ELLIS Pre-ICML Fest 2025: We celebrate Freiburg`s AI Science
The ELLIS Unit Freiburg hosted the event in collaboration with ELIZA and the Collaborative Research Center “Small Data” at the NEXUS Lab of IMBIT. More than 15 scientific posters were presented, and over 70 participants from academia and industry attended the session.
The event was marked by lively discussions, the exchange of ideas, and the exploration of new opportunities for collaboration. In addition, the Pre-ICML Fest provided a valuable platform to strengthen ties with local industry partners and to further raise the visibility of the ELLIS community in Freiburg.
Posters presented:
M Bühler, L Purucker; Towards Synthetic Data for Fine-tuning Tabular Foundation Models; ICML 2025
BrainLinks-BrainTools warmly welcomes a new member: Joana Pereira. She is a postdoctoral researcher at the Stereotactic and Functional Neurosurgery Department at the University of Freiburg – Medical Center and a guest researcher at the Donders Institute for Brain, Cognition, and Behaviour in the Radboud University (Neurotechnology Lab). Currently she is establishing her own group at IMBIT.
N Gosala, K Petek, B Ravi Kiran, S Yogamani, PLJ Drews-Jr, W Burgard, A Valada; LetsMap: Unsupervised Representation Learning for Semantic BEV Mapping; ECCV 2025; doi.org/10.1007/978-3-031-73636-0_7
SMB Azad, Z Padar, G Kalweit, J Boedecker; SR-Reward: Taking the path more traveled; TMLR 2025
M Abdelsamad, M Ulrich, C Gläser, A Valada; Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds; CVPR 2025; doi.org/10.48550/arXiv.2502.20316
H Zhu, S Yan, J Hoffmann, J Boedecker; Multi-convex programming for discrete latent factor models prototyping, 2024; dx.doi.org/10.48550/arXiv.2504.01431
M Naouar, H Raum, J Rahnfeld, Y Vogt, J Boedecker, G Kalweit, M Kalweit; Salvage: Shapley-distribution Approximation Learning Via Attribution Guided Exploration for Explainable Image Classification; ICLR 2025
L Sommer, O Dünkel, C Theobalt, A Kortylewski; Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space; CVPR 2025
M Mráz, B Das, A Gupta, L Purucker, F Hutter; Towards Benchmarking Foundation Models for Tabular Data With Text; ICML 2025
S Schrodi, DT Hoffmann, M Argus, V Fischer, T Brox; Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models; ICLR 2025
E Kempf, S Schrodi, M Argus, T Brox; When and How Does CLIP Enable Domain and Compositional Generalization?; ICML 2025
J Küken, L Purucker, F Hutter; Early Stopping Tabular In-Context Learning; ICML 2025
D Cattaneo, A Valada; CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration; IEEE Transactions on Robotics + IROS; doi.org/10.1109/TRO.2025.3546784
Akshay L Chandra, Iman Nematollahi, Chenguang Huang, Tim Welschehold, Wolfram Burgard, Abhinav Valada; DiWA: Diffusion Policy Adaptation with World Models; CoRL 2025
E Chisari, N Heppert, M Argus, T Welschehold, T Brox, A Valada; Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching; CoRL 2024
R Mohan, D Cattaneo, F Drews, A Valada; Progressive Multi-Modal Fusion for Robust 3D Object Detection; CoRL 2024
A Garg, M Ali, N Hollmann, L Purucker, S Müller, F Hutter; Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data; ICML 2025; openreview.net/forum
