Hengyu Fu

Publications

Selected Publications

• DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning.
  Hengyu Fu*, Tianyu Guo*, Zixuan Wang*, Hanlin Zhu*, Jason D. Lee, Jiantao Jiao, Stuart Russell, Song Mei.
  NeurIPS 2026. [Blog]

• Learning What to Remember: Test-Time Training via Context Distillation.
  Zixuan Wang*, Xingyu Dang*, Rui-Jie Zhu, Zixin Wen, Hengyu Fu, Wenhao Chai, Jason D. Lee.
  NeurIPS 2026.

• From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models.
  Hengyu Fu*, Baihe Huang*, Virginia Adams, Charles Wang, Junkeun Yi, Mohammad Mahdi Kamani, Venkat Krishna Srinivasan, Jiantao Jiao.
  ICML 2026.

• Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit.
  Bohan Zhang*, Zihao Wang*, Hengyu Fu, Jason D. Lee.
  ICLR 2026.

• Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data.
  Hengyu Fu, Zehao Dou, Jiawei Guo, Mengdi Wang, Minshuo Chen.
  ICLR 2025.

• Learning Hierarchical Polynomials of Multiple Nonlinear Features.
  Hengyu Fu, Zihao Wang, Eshaan Nichani, Jason D. Lee.
  ICLR 2025.

• What can a Single Attention Layer Learn? A Study Through the Random Features Lens.
  Hengyu Fu*, Tianyu Guo*, Yu Bai, Song Mei.
  NeurIPS 2023.

(*:Equal contributions)