Jiaxuan Gao

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

Unlocking Long-Horizon Agentic Search with Large-Scale End-to-End RL

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn

AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reasoning Is Not a Race: When Stopping Early Beats Going Deeper

Few-shot In-context Preference Learning using Large Language Models

How Far Are We from Optimal Reasoning Efficiency?

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

On Designing Effective RL Reward at Training Time for LLM Reasoning