Jan-Nico Zaech
Dr. Jan-Nico Zaech
Email: [email protected]
About
My primary research interest is building foundation models for robotics and establishing the emerging field of quantum computer vision. I am especially interested in using large-scale simulation data to train joint vision and planning models for robotics and believe that this approach allows to efficiently scale robotic applications beyond the capabilities learned from human demonstrations.
Before joining INSAIT, I was engaged in research at the Computer Vision Lab at ETH Zurich, focusing on the fusion of quantum computing with computer vision techniques and the development of algorithms for the vision systems of autonomous robots within the TRACE project (Toyota Research on Automated Cars in Europe). During this time I also have been the scientific supervisor of the ETH RoboCup project, organized a CVPR workshop on Quantum Computer Vision and Machine Learning, and managed the institute’s investment in large-scale compute resources. Overall, I have experience in a wide range of image-processing applications, ranging from autonomous medical imaging to work on the Square Kilometre Array radio telescope.
2026
Nikolay Nikolov, Giuliano Albanese, Sombit Dey, Aleksandar Yanev, Luc Van Gool, Jan-Nico Zaech, Danda Pani Paudel
SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)
Asen Nachkov, Jan-Nico Zaech, Danda Pani Paudel, Xi Wang, Luc Van Gool
Autonomous Vehicle Path Planning by Searching With Differentiable Simulation
In: The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)
Asen Nachkov, Danda Pani Paudel, Jan-Nico Zaech, Davide Scaramuzza, Luc Van Gool
Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Models
In: The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)
2025
Anna-Maria Halacheva, Jan-Nico Zaech, Xi Wang, Danda Pani Paudel, Luc Van Gool
GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond
In: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)
Sombit Dey, Jan-Nico Zaech, Nikolay Nikolov, Luc Van Gool, Danda Pani Paudel
ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models
In: International Conference on Robotics and Automation (ICRA 2025)
Anna-Maria Halacheva, Yang Miao, Jan-Nico Zaech, Xi Wang, Luc Van Gool, Danda Pani Paudel
Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description
In: International Conference on Computer Vision (ICCV 2025)
Jiahuan Cheng, Jan-Nico Zaech, Luc Van Gool, Danda Pani Paudel
Occam’s LGS: An Efficient Approach for Language Gaussian Splatting
In: The British Machine Vision Conference (BMVC 2025)
Alexander Spiridonov, Jan-Nico Zaech, Nikolay Nikolov, Luc Van Gool, Danda Pani Paudel
Generalist Robot Manipulation beyond Action Labeled Data
In: The Conference on Robot Learning (CoRL 2025)
Yang Miao, Jan-Nico Zaech, Xi Wang, Fabien Despinoy, Danda Pani Paudel, Luc Van Gool
LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation
In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
2024
Giuliano Albanese; Arka Mitra; Jan-Nico Zaech; Yupeng Zhao; Ajad Chhatkuli; Luc Van Gool
Optimizing Long-Term Robot Tracking with Multi-Platform Sensor Fusion
In: IEEE Workshop on Applications of Computer Vision (WACV 2024)
Jan-Nico Zaech, Martin Danelljan, Tolga Birdal, Luc Van Gool
Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing
In: Computer Vision and Pattern Recognition Conference (CVPR 2024)
