02.06.2026
MCML at CVPR 2026
13 Accepted Papers (11 Main, and 2 Workshops)
IEEE/CVF Conference on Computer Vision and Pattern Recognition, Denver, CO, USA, Jun 03-07, 2026
We are happy to announce that MCML researchers have contributed a total of 13 papers to CVPR 2026: 11 Main, and 2 Workshop papers. Congrats to our researchers!
Main Track (11 papers)
S. A. Baumann • J. Wiese • T. Martorella • M. M. Kalayeh • B. Ommer
Envisioning the Future, One Step at a Time.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv URL
Envisioning the Future, One Step at a Time.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv URL
G. Eskandar • F. Shen • M. Altillawi • D. Chen • Y. Bai • L. Yang • Z. Liu
VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
F. Krause • S. A. Baumann • J. Schusterbauer • O. Grebenkova • M. Gui • V. T. Hu • B. Ommer
Guiding Token-Sparse Diffusion Models.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
Guiding Token-Sparse Diffusion Models.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
D. Kotovenko • O. Grebenkova • B. Ommer
EDGS: Eliminating Densification for Efficient Convergence of 3DGS.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
EDGS: Eliminating Densification for Efficient Convergence of 3DGS.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
S. Kang • Y. Liao • P. Wang • W. Liao • Q. Zhang • B. Busam • X. Chen • Y. Liu
VLM-Loc: Localization in Point Cloud Maps via Vision-Language Models.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv GitHub
VLM-Loc: Localization in Point Cloud Maps via Vision-Language Models.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv GitHub
N. Stracke • K. Bauer • S. A. Baumann • M. A. Bautista • J. Susskind • B. Ommer
Learning Long-term Motion Embeddings for Efficient Kinematics Generation.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv URL
Learning Long-term Motion Embeddings for Efficient Kinematics Generation.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv URL
J. Schusterbauer • M. Gui • Y. Li • P. Ma • F. Krause • B. Ommer
Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv GitHub
Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv GitHub
H. Sarkar • L. Kuang • Y. Velikova • B. Busam
Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
J. Schusterbauer • J. Wiese • N. Stracke • T. Phan • B. Ommer
Probabilistic Precipitation Nowcasting with Rectified Flow Transformers.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. URL
Probabilistic Precipitation Nowcasting with Rectified Flow Transformers.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. URL
M. Tapli • Q. Bouniot • W. Stammer • Z. Akata • E. Akbas
Rethinking Concept Bottleneck Models: From Pitfalls to Solutions.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
Rethinking Concept Bottleneck Models: From Pitfalls to Solutions.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
R. Xiao • S. Kim • Y. Xian • Z. Akata • S. Alaniz
FINER: MLLMs Hallucinate under Fine-grained Negative Queries.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. Oral Presentation. To be published. Preprint available. arXiv GitHub
FINER: MLLMs Hallucinate under Fine-grained Negative Queries.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. Oral Presentation. To be published. Preprint available. arXiv GitHub
Workshops (2 papers)
H. Andrade-Loarca • J. Hege • D. Cremers • G. Kutyniok
Neural Poisson Surface Reconstruction: Resolution-Agnostic Shape Reconstruction from Point Clouds.
3D4S @CVPR 2026 - Workshop on 3D Geometry Generation for Scientific Computing at the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. URL
Neural Poisson Surface Reconstruction: Resolution-Agnostic Shape Reconstruction from Point Clouds.
3D4S @CVPR 2026 - Workshop on 3D Geometry Generation for Scientific Computing at the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. URL
M. Tamim • W. Zheng • J. Meier • D. Cremers • K. Keutzer
GaussianDet3D: Bridging Gaussian Splatting and Sparse LiDAR Detection for Multi-View 3D Object Detection.
DriveX @CVPR 2026 - 4th Workshop on Foundation Models for V2X-based Cooperative Autonomous Driving at the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. URL URL
GaussianDet3D: Bridging Gaussian Splatting and Sparse LiDAR Detection for Multi-View 3D Object Detection.
DriveX @CVPR 2026 - 4th Workshop on Foundation Models for V2X-based Cooperative Autonomous Driving at the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. URL URL
Related
02.06.2026
Benjamin Lange: The Real Risk of AI Agents Is Manipulation Through Kindness
MCML Junior Research Group Leader Benjamin Lange examines how trust in AI agents can itself become a source of risk.
28.05.2026
Zeynep Akata: To Trust AI, We Need to Understand What Goes on Behind the Scenes
MCML PI Zeynep Akata explains that to trust AI, we must understand its inner workings, address foundation model bias, and make explainability central.
