Yingyan Li (李颖彦） | Xiaomi Robotics

About Me

I am currently a Research Scientist at Xiaomi Robotics, where I work on scaling vision-language-action models for real-world robots. I received my Ph.D. from the NLPR, Institute of Automation, Chinese Academy of Sciences (CASIA), advised by Prof. Zhaoxiang Zhang and Prof. Tieniu Tan. Before that, I received my Bachelor’s degree in Computer Science from the University of Chinese Academy of Sciences (UCAS) in 2021, and interned at TuSimple, where I was advised by Naiyan Wang. Please feel free to contact me at liyingyan2021@ia.ac.cn.

Research Interests

Vision-Language-Action Models
Embodied AI and Robot Manipulation
End-to-End Autonomous Driving
World Models and 3D Perception

News

[Jul. 2026] Xiaomi-Robotics-1 technical report released — a VLA foundation model trained on 100K+ hours of real-world trajectories.
[May. 2026] One paper (DynVLA) accepted to ICML 2026.
[Jan. 2026] Two papers (DriveVLA-W0, UniVLA) accepted to ICLR 2026.
[Sep. 2025] One paper (DriveDPO) accepted to NeurIPS 2025.
[Jun. 2025] One paper accepted to ICCV 2025.
[Feb. 2025] One paper accepted to ICLR 2025.
[Apr. 2024] One paper accepted to IEEE TPAMI.
[Jul. 2022] One paper accepted to ECCV 2022.

Publications

First-Author and Core-Contributor Works
arXiv

Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

Xiaomi Robotics Team (Yingyan Li, core contributor)

arXiv preprint arXiv:2607.15330, 2026

PDF Code Project Page

ICLR

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving

Yingyan Li*, Shuyao Shang*, Weisong Liu*, Bing Zhan*, Haochen Wang*, Yuqi Wang, Yuntao Chen, Xiaoman Wang, Yasong An, Chufeng Tang, Lu Hou, Lue Fan† and Zhaoxiang Zhang†

International Conference on Learning Representations (ICLR), 2026

PDF Code

ICCV

End-to-End Driving with Online Trajectory Evaluation via BEV World Model

Yingyan Li*, Yuqi Wang*, Yang Liu, Jiawei He, Lue Fan and Zhaoxiang Zhang

International Conference on Computer Vision (ICCV), 2025

PDF Code

ICLR

Enhancing End-to-End Autonomous Driving with Latent World Model

Yingyan Li, Lue Fan, Jiawei He, Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang and Tieniu Tan

International Conference on Learning Representations (ICLR), 2025

PDF Code

TPAMI

Fully Sparse Fusion for 3D Object Detection

Yingyan Li*, Lue Fan*, Yang Liu, Zehao Huang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang and Tieniu Tan

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

PDF Code

ECCV

Densely Constrained Depth Estimator for Monocular 3D Object Detection

Yingyan Li, Yuntao Chen, Jiawei He and Zhaoxiang Zhang

European Conference on Computer Vision (ECCV), 2022

PDF Code

Collaborations
ICML

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

Shuyao Shang, Bing Zhan, Yunfei Yan, Yuqi Wang, Yingyan Li, Yasong An, Xiaoman Wang, Jierui Liu, Lu Hou, Lue Fan, Zhaoxiang Zhang and Tieniu Tan

International Conference on Machine Learning (ICML), 2026

PDF Code Project Page

ICLR

UniVLA: Unified Vision-Language-Action Model

Yuqi Wang, Xinghang Li, Wenxuan Wang, Junbo Zhang, Yingyan Li, Yuntao Chen, Xinlong Wang and Zhaoxiang Zhang

International Conference on Learning Representations (ICLR), 2026

PDF Code

arXiv

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Jinghui Lu, Jiayi Guan, Zhijian Huang, Jinlong Li, Guang Li, Lingdong Kong, Yingyan Li and 43 others (Xiaomi)

arXiv preprint arXiv:2604.18486, 2026

PDF Code

NeurIPS

DriveDPO: Policy Learning via Safety DPO for End-to-End Autonomous Driving

Shuyao Shang, Yuntao Chen, Yuqi Wang, Yingyan Li and Zhaoxiang Zhang

Conference on Neural Information Processing Systems (NeurIPS), 2025

PDF Project Page