Depu Meng is a Senior Research Engineer and Technical Lead at Applied Intuition, where he leads world foundation model development for physical AI. His work focuses on omni-modal foundation model training, 3D reconstruction and generation, and multimodal learning.

Previously, he was a Postdoctoral Research Fellow at the University of Michigan. He earned his Ph.D. through a joint program between Microsoft Research Asia and the University of Science and Technology of China. Download his CV.

Work Experience

• Sep. 2025 - present
  Senior Research Engineer, Technical Lead
  AI Research, Applied Intuition
  Lead world foundation model development for physical AI, including omni-modal foundation model training and methods for 3D reconstruction and generation.
• Dec. 2024 - Aug. 2025
  Machine Learning Engineer
  AI Research, DiDi Autonomous Driving
  Developed end-to-end autonomous driving models and 3D reconstruction systems.
• Aug. 2023 - Dec. 2024
  Postdoctoral Research Fellow
  Mobility Transformation Lab, University of Michigan
  Conducted traffic safety research and developed a full perception suite spanning object detection, multi-object tracking, sensor fusion, and near-miss and collision identification. Mentor: Prof. Henry X. Liu
• Apr. 2022 - Jul. 2023
  Visiting Scholar
  Mobility Transformation Lab, University of Michigan
  Worked on traffic safety research and roadside perception for connected and automated vehicles. Mentor: Prof. Henry X. Liu
• Aug. 2021 - Apr. 2022
  Research Intern
  Autonomous Delivery Group, Meituan
  Developed joint perception and motion prediction models for autonomous driving. Mentor: Dr. Changqiang Yu
• Jul. 2019 - Jul. 2021, Jul. 2017 - Jul. 2018
  Research Intern
  Visual Computing Group, Microsoft Research Asia
  Researched object detection, Transformer architectures, and self-supervised representation learning. Mentor: Dr. Jingdong Wang

Education

• Sept. 2018 - Jun. 2023
  Ph.D.
  Control Science and Engineering
  Joint Ph.D. Program, Microsoft Research Asia - University of Science and Technology of China
  Supervisor: Dr. Baining Guo and Prof. Houqiang Li
• Sept. 2014 - Jun. 2018
  B.E.
  School of the Gifted Young, major in Electrical Engineering
  University of Science and Technology of China

Selected Publications

* Equal contribution, † Project lead

	Tianshuo Xu, Yichen Xie, Depu Meng†, Chensheng Peng, Quentin Herau, Bo Jiang, Yihan Hu, Wei Zhan Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution arXiv, 2026 [Paper] [Project] [Code] [Model] [Dataset]
	Bo Jiang, Depu Meng, Yihan Hu, Yichen Xie, Tianshuo Xu, Wei Zhan LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation arXiv, 2026 [Paper] [Project] [Code]
	Quentin Herau*, Tianshuo Xu*, Depu Meng†, Zhijie Yang, Chensheng Peng, Spencer Sherk, Yihan Hu, Wei Zhan SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes arXiv, 2026 [Paper]
	Yichen Xie, Depu Meng, Chensheng Peng, Yihan Hu, Quentin Herau, Masayoshi Tomizuka, Wei Zhan URoPE: Universal Relative Position Embedding across Geometric Spaces ECCV, 2026 (Spotlight) [Paper] [Project] [Code]
	Rusheng Zhang*, Depu Meng*, Shengyin Shen, Zhengxia Zou, Houqiang Li, Henry X. Liu MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehicles Tech Report [Paper] [Code]
	Rusheng Zhang, Depu Meng, Lance Bassett, Shengyin Shen, Zhengxia Zou, Henry X. Liu Robust Roadside Perception: an Automated Data Synthesis Pipeline Minimizing Human Annotation IEEE Transactions on Intelligent Vehicles (T-IV) & U.S. Patent, 2024 [Paper]
	Depu Meng, Owen Sayer, Rusheng Zhang, Shengyin Shen, Houqiang Li, Henry X. Liu ROCO: A Roundabout Traffic Conflict Dataset Transportation Research Board Annual Meeting (TRBAM), 2023 [Paper] [Data]
	Depu Meng, Changqian Yu, Jiajun Deng, Deheng Qian, Houqiang Li, Dongchun Ren Hybrid Motion Representation Learning for Prediction from Raw Sensor Data IEEE Transactions on Multimedia (T-MM), 2023 [Paper]
	Depu Meng*, Xiaokang Chen*, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun and Jingdong Wang (*: Equal Contribution) Conditional DETR for Fast Training Convergence International Conference on Computer Vision (ICCV), 2021 [Paper] [Code] [Model]

Services

• Conference Reviewer: CVPR, ECCV, ICCV, NeurIPS, ACM MM, IROS
• Journal Reviewer: IJCV, IEEE T-IV, IEEE T-MM, IEEE T-CSVT, Neurocomputing, Pattern Recognition