7 papers
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…
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…
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…
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…
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…
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…