Paper recorded by Signals 4 on 2026-09-03 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-03 on arXiv · recorded by Signals 4 on 2026-09-04
Category: cs.CV · 计算机视觉 · first seen 2026-09-04
Seeing frames in order does not mean representing time. Modern VideoLMs receive ordered video streams, yet their main supervision acts on generated text rather than video-token representations where event dynamics should first emerge. This mismatch allows models to learn temporal answers from shortcuts such as objects, scenes, and language priors, without requiring internal video representations t