Invited Talk -- Yiran Huang & Zeynep Akata (Technical University of Munich) -- Title: The Asymmetry of Adaptation: Reverse-Engineering Multimodal In-Context Learning

As foundation models face the pressure to rapidly adapt to dynamic global changes, In-Context Learning (ICL) offers a mechanism for adaptation without expensive parameter updates. However, the mechanisms governing how Large Language Models (LLMs) extend this capability to new, unseen modalities remain poorly understood. In this talk, I present a systematic reverse-engineering of multimodal ICL, utilizing controlled synthetic tasks to isolate the architectural and statistical drivers of adaptation.