collaborators

7 papers

cs.CL2025

How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices

Han Peng, Peiyu Liu, Zican Dong +5

Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yiel…

cs.LG2025

FlowRL: Matching Reward Distributions for LLM Reasoning

Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang +20

We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced…

cs.CL2025

From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

Jia Deng, Jie Chen, Zhipeng Chen +7

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditiona…

cs.CL2025

Reasoning with Exploration: An Entropy Perspective

Daixuan Cheng, Shaohan Huang, Xuekai Zhu +4

Balancing exploration and exploitation is a central goal in reinforcement learning (RL). Despite recent advances in enhancing large language model (LLM) reasoning, most methods lea…

cs.CL2025

An Empirical Study on Eliciting and Improving R1-like Reasoning Models

Zhipeng Chen, Yingqian Min, Beichen Zhang +10

In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL…

cs.CL2024

How to Synthesize Text Data without Model Collapse?

Xuekai Zhu, Daixuan Cheng, Hengli Li +7

Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic…