Hi, I'm Zhenxuan Fan (่ŒƒๆŒฏ็’‡) ๐Ÿป

ไฝ ๅฅฝ! / Hello! / ์•ˆ๋…•ํ•˜์„ธ์š”! / ใ“ใ‚“ใซใกใฏ! / ะ—ะดั€ะฐะฒัั‚ะฒัƒะน! / Bonjour! / Guten Tag! / Hola! / Ciao! / ุงู„ุณู„ุงู… ุนู„ูŠูƒู…!

I am a second-year masterโ€™s student in the School of Software Technology, Zhejiang University, under the supervision of Professor Wenqiao Zhang, and previously under the supervision of the late Professor Beng Chin Ooi (Foreign Member of the Chinese Academy of Sciences and Academia Europaea; Fellow of the ACM, the IEEE, the Singapore National Academy of Science, the Singapore Academy of Engineering, and the China Computer Federation).

Prior to this, I received my bachelorโ€™s degree from the Software Colleage, Northeastern University (China).

I am currently conducting research in Embodied AI, especially on VLA models. In the past, I focused on the efficient training and inference of LLMs and MLLMs, including model quantization, parameter-efficient fine-tuning and CoT compression.

๐Ÿ‘‹๐Ÿ‘‹๐Ÿ‘‹ If youโ€™re interested in my work, please feel free to reach out for discussions or collaborations!

Contact me via:
๐Ÿ“ง Mail: zxfan[AT]zju.edu.cn / fzx0228[AT]gmail.com

๐ŸŒˆ What's new:

  • [10/2026] ๐Ÿš— Internship: I joined Li Auto Robotics as a Research Intern, working on Embodied Brain and VLA Models! ๐Ÿค–
  • [10/2026] ๐Ÿ† Award: I received the National Scholarship for Graduate Students!
  • [10/2026] ๐Ÿค– Technical Report: IronMind has been released! I contributed to this work during my internship at XPENG Robotics.
  • [09/2026] ๐Ÿ† Award: I ranked 1st in my class in the comprehensive evaluation for my first year of master's studies and received the โ€œFive-Goodโ€ Graduate Student Award!
  • [09/2026] ๐Ÿ“œ Preprint: We released EmbodiedSkills.
  • [08/2026] ๐ŸŽ‰ EMNLP'26: RoboSPA has been accepted to EMNLP 2026 Oral! ๐ŸŽ‰๐ŸŽ‰๐ŸŽ‰
  • [06/2026] ๐Ÿš— Internship: I joined XPENG Robotics as a Research Intern, working on Pre-Training of VLA Foundation Models! ๐Ÿค–
  • [05/2026] ๐ŸŽ‰ CVPR'26: We won the championship at the CVPR 2026 ManipArena Challenge, and AgentVLA has been accepted to the CVPR 2026 EAI Workshop! ๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ
  • [04/2026] ๐ŸŽ‰ ACL'26: CoMoL has been accepted to ACL 2026 Findings! ๐ŸŽ‰
  • [02/2026] ๐Ÿ“œ Preprint: We released Draft-Thinking.
  • [01/2026] ๐Ÿ“œ Preprint: We released CtrlCoT.
  • [01/2026] ๐ŸŽ‰ ICLR'26: OmniCT has been accepted to ICLR 2026! ๐ŸŽ‰
  • [01/2026] ๐ŸŽ‰ ICASSP'26: FAQ has been accepted to ICASSP 2026! ๐ŸŽ‰
  • [11/2025] ๐ŸŽ‰ AAAI'26: MAU-GPT has been accepted to AAAI 2026! ๐ŸŽ‰
  • [09/2025] ๐ŸŽ“ Starting Masterโ€™s@ZJU: I will join Academician Beng Chin Ooi's group at SST, ZJU in 2025 Fall!
  • [06/2025] ๐ŸŽ“ Graduation@NEU: Received my Bachelor's degree from Northeastern University as an Outstanding Graduate.

๐ŸŽ“ Selected Publications (Google Scholar)

IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric Pretraining
Huimin Pan, Yufan Ren, Kunpeng Song, Siyang Wang, Xiwen Zhang, Xiaoyun Hu, Zhuoxu Duan, Hanrui Zheng, Jialeng Ni, Nathan Zhao, Sibo Ma, Zhenxuan Fan, Zhongyang Che, Danny Bao, Jiacheng Wei, Jerry Bai, Xiaoyu Yue, Xiaoyang Guo, Chenyi Chen
arXiv Preprint, 2026.
[PDF] [arXiv] [bibtex]
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
Zhenxuan Fan, Bo Zhang, Yutong Lin, Yuqian Yuan, Juekai Lin, Liang Liang, Zhuoyi Huang, Wenqiao Zhang, Juncheng Li, Siliang Tang, Jun Xiao, Yueting Zhuang
EMNLP 2026 Main Conference.
[PDF] [arXiv] [bibtex]
EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent.
Wei Wang, Wenqiao Zhang, Yutong Lin, Yuqian Yuan, Tianwei Lin, Jinhao Mao, Zhenxuan Fan, Mingjian Gao, Yang Dai, Wentong Li, Zheqi Lv, Zheng Dong, Yingjie Niu, Jiaqi Zhu, Jun Xiao, Chao Li, Yueting Zhuang
arXiv preprint, 2026.
[PDF] [arXiv] [bibtex]
Agentic Decomposition for Reasoning-Oriented Real-World Robot Manipulation.
Yutong Lin, Zhenxuan Fan, Yuqian Yuan, Wentong Li, Wenqiao Zhang, Changxu Cheng, Tao Wang, Juncheng Li, Jun Xiao, Siliang Tang, Yueting Zhuang
CVPR 2026 Embodied AI Workshop.
[PDF] [bibtex]
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging.
Jie Cao*, Zhenxuan Fan*, Zhuonan Wang, Tianwei Lin, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao, Siliang Tang
arXiv preprint, 2026.
[PDF] [arXiv] [bibtex]
Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs.
Jie Cao*, Tianwei Lin*, Zhenxuan Fan, Bo Yuan, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Siliang Tang
arXiv preprint, 2026.
[PDF] [arXiv] [bibtex]
CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning.
Zhenxuan Fan, Jie Cao, Yang Dai, Zheqi Lv, Wenqiao Zhang, Zhongle Xie, Peng Lu, Beng Chin Ooi
arXiv preprint, 2026.
[PDF] [arXiv] [bibtex]
OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis.
Tianwei Lin*, Zhongwei Qiu*, Wenqiao Zhang, Jiang Liu, Yihan Xie, Mingjian Gao, Zhenxuan Fan, Zhaocheng Li, Sijing Li, Zhongle Xie, Peng Lu, Yueting Zhuang, Ling Zhang, Beng Chin Ooi, Yingda Xia
The Fourteenth International Conference on Learning Representations, 2026.
[OpenReview] [PDF] [arXiv] [bibtex]
Enhancing Post-Training Quantization via Future Activation Awareness.
Zheqi Lv*, Zhenxuan Fan*, Qi Tian, Wenqiao Zhang, Yueting Zhuang
arXiv preprint, 2026.
[PDF] [arXiv] [bibtex]
MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation.
Zhuonan Wang*, Zhenxuan Fan*, Siwen Tan*, Yu Zhong, Yuqian Yuan, Haoyuan Li, Hao Jiang, Wenqiao Zhang, Feifei Shao, Hongwei Wang, others
Proceedings of the AAAI Conference on Artificial Intelligence, 2026.
[PDF] [arXiv] [bibtex]

๐Ÿง‘โ€๐Ÿ’ป Research Intern

Li Auto Robotics

Embodied Intelligence Algorithm Intern

Li Auto Robotics ยท Hangzhou ยท Oct. 2026 โ€“ Present

Topic: Embodied Brain and VLA models.

XPENG Robotics

VLA Foundation Model Intern

XPENG Robotics ยท Shenzhen ยท Jun. 2026 โ€“ Sep. 2026

Topic: Pre-training and mid-training of VLA foundation models.

๐Ÿ† Honors and Awards


Site Analytics