Sep 18: Seeing What Matters, Learning How to Find Out: Toward Visual General Intelligence by Kohsuke Ide

​Abstract: Which visual differences should change a model's answer, and which should not? I will discuss recent work on learning relations between 3D objects and on color-dependent judgments in vision-language models. These studies examine the importance of fine-grained geometry and the effects of changing how the same text is presented. Using these concrete examples, I will connect the task-dependent use of visual information to questions in Visual General Intelligence: A White Paper about acquiring knowledge from visual experience and applying it to new tasks. I will close with a research perspective on a further challenge: when current observations are insufficient, can a system learn how to obtain useful evidence through observation and interaction, and can those ways of finding out transfer to unfamiliar situations?

​Speaker: Kohsuke Ide is a master's student in Computer Science at the University of Tsukuba and a Research Assistant at Japan's National Institute of Advanced Industrial Science and Technology (AIST). Previously, he received his B.Eng. in Applied Mechanics and Aerospace Engineering from Waseda University. His research focuses on 3D understanding, vision-language models, and self-supervised visual learning. He is a co-author of Visual General Intelligence: A White Paper and a co-organizer of the CVPR 2026 Workshop on Visual General Intelligence.

​Format: ~40-minute talk followed by open Q&A. Part of the weekly Video Model Journal Club (Fridays 7:30 PM PT).

​All sessions: https://luma.com/video-model Register on this page to receive the Zoom join link (sent automatically with your confirmation).

​Subscribe to our mailing list for weekly talk announcements: Open Google Form