4 papers
A Distribution-Matching Perspective on LLM Training Algorithms
Yanxing Huang, Bingzhang Yan, Zihan Tang +3
In this work, we propose a unified framework for training algorithms across different stages of modern large language model development, based on the perspective of distribution ma…
Pessimistic Verification for Open Ended Math Questions
Yanxing Huang, Zihan Tang, Zejin Lin +2
Automatic verification is a critical component in building math-solving agents and reinforcement learning, yet it often falls short in generalizability, performance, and cost-effic…
FormaRL: Enhancing Autoformalization with no Labeled Data
Yanxing Huang, Xinling Jin, Sijie Liang +2
Autoformalization is one of the central tasks in formal verification, while its advancement remains hindered due to the data scarcity and the absence efficient methods. In this wor…
AI Mathematician: Towards Fully Automated Frontier Mathematical Research
Yuanhang Liu, Yanxing Huang, Yanqiao Wang +2
Large Reasoning Models (LRMs) have made significant progress in mathematical capabilities in recent times. However, these successes have been primarily confined to competition-leve…