collaborators

5 papers

cs.LG2026

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Zijian Zhang, Rizhen Hu, Athanasios Glentis +4

Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across tra…

cs.LG2026

REVES: REvision and VErification--Augmented Training for Test-Time Scaling

Yuanxin Liu, Ruida Zhou, Xinyan Zhao +6

Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Language Model (LLM) reasoning. However, standard post-training methods primarily o…

cs.CL2026

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

Jiazheng Li, Hongzhou Lin, Hong Lu +5

Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize…

cs.LG2025

Task Generalization With AutoRegressive Compositional Structure: Can Learning From Tasks Generalize to Tasks?

Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen +3

Large language models (LLMs) exhibit remarkable task generalization, solving tasks they were never explicitly trained on with only a few demonstrations. This raises a fundamental q…

cs.LG2025

From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency

Kaiyue Wen, Huaqing Zhang, Hongzhou Lin +1

Chain-of-thought (CoT) significantly enhances the reasoning performance of large language models (LLM). While current theoretical studies often attribute this improvement to increa…