FlowBench2 min read
FlowBench: Counterfactual Imagination Training for Spatial Intelligence
Humans imagine scene changes under hypothetical motions, an ability central to spatial reasoning and robotic planning. However, this capability remains underexplored in vision-language models and world models.
By Yifan Liu, Baihan Zhang, Khai Loong Aw, Klemen Kotar, Daniel L. K. YaminsarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 4, 2026.
Comments
Sign in to join the discussion.