Yichen Xie

Yichen Xie (谢熠辰)

Hi, there! I am a fifth-year Ph.D. (Sep. 2021 - ) at UC Berkeley under the supervision of under the supervision of Prof. Masayoshi Tomizuka in the Mechanical Systems Control (MSC) Lab, which is affiliated with the Berkeley Artificial Intelligence Research (BAIR). During my graduate study, I am fortunate to have the opportunity as an intern at Apple, Waymo, Applied Intuition and Cruise .

Prior to this, I obtained my B.Eng (Sep. 2017 - Jun. 2021) in Computer Science and Engineering from Shanghai Jiao Tong University with an honor degree at Zhiyuan Honors Program, where I was advised by Prof. Cewu Lu and Prof. Quanshi Zhang.

My primary research interests focus on multimodal foundation models and 3D computer vision, especially their intersection and their applications to embodied agents.

I am open to collaboration!
I am seeking for reseacher opportunities in industry in 2026!
Please feel free to contact me if interested!

Email / Google Scholar / Github / LinkedIn

[email protected]

Recent News

[10/2025] One paper (UNICST) received Outstanding Paper, RIWM Workshop@ICCV 2025. A significantly improved version is under review now.

[07/2025] One paper, extension of ActiveFT (CVPR 2023), accepted by T-PAMI.

[06/2025] One paper (Plug-and-Forecast) accepted by IROS 2025.

[05/2025] Starting Machine Learning Intern position at Apple.

[02/2025] Two papers (S4-Driver and DeSiRe-GS) accepted by CVPR 2025.

[01/2025] Two papers (X-Drive and LORT) accepted by ICLR 2025.

Selected Publications (see full list)

	RAYNOVA: Geometry-Free Auto-Regressive 4D World Modeling with Unified Spatio-Temporal Representation Yichen Xie, Chensheng Peng, Mazen Abdelfattah, Yihan Hu, Jiezhi Yang, Eric Higgins, Ryan Brigden, Masayoshi Tomizuka, Wei Zhan Outstanding Paper, RIWM Workshop@ICCV 2025 (UNICST) Under Review (new version) Coming Soon
	S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual Representation Yichen Xie, Runsheng Xu, Tong He, Jyh-Jing Hwang, Katie Luo, Jingwei Ji, Hubert Lin, Letian Chen, Yiren Lu, Zhaoqi Leng, Dragomir Anguelov, Mingxing Tan CVPR 2025 arXiv / project
	X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios Yichen Xie, Chenfeng Xu, Chensheng Peng, Shuqi Zhao, Nhat Ho, Alexander T. Pham, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan ICLR 2025 arXiv / code
	Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving Yichen Xie, Hongge Chen, Gregory P. Meyer, Yong Jae Lee, Eric M. Wolff, Masayoshi Tomizuka, Wei Zhan, Yuning Chai, Xin Huang ICRA 2025 arXiv
	Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning Yixiao Wang, Yifei Zhang, Mingxiao Huo, Ran Tian, Xiang Zhang, Yichen Xie, Chenfeng Xu, Pengliang Ji, Wei Zhan, Mingyu Ding, Masayoshi Tomizuka CoRL 2024 arXiv / code / project
	AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains Hao-Shu Fang, Chenxi Wang, Hongjie Fang, Minghao Gou, Jirong Liu, Hengxu Yan, Wenhai Liu, Yichen Xie, Cewu Lu T-RO 2023 arXiv / code / project
	SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection Yichen Xie, Chenfeng Xu, Marie-Julie Rakotosaona, Patrick Rim, Federico Tombari, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan ICCV 2023 arXiv / code
	Towards Free Data Selection with General-Purpose Models Yichen Xie, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan NeurIPS 2023 arXiv / code
	Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm Yichen Xie, Han Lu, Junchi Yan, Xiaokang Yang, Masayoshi Tomizuka, Wei Zhan CVPR 2023, T-PAMI 2025 arXiv / code
	Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang, Yanjiang Guo, Jianyu Chen, Stefan Schaal, Masayoshi Tomizuka ICRA 2023 arXiv
	Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds Siyuan Huang, Yichen Xie, Song-Chun Zhu, Yixin Zhu ICCV 2021 arXiv / code / project
	DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection Hao-Shu Fang, Yichen Xie, Dian Shao, Cewu Lu AAAI 2021 arXiv / code
	Interpreting Multivariate Shapley Interactions in DNNs Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, Quanshi Zhang AAAI 2021 arXiv / code

Experiences

Machine Learning Intern @ Apple (May 2025 - Aug. 2025)

Advisor: Haofeng Chen, Shreyash Pandey

Worked on multimodal LLM agent

Research Intern @ Applied Intuition (Jan. 2025 - May 2025)

Advisor: Yihan Hu

Worked on world model

Research Science Intern @ Waymo (May 2024 - Nov. 2024)

Advisor: Tong He, Runsheng Xu

Worked on vision-language action model

AI Research Intern @ (GM) Cruise (May 2023 - Nov. 2023)

Advisor: Cyrus Huang, Hongge Chen

Worked on self-supervised representation learning

Selected Honors

Zhiyuan Outstanding Student Scholarship, 2021.

China National Scholarship, 2018, 2019, 2020.

Services

Reviewer of CVPR, ICCV, ECCV, ICLR, NeurIPS, ICML, ICRA, IROS.

Template from Jon Barron