Get started
Author

Hengyu Fu

Observed name: Fu, Hengyu
OpenAlex ID: A5114137722
Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
2024 · Fu, Hengyu, Yang, Zhuoran, et al. · arXiv (Cornell University) · 72
PDF
From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
2025 · Fu, Hengyu, Huang, Baihe, et al. · arXiv (Cornell University) · 21
PDF
What can a Single Attention Layer Learn? A Study Through the Random Features Lens
2023 · Hengyu Fu, Tianyu Guo, et al. · neural information processing systems · 19
PDF
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
2026 · Fu, Hengyu, Guo, Tianyu, et al. · arXiv (Cornell University) · 7
PDF
Learning Hierarchical Polynomials of Multiple Nonlinear Features with Three-Layer Networks
2024 · Fu, Hengyu, Wang, Zihao, et al. · arXiv (Cornell University) · 5
PDF
Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models
2026 · Miao Li, Hanyang Jiang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 3
PDF
Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
2024 · Fu, Hengyu, Dou, Zehao, et al. · arXiv (Cornell University) · 3
PDF
Learning What to Remember: Test-Time Training via Context Distillation
2026 · Wang, Zixuan, Dang, Xingyu, et al. · arXiv (Cornell University) · 2
PDF
Principal Component Regression Dominates all Monotone Spectral Filters for Linear Regression
2026 · Kim, Juno, Fu, Hengyu, et al. · arXiv (Cornell University)
PDF
Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards
2026 · Chen, Fanchao, Fu, Hengyu, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count: 132
H-index: 5
I10-index: 3
Year
Topic
Type