Singapore and Phuket!
• (Sept. 2024) Two papers was accepted by NeurIPS 2024, including training-free guidance (Spotlight) and geometric trajectory models. See you in Vancouver!

Selected Publications

• (AISTATS 2025) Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models
  Haotian Ye, Himanshu Jain, Chong You, Ananda Theertha Suresh, Haowei Lin, James Zou, Felix Yu
  [Paper]
• (NeurIPS 2024, Spotlight) TFG: Unified Training-Free Guidance for Diffusion Models
  Haotian Ye*, Haowei Lin*, Jiaqi Han*, Minkai Xu, Sheng Liu, Yitao Liang, Jianzhu Ma, James Zou, Stefano Ermon
  [Paper]
• (Nature Machine Intelligence) A computational framework for neural network-based variational Monte Carlo with Forward Laplacian
  Ruichen Li*, Haotian Ye*, Du Jiang, Xuelan Wen, Chuwei Wang, Zhe Li, Xiang Li, Di He, Ji Chen, Weiluo Ren, Liwei Wang
  [Paper]
• (NeurIPS 2023, Oral) Towards Revealing the Mystery behind Chain of Thought: a Theoretical Perspective
  Guhao Feng*, Bohang Zhang*, Yuntian Gu*, Haotian Ye*, Di He, Liwei Wang
  [Paper] [Video] [Slides]
• (ICML 2023, Oral) On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness
  Haotian Ye*, Xiaoyu Chen*, Liwei Wang, Simon Shaolei Du
  [Paper]
• (AISTATS 2023) Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise
  Haotian Ye, James Zou, Linjun Zhang
  [Paper] [Code] [Video] [Slides]
• (ICLR 2023) Discovering Latent Knowledge in Language Models Without Supervision
  Collin Burns*, Haotian Ye*, Dan Klein, Jacob Steinhardt
  [Paper]
• (J. Chem. Phys. Aug 2023) DeePMD-kit v2: A software package for Deep Potential models
  Jinzhe Zeng, Duo Zhang, …, Haotian Ye, …, Weinan E, Roberto Car, Linfeng Zhang, Han Wang
  [Paper]
• (NeurIPS 2021) Towards a Theoretical Framework of Out-of-Distribution Generalization
  Haotian Ye*, Chuanlong Xie, Tianle Cai, Ruichen Li, Zhenguo Li, Liwei Wang
  [Paper] [Code] [Video] [Slides]

Selected Awards

• Weiming Scholar of Peking University (1%), 2023
• Person of the Year of Peking University (10 people/year), 2021
• May 4 scholarship (1%, Rank 1), 2021
• National scholarship (1%, Rank 2), 2019
• Leo Koguan scholarship (1%), 2020
• Merit student pacesetter (2%), 2019
• Chinese Mathematical Olympiad (First Prize, Rank 7 in China), 2017