Shang Qu — accepted AI-conference papers

2025

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

Yuxin Zuo, Shang Qu, Yifei Li, Zhang-Ren Chen, Xuekai Zhu, Ermo Hua +3

ICML 2025poster

We introduce MedXpertQA, a highly challenging and comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning. MedXpertQA includes 4,460 questions spanning 17 specialties and 11 body systems. It includes two subsets, Text for text evaluation and MM for multimodal evalua…

Cited by 16 Source ↗PDF ↗Scholar ↗

2025

TTRL: Test-Time Reinforcement Learning

Yuxin Zuo, Kaiyan Zhang, Li Sheng, Shang Qu, Ganqu Cui, Xuekai Zhu +10

NeurIPS 2025poster

This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to ground-truth information. While this setting appears elusive, we…

Cited by 0 Source ↗Scholar ↗