activity
20242026
most citedImitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems

2 citations · 2 across the 6 of their papers we have counts for

collaborators

8 papers

cs.LG2026

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging

Jiapeng Wang, Changxin Tian, Kunlong Chen +5

Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive…

cs.CL2025

Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data

Jiapeng Wang, Yiwen Hu, Yanzipeng Gao +7

As access to high-quality, domain-specific data grows increasingly scarce, multi-epoch training has become a practical strategy for adapting large language models (LLMs). However,…

cs.CL2025

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics

Jiapeng Wang, Changxin Tian, Kunlong Chen +5

Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscur…

cs.CL2025

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Changxin Tian, Jiapeng Wang, Qian Zhao +7

Recent advances in learning rate (LR) scheduling have demonstrated the effectiveness of decay-free approaches that eliminate the traditional decay phase while maintaining competiti…

cs.AI2025

RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library

Jiapeng Wang, Jinhao Jiang, Zhiqiang Zhang +2

The advancement of reasoning capabilities in Large Language Models (LLMs) requires substantial amounts of high-quality reasoning data, particularly in mathematics. Existing data sy…

cs.CL2024

Enhancing LLM Reasoning with Reward-guided Tree Search

Jinhao Jiang, Zhipeng Chen, Yingqian Min +12

Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By alloc…