Jiahao Xu

WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELS

Learning to Reward: A Contextual Bandit Framework for Distributional Reward Policy Optimization

DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation

Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

RaSA: Rank-Sharing Low-Rank Adaptation

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training