AI RESEARCH
Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs
arXiv CS.CV
•
ArXi:2605.22823v1 Announce Type: new Video Large Language Models (Video-LLMs) have made rapid progress on temporal video understanding, yet many fail at a basic perceptual primitive: signed image-plane motion direction. On simple videos of a single object moving left, right, up, or down, most Video-LLMs perform near chance, with above-chance cases largely attributable to prediction biases rather than genuine direction understanding. We call this failure directional motion blindness. We localize the failure by tracing motion direction information through the Video-LLM pipeline.