We are happy to invite you for the upcoming Pre-NeurIPS Poster Session featured by ELIZA. When: Thursday, November 26th, 2025, 4-6 pmLocation: IMBIT, NEXUS Lab, Georges-Köhler-Allee 201, Univ. FreiburgRegistration: https://brainlinks-braintools.uni-freiburg.de/registration/?id=2 Please register by 24.11.2026 latest. You will have the opportunity to view the latest research works from our ELLIS Unit, Read more
Jake Robertson and Arik Reuter will give a talk on their recent work “Do-PFN: In-Context Learning for Causal Effect Estimation“. Abstract Estimation of causal effects is critical to a range of scientific disciplines. Existing methods for this task either require interventional data, knowledge about the ground truth causal graph, or Read more
Authors: Muhammad Zubair Irshad, Mauro Comi, Yen-Chen Lin, Nick Heppert, Abhinav Valada, Rares Ambrus, Zsolt Kira, Jonathan Tremblay How do we represent 3D world knowledge for spatial intelligence in next-generation robots? This is the question ELLIS-ELIZA PhD student Nick Heppert, ELLIS-ELIZA Fellow Abhinav Valada, and their co-authors tried to answer Read more
TIME: 23rd – 26th September 2025 The 47th German Conference on Pattern Recognition (GCPR 2025) will be hosted at the University of Freiburg! GCPR is the annual symposium of the German Association for Pattern Recognition (DAGM) and the leading national venue for advances in image processing, pattern recognition, and computer Read more
Date: March 13th, 2025 At BrAInWorlds, around 250 participants embarked on an interactive journey into the fascinating interplay between brain, environment, and perception. Through two immersive installations, visitors experienced firsthand how surroundings shape our internal world models in real time. In the Connected Thinking space, warm yellows, greens, and lively activities encouraged openness Read more
Authors: Jörg Franke, Michael Hefenbrock, Gregor Koehler, Frank Hutter Introduction We present in our recent preprint a novel approach to parameter regularization for deep learning: Constrained Parameter Regularization (CPR). It is an alternative to traditional weight decay. Instead of applying a constant penalty uniformly to all parameters, we enforce an Read more