UCAS · LAMP Laboratory
ARTE Group
Autonomous Representation de Temps et Espace
The ARTE Group is a research group affiliated with the LAMP Laboratory at the University of Chinese Academy of Sciences (UCAS).
About
Building representations that understand how the physical world evolves.
Rather than treating the physical world as a static collection of observations, we study how intelligent systems can form compact, structured, and predictive representations of space, time, and interaction.
Our work spans spatial intelligence, autonomous driving, world models, and multimodal representation learning, with the goal of making machine perception more grounded, coherent, and actionable.
Representative Works
Selected projects from our recent research.
Directions
Research directions that shape our current work.
Spatial Intelligence
Learning representations that reason about structure, geometry, and interaction in complex 3D worlds.
Autonomous Driving
Connecting perception, prediction, and planning with grounded multimodal understanding.
World Models
Modeling temporal dynamics and latent structure so intelligent systems can predict and simulate future states.
Representation Learning
Designing scalable self-supervised and multimodal learning strategies for real-world visual understanding.
Professor
Leading the group with a focus on grounded visual intelligence.
I am a tenure-track Assistant Professor at the University of Chinese Academy of Sciences (UCAS) and a visiting Professor at EPFL. Before joining UCAS, I received several exciting faculty offers from other renowned universities; however, I ultimately chose UCAS for a variety of reasons. Prior to this, I spent five wonderful years at EPFL, where I worked closely with Prof. Sabine Süsstrunk, Dr. Mathieu Salzmann, and many talented students at IVRL, (a place I am proud to call home).
I obtained my Ph.D. from the Australian National University (ANU) in 2020 under the supervision of Prof. Richard Hartley, Prof. Faith Porikli, Prof. Mehrtash Harandi, and Prof. Hongdong Li. After submitting my thesis, I continued working on a semantic geo-localization project in collaboration with several Ph.D. students at ANU.
During my research, I was fortunate to work with outstanding collaborators, which led to the Best Student Paper Honorable Mention at ACCV 2016, recognition as a Finalist for the Best Paper Award at CVPR 2020, and the Best Poster Award at BMVC 2025.
Prior to that, I obtained a Master’s degree from New York University in 2014 and a Bachelor’s degree from Beihang University in 2011.
Life is not always easy, but it is important to live fully in the present moment.
Recent News
Updates from our papers, people, and events.
From June 3 to June 7, 2026, Mingrui Wu attended the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026) at the Colorado Convention Center in Denver, Colo...
Congratulations to the Team on Achieving State-of-the-Art in Autonomous Driving! We are thrilled to announce that our recent joint work with Horizon Robotics, led by Yanhao Wu, ...
Prof. Tong Zhang, together with team member Zhaozhi Wang, was invited to participate in CICV 2026, the 13th Congress of Intelligent and Connected Vehicles Technology, held in Sh...
Explore More