Scholar
Hui Yuan
Google Scholar ID: 9gxhjYcAAAAJ
Princeton University
Citations & Impact
Citations
304
H-index
7
i10-index
6
Publications
19
Co-authors
10
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement (preprint, leading contributor)
- Gradient Guidance for Diffusion Models: An Optimization Perspective (NeurIPS 2024, equal contribution)
- MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences (ICML 2024)
- Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement (NeurIPS 2023)
- Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective (NeurIPS 2023)
- Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization (NeurIPS 2022)
- Learning Entangled Single-Sample Gaussians in the Subset-of-Signals Model (COLT 2020)
