What we’re about
heidelberg.ai is a non-profit platform for enthusiasts, students and researchers in the field of Artificial Intelligence hosted by the German Cancer Research Center (DKFZ). We provide opportunities for technical discussions, networking and connecting with industrial partners. Our vision is to create a hub of AI expertise in the Heidelberg area.
People with all backgrounds and knowledge levels are welcome to participate.
Slides of previous talks and events are available at heidelberg.ai/posts and our github page.
Please contact us for ideas, contributions and event suggestions at heidelberg.ai@dkfz.de .
Upcoming events
1
•OnlineTest-Time Training Agents to Solve Challenging Problems
OnlineWe’re thrilled to welcome Jonas Huebotter from ETH Zurich to our heidelberg.ai & NCT Data Science Seminar on November 5th at 6 PM.
"When solving a problem of interest, do not solve a more general problem as an intermediate step. Try to get the answer that you really need but not a more general one."
-- Vladimir VapnikIn this online session, Jonas will guide us through the world of test-time training in which the model is adapted for each new input during the prediction phase. This unlocks powerful new applications by letting the model adapt and search for the most relevant information to solve the task at hand for this specific input, which is one of the most promising strategies on the ARC-AGI challenge.
Jonas Huebotter is a PhD student in the Learning and Adaptive Systems Group at ETH Zurich working with Andreas Krause. Prior to this, he obtained a Master’s degree in Theoretical Computer Science and Machine Learning from ETH Zurich and a Bachelor’s degree in Computer Science and Mathematics from the Technical University of Munich. He is a recipient of the ETH Medal.
His research aims to leverage foundation models for solving hard tasks through specialization and reinforcement learning. Furthermore, his work encompasses probabilistic inference, optimization, and online learning.
24 attendees
Past events
72
