Kechun Xu

[05/2026] One paper UniMM accepted to T-PAMI 2026.

[03/2026] Honored to receive EAI-100 Next 20 Award.

[02/2026] Invited talk at CAA Qingfan-series Talk.

[02/2026] Invited talk on BayesVLA at Lumina Talk.

[01/2026] A2 and E2VLA accepted to ICRA 2026.

[01/2026] One paper PolyFold accepted to T-ASE 2026.

[08/2025] One paper A2 accepted to T-ASE 2025.

[05/2025] Invited talk at 3D视觉工坊.

[04/2025] Invited talk at Autonomous Robotic Technology Seminar (ARTS).

[12/2024] Invited talk at TEA Lab, Tsinghua University.

[11/2024] Honored to receive ARTS Scholarship (Top 5 in China).

[10/2024] One paper GSP accepted to T-RO 2024.

[02/2023] Two papers VLG and FMP accepted to ICRA 2023.

[02/2022] One paper EOM accepted to ICRA 2022.

[06/2021] One paper EPG accepted to RA-L 2021.

Kechun Xu

I am a final-year PhD (Sep. 2021 - ) student in Control Science and Engineering department at Zhejiang University. I belong to Robotics Lab, advised by Prof. Rong Xiong and Yue Wang. I was a visiting student at MSC Lab in UC Berkeley, advised by Prof. Masayoshi Tomizuka. I also spent time in Alibaba Cloud and ZJ Humanoid as a research intern.

I obtained my B.Eng (Sep. 2017 - Jun. 2021) in Control Science and Engineering and Mechanical and Electronic Engineering from Zhejiang University with an honor degree at Chu Kochen Honor College.

My current research interests lie in robotic manipulation, robot learning, and embodied AI. My research goal is to develop human-level intelligence in robotic manipulation, including behavior dexterity, learning efficiency, and open-world generalization.

I am now open to potential academic and industry job opportunities. Please feel free to contact me!

Email / Google Scholar / Github / Twitter / LinkedIn

Photo taken by Zizhang Li.

Recent News

[06/2026] One paper APT is released on arXiv.

Publications

	APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies Kechun Xu, Zhenjie Zhu, Anzhe Chen, Rong Xiong, Yue Wang Under Review arXiv / project / code
	Direction Matters: Learning Force Direction Enables Sim-to-Real Contact-Rich Manipulation Yifei Yang, Anzhe Chen, Zhenjie Zhu, Kechun Xu, Yunxuan Mao, Yufei Wei, Lu Chen, Rong Xiong, Yue Wang Under Review arXiv / project / video
	Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy Kechun Xu, Zhenjie Zhu, Anzhe Chen, Shuqi Zhao, Qing Huang, Yifei Yang, Haojian Lu, Rong Xiong, Masayoshi Tomizuka, Yue Wang Under Review arXiv / project / code / video
	Toward Embodiment Equivariant Vision-Language-Action Policy Anzhe Chen, Yifei Yang, Zhenjie Zhu, Kechun Xu, Zhongxiang Zhou, Rong Xiong, Yue Wang IEEE International Conference on Robotics and Automation (ICRA 2026) arXiv / code
	Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter Kechun Xu, Xunlong Xia, Kaixuan Wang, Yifei Yang, Yunxuan Mao, Bing Deng, Jieping Ye, Rong Xiong, Yue Wang IEEE Transactions on Automation Science and Engineering (T-ASE 2025) Conference on Robot Learning (CoRL 2025), GenPriors Workshop IEEE International Conference on Robotics and Automation (ICRA 2026) arXiv / ieee / project / code / video
	UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation Longzhong Lin, Xuewu Lin, Kechun Xu, Haojian Lu, Lichao Huang, Rong Xiong, Yue Wang IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI 2026) arXiv / project / code
	PolyFold: A Generalizable Framework for Language-Conditioned Bimanual Cloth Folding Haozhe Du, Kechun Xu, Rong Xiong, Yue Wang IEEE Transactions on Automation Science and Engineering (T-ASE 2026) arXiv / project
	Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions He Zhu, Quyu Kong, Kechun Xu, Xunlong Xia, Bing Deng, Jieping Ye, Rong Xiong, Yue Wang IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2025) arXiv / project / code / dataset
	Grasp, See, and Place: Efficient Unknown Object Rearrangement with Policy Structure Prior Kechun Xu, Zhongxiang Zhou, Jun Wu, Haojian Lu, Rong Xiong, Yue Wang IEEE Transactions on Robotics (T-RO 2024) IEEE International Conference on Robotics and Automation (ICRA 2025) arXiv / ieee / project / code