Preprint
Sep 2026
The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
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,...
Yu-Meng Shi, Quanyu Long, Yin Wu et al.
· 0 citations