Visual General Intelligence white paper authors to present at Video Model Journal Club

HirokatuKataoka · x · 2026-09-18

The Video Model Journal Club hosts Kohsuke Ide (Univ. of Tsukuba / AIST) on Sep 18, 7:30 PM PT, presenting his co-authored 'Visual General Intelligence: A White Paper' with Hirokatu Kataoka and others.

The talk asks which visual differences should change a model's answer and which shouldn't, drawing on work on learning relations between 3D objects and color-dependent judgments in vision-language models, fine-grained geometry, and how text presentation affects results. He closes with a research challenge: can a system learn to obtain useful evidence through observation and interaction when current observations are insufficient, and can those ways of finding out transfer to unfamiliar situations?

Original post →

More from Research

Research channel →