Portrait
Jun Bai (白骏)
Assistant Researcher
BIGAI NLCo Lab
Flag Counter
About Me

I received my Ph.D. degree from the School of Computer Science and Engineering at Beihang University, China. I completed my doctoral studies under the supervision of Prof. Wenge Rong and Prof. Chuantao Yin.

My research primarily focuses on building Trustworthy AI systems. My current research themes include:

  • Investigating and Improving the Faithfulness of LLMs.
  • Exploring and Enhancing the CoT Monitorability of LRMs.
  • Understanding the Internal Workings of LLMs through Mechanistic Interpretability.
Education
  • Beihang University
    Beihang University
    Ph.D. in Computer Science
    Sep. 2020 - Nov. 2024
Employment
  • BIGAI NLCo Lab
    BIGAI NLCo Lab
    Assistant Researcher
    Dec. 2024 - present
News
2026
We released Xetrieval: Mechanistically Explaining Dense Retrieval.
May 28
Native Parallel Reasoner has been accepted by ICML 2026.
May 01
We released OneMillion-Bench.
Mar 09
2025
RouterLens, TongSearch-QR, and CogAtom are accepted by EMNLP 2025.
Aug 20
CLG has been accepted by ACL 2025.
May 15
Selected Publications (view all )
Xetrieval: Mechanistically Explaining Dense Retrieval
Xetrieval: Mechanistically Explaining Dense Retrieval

Zhixin Cai*, Jun Bai*, Yang Liu*, Jiaqi Li, Yichi Zhang, Taichuan Li, Zhuofan Chen, Zixia Jia, Zilong Zheng, Wenge Rong (* equal contribution)

Preprint 2026

[Paper] [Code] [Website]

Xetrieval: Mechanistically Explaining Dense Retrieval

Zhixin Cai*, Jun Bai*, Yang Liu*, Jiaqi Li, Yichi Zhang, Taichuan Li, Zhuofan Chen, Zixia Jia, Zilong Zheng, Wenge Rong (* equal contribution)

Preprint 2026

[Paper] [Code] [Website]

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

Tong Wu*, Yang Liu*, Jun Bai*, Zixia Jia, Shuyi Zhang, Ziyong Lin, Yanting Wang, Song-Chun Zhu, Zilong Zheng (* equal contribution)

ICML 2026

[Paper] [Website] [Code] [Model]

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

Tong Wu*, Yang Liu*, Jun Bai*, Zixia Jia, Shuyi Zhang, Ziyong Lin, Yanting Wang, Song-Chun Zhu, Zilong Zheng (* equal contribution)

ICML 2026

[Paper] [Website] [Code] [Model]

OneMillion-Bench: How Far are Language Agents from Human Experts?
OneMillion-Bench: How Far are Language Agents from Human Experts?

Qianyu Yang*, Yang Liu*, Jiaqi Li*, Jun Bai*, Hao Chen, Kaiyuan Chen, Tiliang Duan, Jiayun Dong, Xiaobo Hu, Zixia Jia, Yang Liu, Tao Peng, Yixin Ren, Ran Tian, Zaiyuan Wang, Yanglihong Xiao, Gang Yao, Lingyue Yin, Ge Zhang, Chun Zhang, Jianpeng Jiao, Zilong Zheng, Yuan Gong (* equal contribution)

Preprint 2026

[Paper] [Data] [Code]

OneMillion-Bench: How Far are Language Agents from Human Experts?

Qianyu Yang*, Yang Liu*, Jiaqi Li*, Jun Bai*, Hao Chen, Kaiyuan Chen, Tiliang Duan, Jiayun Dong, Xiaobo Hu, Zixia Jia, Yang Liu, Tao Peng, Yixin Ren, Ran Tian, Zaiyuan Wang, Yanglihong Xiao, Gang Yao, Lingyue Yin, Ge Zhang, Chun Zhang, Jianpeng Jiao, Zilong Zheng, Yuan Gong (* equal contribution)

Preprint 2026

[Paper] [Data] [Code]

Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs

Jun Bai, Minghao Tong, Yang Liu, Zixia Jia, Zilong Zheng

EMNLP 2025 Top 2%

[Paper] [Code] [Jiqizhixin]

Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs

Jun Bai, Minghao Tong, Yang Liu, Zixia Jia, Zilong Zheng

EMNLP 2025 Top 2%

[Paper] [Code] [Jiqizhixin]

Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks
Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks

Xubo Qin, Jun Bai, Jiaqi Li, Zixia Jia, Zilong Zheng

EMNLP 2025

[Paper] [Code]

Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks

Xubo Qin, Jun Bai, Jiaqi Li, Zixia Jia, Zilong Zheng

EMNLP 2025

[Paper] [Code]

Leveraging Estimated Transferability over Human Intuition for Model Selection in Text Ranking
Leveraging Estimated Transferability over Human Intuition for Model Selection in Text Ranking

Jun Bai, Zhuofan Chen, Zhenzi Li, Hanhua Hong, Jianfei Zhang, Chen Li, Chenghua Lin, Wenge Rong

EMNLP 2024

[Paper] [Code]

Leveraging Estimated Transferability over Human Intuition for Model Selection in Text Ranking

Jun Bai, Zhuofan Chen, Zhenzi Li, Hanhua Hong, Jianfei Zhang, Chen Li, Chenghua Lin, Wenge Rong

EMNLP 2024

[Paper] [Code]

How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey
How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey

Jun Bai, Xiaofeng Zhang, Chen Li, Hanhua Hong, Xi Xu, Chenghua Lin, Wenge Rong

EMNLP Findings 2023

[Paper] [Code]

How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey

Jun Bai, Xiaofeng Zhang, Chen Li, Hanhua Hong, Xi Xu, Chenghua Lin, Wenge Rong

EMNLP Findings 2023

[Paper] [Code]

All publications