AI RESEARCH
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
arXiv CS.CV
•
ArXi:2603.12267v1 Announce Type: new Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation computational cost. Traditional video tokenizers apply a uniform token assignment across temporal blocks of different videos, often wasting tokens on simple, static, or repetitive segments while underserving dynamic or complex ones. To address this inefficiency, we.