I am a second-year CS PhD student at HKUST, supervised by Prof. Junxian He. I was a Master’s student at Shanghai Jiao Tong University, under the supervision of Prof. Hai Zhao, majoring in computer science. Before that, I received my B.S. degree in the IEEE honor class at SJTU in 2022, majoring in computer science. I also collaborated with Dr. Zhuosheng Zhang during my undergraduate years.

I’m now interning at NVIDIA in NV Research, DLER led by Dr. Pavlo Molchanov, under the supervision of Dr. Jindong Jiang. I used to work as a research intern at Microsoft Research Asia (MSRA) in the NLC group, guided by Dr. Lei Cui. I worked on several interesting research topics related to Document AI, including webpage understanding and document Image foundation models. During May 2023 to Feb 2024, I worked closely with Prof. Pengfei Liu at GAIR on various aspects of Large Language Models (LLMs), primarily focusing on the evaluation and alignment of LLMs. Before entering HKUST, I also spent some time on DeepSeek LLM Alignment Team as a research intern, conducting research on topics related to general reasoning under the supervision of Dr. Yu Wu.

Selected Publications

(* indicates equal contribution. A full list is on Google Scholar.)

Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild

Yuxuan Cao*, Junlong Li*, Hao Li, Junxian He
Preprint, 2026 | PDF | Code | Page

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

DeepSeek-AI, … Junlong Li, … (among 318 contributors)
Preprint, 2026 | PDF

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Junlong Li*, Wenshuo Zhao*, Jian Zhao*, Weihao Zeng*, Haoze Wu*, Xiaochen Wang, Rui Ge, Yuxuan Cao, Yuzhen Huang, Wei Liu, Junteng Liu, Zhaochen Su, Yiyang Guo, Fan Zhou, Lueyang Zhang, Juan Michelini, Xingyao Wang, Xiang Yue, Shuyan Zhou, Graham Neubig, Junxian He
ICLR 2026 | PDF | Code | Page | Dataset

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

DeepSeek-AI, … Junlong Li, … (among 263 contributors)
Preprint, 2025 | PDF

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Junlong Li, Daya Guo, Dejian Yang, Runxin Xu, Yu Wu, Junxian He
ICML 2025 Oral | PDF | Code | Page | HF Repo

DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning

DeepSeek-AI, … Junlong Li, … (among 195 contributors)
Nature, 2025 Cover Article | PDF

DeepSeek-V3 Technical Report

DeepSeek-AI, … Junlong Li, … (among 199 contributors)
Preprint, 2024 | PDF

Diving into Self-Evolving Training for Multimodal Reasoning

Wei Liu*, Junlong Li*, Xiwen Zhang, Fan Zhou, Yu Cheng, Junxian He
ICML 2025 | PDF | Code | Page | HF Repo

Dissecting Human and LLM Preferences

Junlong Li, Fan Zhou, Shichao Sun, Yikai Zhang, Hai Zhao, Pengfei Liu
ACL 2024 | PDF | Demo | Code | Dataset

Generative Judge for Evaluating Alignment

Junlong Li, Shichao Sun, Weizhe Yuan, Run-Ze Fan, Hai Zhao, Pengfei Liu
ICLR 2024 | PDF | Code | Page

Self-Prompting Large Language Models for Zero-Shot Open-Domain QA

Junlong Li, Jinyuan Wang, Zhuosheng Zhang, Hai Zhao
NAACL 2024 | PDF

Dialogue-adaptive language model pre-training from quality estimation

Junlong Li, Zhuosheng Zhang, Hai Zhao
Neurocomputing, 2022 | PDF | Code

DiT: Self-supervised pre-training for document image transformer

Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei
ACM Multimedia 2022 | PDF | Code

Markuplm: Pre-training of text and markup language for visually-rich document understanding

Junlong Li*, Yiheng Xu*, Lei Cui, Furu Wei
ACL 2022 | PDF | Code

Educations

2025.09 - 2028.6 (expected), Ph.D.@HKUST, Computer Science & Engineering
2022.09 - 2025.03, M.S.@SJTU, Computer Science & Engineering
2018.09 - 2022.06, B.S.@SJTU, IEEE honor class, Computer Science.

Talks

2023.10, Invited talk at CIKM 2023 Workshop on Document Intelligence and Understanding.

Service

Reviewer: ACM MM, ARR, ICLR

Awards

Hong Kong PhD Fellowship Scheme, 2025
Yang Yuanqing Education Scholarship (top 0.3%), 2024
MSRA Stars of Tomorrow (Award of Excellent Intern), 2022
National Scholarship (top 2%), 2022
SJTU Zhiyuan Honors Scholarship (top 5%), 2019-2021