Ziniu Li

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang, Zhihang Lin, Yang Yu, Ruoyu Sun, Zhi-Quan Luo
The 41st International Conference on Machine Learning (ICML), 2024

TL;DR: This work develops an RL method called ReMax for RLHF in LLMs, which is simple (6 lines of code) and efficient (less memory and fast training)

When is RL better than DPO in RLHF? A Representation and Optimization Perspective
Ziniu Li* , Tian Xu*, Yang Yu
Oral Presentation, The 12th International Conference on Learning Representations (ICLR) (Tiny Paper Track), 2024

TL;DR: This work analyzes the reward modeling quality in view of representations, and analyzed the optimization error sources

Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
Ziniu Li* , Tian Xu*, Zeyu Qin, Yang Yu, Zhi-Quan Luo
Spotlight Presentation (acceptance rate < 5%), In Neural Information Processing System (NeurIPS) 37, 2023

TL;DR: This work validates that importance sampling is effective in data selection when leveraging multiple imperfect (out-of-distribution and low-quality) data sources

Provably Efficient Adversarial Imitation Learning with Unknown Transitions
Tian Xu*, Ziniu Li* , Yang Yu, Zhi-Quan Luo
Oral Presentation (acceptance rate < 3%), The 39th Conference on Uncertainty in Artificial Intelligence (UAI), 2023

TL;DR: This work addresses the online sample efficiency issue of adversarial imitation learning by bridging it with reward-free exploration

Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
Tian Xu*, Ziniu Li* , Yang Yu, Zhi-Quan Luo
arXiv:2208.01899

TL;DR: This work presents the first horizon-free sample complexity bound of adversarial imitation learning (AIL), providing an answer to the open question –why does AIL outperform BC by a wide margin, particularly in the low data regime ? (raised in CoRL 2019 best paper by Ghasemipour et al.)