About Me

Hi, I am Xingcheng Zhou. I joined the Chair of Robotics, Artificial Intelligence and Real time Systems at Technical University of Munich in 2023 as a Research Associate, working under the supervision of Prof. Dr. Ing. habil. Alois Christian Knoll.

My research interests include Vision Language Models, 3D Environment Perception, Scene Understanding, World Models and related areas.

I completed my M.Sc. in Electrical and Computer Engineering at the Technical University of Munich in 2021. Before joining TUM, I worked as an Industrial AI Researcher at Siemens.

Xingcheng Zhou

News

May 2025One paper accepted by ICML 2025 in Vancouver, Canada!
Jul 2024One paper accepted by IEEE-ITSC 2024 in Edmonton, Canada!
May 2024One paper accepted by T-IV. One paper accepted by CVPR 2024!
May 2023I start my PhD at TUM Chair of Robotics, Artificial Intelligence and Real time Systems!
Jun 2021Completed my M.Sc. thesis "Real-Time LiDAR-Based 3D Object Detection on the Highway" at TUM!

Selected Publications

TUMTraffic VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
TUMTraffic VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
Xingcheng Zhou, Konstantinos Larintzakis, Hao Guo, Walter Zimmer, Mingyu Liu, Hu Cao, Jiajie Zhang, Venkatnarayanan Lakshminarasimhan, Leah Strand, Alois C Knoll
ICML Poster, 2025
ProjectOpenReview
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
Xingcheng Zhou, Xuyuan Han, Feng Yang, Yunpu Ma, Alois C Knoll
arXiv, 2025
PaperCodeProject
Vision Language Models in Autonomous Driving: A Survey and Outlook
Vision Language Models in Autonomous Driving: A Survey and Outlook
Xingcheng Zhou, Mingyu Liu, Ekim Yurtsever, Bare Luka Zagar, Walter Zimmer, Hu Cao, Alois C Knoll
T-IV, 2024
PaperGithub
WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection
WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection
Xingcheng Zhou*, Deyu Fu*, Walter Zimmer, Hao Guo, Hu Cao, Alois C Knoll
ITSC, 2024
PaperProject

National Projects

AutoTech.agil
AutoTech.agil
Time: May 2023 to Oct 2025
Funder: German Federal Ministry of Education and Research BMBF

Extend a real time traffic digital twin for connected intelligent infrastructure.

WebsiteTUM Page
Providentia++
Providentia++
Time: Oct 2020 to Jun 2021
Funder: Federal Ministry of Transport and Intelligent Infrastructure BMVI

Design and implement real time 3D object detection for roadside LiDAR on highways.

WebsiteLive stream

Academic Service

Workshops

DriveX Workshop
Organizer • CVPR and ICCV • 2025

Foundation Models for V2X based cooperative autonomous driving

Website
DDIVA Workshop
Organizer • IEEE Intelligent Vehicles Symposium • 2024

Data Driven Intelligent Vehicle Applications

Website

Reviewer

CVPRICCVAAAIITSCIVIROSICRARA-LTRBT-IVT-ITS