6 citations · 15 across the 7 of their papers we have counts for
7 papers
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
Hui Yuan, Yifan Zeng, Yue Wu +3
Reinforcement Learning from Human Feedback (RLHF) has become the predominant approach for language model (LM) alignment. At its core, RLHF uses a margin-based loss for preference o…
Conversational Dueling Bandits in Generalized Linear Models
Shuhua Yang, Hui Yuan, Xiaoying Zhang +3
Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities. Such systems utilize a multi-armed band…
PERSONA: A Reproducible Testbed for Pluralistic Alignment
Louis Castricato, Nathan Lile, Rafael Rafailov +2
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the…
Gradient Guidance for Diffusion Models: An Optimization Perspective
Yingqing Guo, Hui Yuan, Yukang Yang +2
Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidanc…
Diffusion Model for Data-Driven Black-Box Optimization
Zihao Li, Hui Yuan, Kaixuan Huang +4
Generative AI has redefined artificial intelligence, enabling the creation of innovative content and customized solutions that drive business practices into a new era of efficiency…
MaxMin-RLHF: Alignment with Diverse Human Preferences
Souradip Chakraborty, Jiahao Qiu, Hui Yuan +5
Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an ap…
Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization
Jiahao Qiu, Hui Yuan, Jinghong Zhang +3
While modern biotechnologies allow synthesizing new proteins and function measurements at scale, efficiently exploring a protein sequence space and engineering it remains a dauntin…