collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

Defeating the Training-Inference Mismatch via FP16

Penghui Qi, Zichen Liu, Xiangxin Zhou +4

Reinforcement learning (RL) fine-tuning of large language models (LLMs) often suffers from instability due to the numerical mismatch between the training and inference policies. Wh…

cs.LG2025

Nonparametric Data Attribution for Diffusion Models

Yutian Zhao, Chao Du, Xiaosen Zheng +2

Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require acc…

cs.LG2025

Continual Reinforcement Learning by Planning with Online World Models

Zichen Liu, Guoji Fu, Chao Du +2

Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented seq…

cs.LG2025

Reinforcing General Reasoning without Verifiers

Xiangxin Zhou, Zichen Liu, Anya Sims +6

The recent paradigm shift towards training large language models (LLMs) using DeepSeek-R1-Zero-style reinforcement learning (RL) on verifiable rewards has led to impressive advance…

cs.LG2025

Optimizing Anytime Reasoning via Budget Relative Policy Optimization

Penghui Qi, Zichen Liu, Tianyu Pang +3

Scaling test-time compute is crucial for enhancing the reasoning capabilities of large language models (LLMs). Existing approaches typically employ reinforcement learning (RL) to m…

cs.LG2025

Understanding R1-Zero-Like Training: A Critical Perspective

Zichen Liu, Changyu Chen, Wenjun Li +5

DeepSeek-R1-Zero has shown that reinforcement learning (RL) at scale can directly enhance the reasoning capabilities of LLMs without supervised fine-tuning. In this work, we critic…