Past Events

September 24th, 2026 • IMBIT, NEXUS Lab, George Köhler Allee 201, 79110 Freiburg
How to Encode World Knowledge?
Foundation models are a key platform which implicitly encodes world knowledge. In this talk we first focus on vision-language models, such as CLIP, and investigate their geometric behavior and logic behind the high-dimensional feature encoding. For instance, we find that as image or text become...
Guest Lecture
July 1st, 2026 • IMBIT, NEXUS Lab, Georges Köhler Allee 201, 79110 Freiburg
Inference-Time Alignment of Diffusion-Based Trajectory Planners for Autonomous Driving
Diffusion models have emerged as a powerful class of generative trajectory planners for autonomous driving, capable of producing diverse, multimodal motion plans from large-scale demonstration data. Yet deploying such models in safety-critical settings raises a recurring challenge: how to steer...
June 29th, 2026 • IMBIT, NEXUS Lab, Georges Köhler Allee 201, 79110 Freiburg
Pre-ICML Poster Session 2026
The ELLIS Units Freiburg and Darmstadt, together with the ZUSE School ELIZA, cordially invite you and your research group to the Pre-ICML Poster Session 2026. Join researchers from our regional AI community to exchange ideas, network, and showcase recent publications at top-tier AI and machine...
Poster Session
June 24th, 2026 • Georges-Köhler-Allee 080, 79110 Freiburg
ELIZA Welcome Event and Orientation Meeting, Summer 2026
Meeting
June 19th, 2026 • Georges-Köhler-Allee 80, Robot Learning Lab, Room 00.021
Uncertainty-Driven Safe Continual Improvement of Generative Robot Policies
Generative robot policies, such as diffusion policies and vision-language-action models, have demonstrated impressive capabilities for solving complex, long-horizon tasks. However, deploying these models in our ever-changing real world, where robots must continuously adapt to novel situations...
June 11th, 2026 • Georges-Köhler-Allee 101, SR 00-017/19
Cloud-Scale Automated Reasoning at Amazon
Amazon has what is likely the largest team of automated reasoning experts ever assembled. Why? Amazon works backwards from customers, and they want the assurance that only automated reasoning can provide. This is especially critical as AI agents write production code — and become production code....
June 3rd, 2026 • IMBIT, NEXUS Lab, Georges Köhler Allee 201, 79110 Freiburg
Imagine, Verify, Act: Robot Planning with World Models and Vision-Language Evaluators
Humans and animals anticipate the consequences of their actions before acting, yet most robot policies remain reactive and limited to short horizons. In this talk, Dr. Gumbsch will sketch an approach to building embodied agents that learn to solve tasks by thinking ahead, rather than relying on...
May 26th, 2026 • IMBIT, NEXUS Lab, Georges Köhler Allee 201, 79110 Freiburg
Multimodal Distributed Perception for Networked Autonomous Systems
The potential of increasingly prevalent networked control systems, including connected automated driving systems (ADS) and networked robots, to enable fast and reconfigurable autonomy underscores the critical need for distributed sensing, perception, and planning architectures that are robust to...
May 19th, 2026 • IMBIT, NEXUS Lab, Georges Köhler Allee 201, 79110 Freiburg
Bayesian Fusion for Multimodal Human-Robot Interaction
To cope with perceptual uncertainty, humans integrate information from multiple sources, such as visual, auditory, and haptic input. A large body of evidence shows that this multimodal integration is often statistically optimal and can be explained by Bayes’ rule. In an inherently uncertain...
April 1st, 2026 • IMBIT, NEXUS LAB, Georges-Köhler-Allee 201, 79110 Freiburg
Revisiting the Platonic Representation Hypothesis: An Aristotelian View
The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure representational similarity are confounded by network scale: increasing model depth or width can...
Guest Lecture
March 24th, 2026 • Robot Learning Lab; Seminar Room, Georges-Köhler-Allee 080, 79110 Freiburg
From 2D Similarities to 3D Correspondences
Self-supervised visual representations often capture semantic part similarities, features that respond consistently to wings, legs, or wheels. However, these features encode 2D similarities rather than 3D correspondences. To reason in a 3D world, an ideal representation would provide 3D...
Guest Lecture
February 19th, 2026 • Robot Learning Lab; Seminar Room, Georges-Köhler-Allee 080, 79110 Freiburg
Accelerating 3D Solar atmosphere modelling with Graph Neural Networks
Simulating the sun's atmosphere requires solving complex non-local, non-linear systems of coupled equations. A massive computational bottleneck that typically restricts researchers to 1.5D approximations or requires millions of CPU hours for full 3D snapshots. We present a solution that bypasses...
Guest Lecture
January 19th, 2026 • Georges-Köhler-Allee 080, 79110 Freiburg
ELIZA Welcome Event and Orientation Meeting, Winter 2026
Meeting
December 12th, 2025 • IMBIT NEXUS Lab, Georges-Köhler-Allee 201, 79110 Freiburg
Agile Robotics: from Cameras to Neuromorphic Sensors
Autonomous drones play a crucial role in inspection, agriculture, logistics, and search-and-rescue missions and promise to increase productivity by a factor of 10. However, they still lag behind human pilots in speed, versatility, and robustness. What does it take to fly autonomous drones as...
Guest Lecture
November 26th, 2025 • IMBIT NEXUS Lab, Georges-Köhler-Allee 201, 79110 Freiburg
Freiburg's Pre-NeurIPS Poster Session hosted by ELIZA
We are happy to invite you to the upcoming Pre-NeurIPS Poster Session featured by ELIZA.If you would like to participate, please register under https://brainlinks-braintools.uni-freiburg.de/registration/?id=2 by 24.11.2026 latest.You will have the opportunity to view the latest research works...
Poster Session
October 13th, 2025 • IMBIT NEXUS Lab, Georges-Köhler-Allee 201, 79110 Freiburg
The Importance of Policy Representations
Learning motor skills in robotics has applications ranging from agriculture, manufacturing, to household environments and care. Imitation learning is one of the most prominent approaches in this field. Recent advances on large-scale models have enabled generalists, but are not yet suitable for...
Guest Lecture

Page 1 of 16