Jiahao Xu

Senior Researcher, Tencent AI Lab, Tencent AI Lab

Joined

December 2021

Names

Jiahao Xu (Preferred)

Emails

****@e.ntu.edu.sg (Confirmed)

****@gmail.com (Confirmed)

****@tencent.com (Confirmed)

Personal Links

Career & Education History

Senior Researcher

Tencent AI Lab, Tencent AI Lab (tencent.com)

2024 – Present

PhD student

EEE School, Nanyang Technological University (ntu.edu.sg)

2020 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Lihui Chen

2020 – 2024

Expertise

Sentence Embeddings

Present

Machine Translation

Present

Reinforcement Learning from Human Feedback

Present

Large Language Models

Present

LLM Reasoning

Present

Publications

DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
Tian Liang, Wenxiang Jiao, Zhiwei He, Jiahao Xu, Haitao Mi, Dong Yu
- ICLR 2026 Poster
- Readers: Everyone
WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality
Chunyang Li, Yilun Zheng, Xinting Huang, Tianqing Fang, Jiahao Xu, Lihui Chen, Yangqiu Song, Han Hu
- ICLR 2026 Oral
- Readers: Everyone
Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation
Yilun Zheng, Dan Yang, Jie Li, Lin Shang, Lihui Chen, Jiahao Xu, Sitao Luan
- Submitted to ICLR 2026
- Readers: Everyone
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Ziyin Zhang, Jiahao Xu, Zhiwei He, Tian Liang, Qiuzhi Liu, Yansi Li, Linfeng Song, Zhenwen Liang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
- Submitted to ICLR 2026
- Readers: Everyone
THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELS
Zhichao Wang, Dongyang Ma, Xinting Huang, Deng Cai, Tian Lan, Jiahao Xu, Haitao Mi, Xiaoying Tang, Yan Wang
- ICLR 2026 Poster
- Readers: Everyone
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
Zhiwei He, Tian Liang, Jiahao Xu, Qiuzhi Liu, Xingyu Chen, Yue Wang, Linfeng Song, Dian Yu, Zhenwen Liang, Wenxuan Wang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
- ICLR 2026 Poster
- Readers: Everyone
Learning to Reward: A Contextual Bandit Framework for Distributional Reward Policy Optimization
Sheng Ouyang, Yulan Hu, Hao Yi, Jiahao Xu, Yong Liu
- Submitted to ICLR 2026
- Readers: Everyone
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
Ke Ji, Jiahao Xu, Tian Liang, Qiuzhi Liu, Zhiwei He, Xiaoyuan Liu, Xingyu Chen, Junying Chen, Benyou Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
- NeurIPS 2025 poster
- Readers: Everyone
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Mengru Wang, Xingyu Chen, Yue Wang, Zhiwei He, Jiahao Xu, Tian Liang, Qiuzhi Liu, Yunzhi Yao, Wenxuan Wang, Ruotian Ma, Haitao Mi, Ningyu Zhang, Zhaopeng Tu, Xiaolong Li, Dong Yu
- NeurIPS 2025 poster
- Readers: Everyone
Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
Yue Wang, Qiuzhi Liu, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Linfeng Song, Dian Yu, Juntao Li, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
- NeurIPS 2025 spotlight
- Readers: Everyone

View all 28 publications

Co-Authors

View all 70 co-authors