Junxing Hu (胡俊星)

AI Researcher

Ph.D. in Computer Science, CASIA, UCAS
Ex-Senior Applied Scientist, JD.com (Tech Genius Team)
Email: junxinghu@gmail.com

     

Biography

I was a Senior Applied Scientist at JD.COM, selected as a member of the Tech Genius Team (TGT). My recent work focuses on Large Language Models and AI Agents, specifically in LLM post-training and multi-agent systems.

I obtained my Ph.D. degree in Computer Science from the Institute of Automation, Chinese Academy of Sciences (CASIA) and University of Chinese Academy of Sciences (UCAS) in June 2024, advised by Prof. Zhenan Sun on 3D vision and biometrics. Prior to that, I earned my M.S. degree in Computer Science from the Institute of Software, CAS (ISCAS) in 2020, and my B.E. in Software Engineering & B.A. in Japanese dual degree from Dalian University of Technology (DLUT).

Up to now, I have published and submitted more than 20 papers, including 10 first-authored, across Top-tier Conferences, JCR-Q1 journals, and the Best Student Paper Award. The multi-agent framework (OxyGent) I contributed to has garnered over 2,000 GitHub stars. The open-source computer vision benchmarks (CASIA-Iris-Degradation and CASIA-Iris-Africa) I constructed have been downloaded over 1,000 times.

Work Experience

Selected Publications

OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
Junxing Hu, Tianlong Li, Lei Yu, Ai Han
The 64th Annual Meeting of the Association for Computational Linguistics (ACL System Demonstrations), 2026

[paper] [website] [code] [poster]

HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants
Junxing Hu, Ai Han, Haolan Zhan, Pu Wei, Zhiqian Zhang, Yuhang Guo, Jiawei Lu, Zhen Chen, Haoran Li, Zicheng Zhang.
arXiv preprint arXiv:2506.19846, 2025

[paper]

Learning Explicit Contact for Implicit Reconstruction of Hand-held Objects from Monocular Images
Junxing Hu, Hongwen Zhang, Zerui Chen, Mengcheng Li, Yunlong Wang, Yebin Liu, Zhenan Sun
AAAI Conference on Artificial Intelligence (AAAI), 2024

[paper] [project] [code] [poster]

Personalized Graph Generation for Monocular 3D Human Pose and Shape Estimation
Junxing Hu, Hongwen Zhang, Yunlong Wang, Min Ren, Zhenan Sun
IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2023

[paper]

Seg-Edge Bilateral Constraint Network for Iris Segmentation
Junxing Hu, Hui Zhang, Jing Liu, Lihu Xiao, Xingguang Li, Zhaofeng He
International Conference on Biometrics (ICB), 2019, Best Student Paper

[paper]

Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
Hao Zhou, Tiru Wu, Yan Jiang, Wanqi Zhou, Junxing Hu, Ai Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

[paper]

The Primacy of Magnitude in Low-Rank Adaptation
Zicheng Zhang, Haoran Li, Yifeng Zhang, Guoqiang Gong, Jiaxing Wang, Junxing Hu, Pengzhang Liu, Qixia Jiang
Neural Information Processing Systems (NeurIPS),2025, Spotlight

[paper]

Academic Services

Selected Awards

Last updated: July 2026.