Skip to content

DFG Research Training Group KD2School – 2nd Funding Period approved

We are excited to announce that the DFG Research Training Group (RTG) KD²School will receive funding for another five years.  In this RTG, KIT is collaborating with the Universities of Bremen and of Oldenburg to research the design of biosignal-adaptive systems for decision-making processes in economic contexts as well as… Read More »DFG Research Training Group KD2School – 2nd Funding Period approved

Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories got accepted at AISTATS 2026

Our paper “Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories” has been accepted for publication at the 29th International Conference on Artificial Intelligence and Statistics: AISTATS 2026. It will be presented at the conference in early May in Tangier, Morocco. In the… Read More »Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories got accepted at AISTATS 2026

Excellence Cluster “Reasonable AI” is hiring PhD students (deadline 16.11.25)

The German Cluster of Excellence on “Reasonable Artificial Intelligence” (RAI) is now looking for PhD candidates to give rise to richer, more robust AI systems that inherently possess the abilities to think, learn, interact, and adapt. The cluster is structured across four labs – each… Read More »Excellence Cluster “Reasonable AI” is hiring PhD students (deadline 16.11.25)

“Aligning Generalization Between Humans and Machines” has been published at Nature Machine Intelligence

Our paper “Aligning generalization between humans and machines” is now published at Nature Machine Intelligence! This paper has been co-authored with 25 experts in AI and cognitive science and is a product of the Dagstuhl seminar on “Generalization by People and Machines” in May 2024.… Read More »“Aligning Generalization Between Humans and Machines” has been published at Nature Machine Intelligence

“Core Tokensets for Data-efficient Sequential Training of Transformers” has been accepted to the ICCV Workshop on Continual Learning in Computer Vision

Our paper “Core Tokensets for Data-efficient Sequential Training of Transformers” has been accepted for publication in the ICCV-W proceedings in context of the Workshop on Continual Learning for Computer Vision. The paper will be presented at the Workshop in October at ICCV in Hawaii. In… Read More »“Core Tokensets for Data-efficient Sequential Training of Transformers” has been accepted to the ICCV Workshop on Continual Learning in Computer Vision

We are proud to be part of the cluster of excellence “Reasonable AI” – headed by TU Darmstadt

We are very happy and proud to be part of the team within the newly funded cluster of excellence “RAI: Reasonable Artificial Intelligence”! RAI has succeeded in a prestigious and highly competitive process through the Excellence Strategy of the German federal and state governments. The… Read More »We are proud to be part of the cluster of excellence “Reasonable AI” – headed by TU Darmstadt

Our paper “BOWL: A Deceptively Simple Open World Learner” got accepted at CoLLAs 2025

Our work “BOWL: A Deceptively Simple Open World Learner” has just been accepted at the Fourth Conference on Lifelong Learning Agents (CoLLAs 2025). Congratulations to our PhD student Roshni Kamath, not only for this acceptance, but also for getting two papers accepted in sequence, following… Read More »Our paper “BOWL: A Deceptively Simple Open World Learner” got accepted at CoLLAs 2025