Paper

Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting

arXiv:2606.06158v1 Announce Type: new Abstract: Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous-regime approaches achieve this via iterative binarised searches or trained neural regressors, while discrete methods often require a full-rate decoder pass to estimate information content. We demonstrate that such computational overheads are not strictly necessary. We show that the latent space of a frozen continuous video tokeniser inherently encodes temporal redundancy that can be exploited directl…

Authors:

Related discussions