Three submitted papers by SciAI Center researchers were accepted at the forty-first International Conference on Machine Learning (ICML 2024) that took place in Vienna, Austria in July.

• LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law by Toni J.B. Liu, Nicolas Boullé, Raphaël Sarfati, Christopher Earls was presented at the 1st ICML Workshop on In-Context Learning
• Prototype-based Methods in Explainable AI and Emerging Opportunities in the Geosciences by Anushka Narayanan, Karianne Bergen was presented at the workshop titled “AI for Science: Scaling in AI for Scientific Discovery”
• Semantically-correlated memories in a dense associative model by Tom Burns was accepted in the main conference track. Tom could not attend to present, but his poster can be viewed in the link.

Anushka Narayanan presents her poster at ICML 2024.

Anushka Narayanan presents her paper at ICML 2024.

Toni Liu presents his poster at ICML 2024.

Lab mate Toni Liu puts up Tom Burns’s poster at ICML 2024