Research homepage of Peizheng Li

Peizheng Li

PhD Researcher | Spatial Intelligence · Embodied AI · Foundation Models for Physical World

My research focuses on building autonomous systems that can perceive, model, and reliably act in the 3D physical world, spanning 3D/4D dynamics scene understanding, open world modeling, spatial intelligence and embodied systems.

I am a PhD researcher at the University of Tübingen and Mercedes-Benz AG R&D, advised by Prof. Andreas Geiger and Prof. Andreas Zell. My work bridges academic research and industrial-scale engineering, with publications at CVPR, ICCV, ECCV, and IJCAI as first or core author across four consecutive years.

Getting AI into the physical world is pretty cool I guess.

Portrait of Peizheng Li

01 · Research focus

Modeling physical worlds across space, modality, and time.

01

Spatial Intelligence

Learning structured 3D/4D representations for scenes, agents, motion, and geometry in dynamic physical environments.

02

Multimodal Foundation Model

Connecting vision, language, temporal signals, and spatial context for generalizable physical-world understanding.

03

World Model

Modeling how scenes evolve, how agents move, and how actions may change the physical world.

02 · Updates

Recent signals

All news
Feb 26, 2026 Our SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving paper is accepted by CVPR 2026. 🎉 The 1st ranking on nuScenes benchmark and 2nd best close-loop performance on Bench2Drive leaderboard!
Jun 25, 2025 Our AGO: Adaptive Grounding for Open World 3D Occupancy Prediction paper is accepted by ICCV 2025. 🎉
Jul 01, 2024 Our SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving paper is accepted by ECCV 2024. 🎉 The 1st ranking on Argoverse 2 Self-supervised scene flow leaderboard!
Apr 19, 2023 PowerBEV, our paper on camera-based end-to-end instance prediction in bird’s-eye view, has been accepted by IJCAI 2023. 🎉

03 · Publications

Publication highlights

Full list
  1. CVPR 2026
    spacedrive_arch.png
    SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving
    Infusing explicit spatial representations into vision-language models for robust autonomous driving with 3D spatial reasoning.
    Peizheng Li, Zhenghao Zhang, David Holtz, Hang Yu, Yutong Yang, Yuzhi Lai, Rui Song, Andreas Geiger, and Andreas Zell
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    arXiv PDF Supp Video Code Poster Website
  2. ICCV 2025
    ago_arch.jpg
    AGO: Adaptive Grounding for Open World 3D Occupancy Prediction
    Adaptive grounding framework that bridges 2D vision-language features to open-world 3D occupancy prediction without manual vocabulary.
    Peizheng Li, Shuxiao Ding, You Zhou, Qingwen Zhang, Onat Inak, Larissa Triess, Niklas Hanselmann, Marius Cordts, and Andreas Zell
    International Conference on Computer Vision (ICCV), 2025
    arXiv PDF Supp Code Poster Website
  3. ECCV 2024
    seflow_arch.png
    SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving
    Self-supervised scene flow estimation from point clouds, eliminating the need for expensive human annotations.
    Qingwen Zhang, Yi Yang, Peizheng Li, Olov Andersson, and Patric Jensfelt
    European Conference on Computer Vision (ECCV), 2024
    arXiv PDF Supp Code Poster
  4. IJCAI 2023
    powerbev_arch.png
    PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird’s-Eye View
    Lightweight yet powerful BEV framework for joint instance segmentation and future motion prediction.
    Peizheng Li, Shuxiao Ding, Xieyuanli Chen, Niklas Hanselmann, Marius Cordts, and Juergen Gall
    International Joint Conference on Artificial Intelligence (IJCAI), 2023
    arXiv PDF Code Poster
  5. T-ASE 2026
    fam_hri_arch.jpg
    FAM-HRI: Foundation-Model Assisted Multimodal Human-Robot Interaction Combining Gaze and Speech
    Foundation-model assisted multimodal HRI that fuses gaze and speech via LLMs for intuitive robot manipulation.
    Yuzhi Lai, Shenghai Yuan, Peizheng Li, Boya Zhang, Benjamin Kiefer, Tianchen Deng, and Andreas Zell
    IEEE Transactions on Automation Science and Engineering, 2026
    DOI arXiv PDF Code
  6. ArXiv 2025
    tqd_track_arch.jpg
    TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking
    Temporal query denoising approach for robust 3D multi-object tracking in autonomous driving scenarios.
    Shuxiao Ding, Yutong Yang, Julian Wiederer, Markus Braun, Peizheng Li, Juergen Gall, and Bin Yang
    arXiv preprint arXiv:2504.03258, 2025
    arXiv PDF

04 · Writing

Research notes

All posts
Dec 24, 2025 SpaceDrive：Infusing Spatial Awareness into VLM-based Autonomous Driving
Dec 15, 2025 In the Perspective of Manifold Hypotheses - 2
Nov 25, 2025 In the Perspective of Manifold Hypotheses - 1

05 · Contact & positions

I am open to research scientist / research engineer positions in spatial AI, robotics, autonomous driving, and embodied intelligence.