Signals 4 · free daily AI digest

VideoTok4D: A 4D-Aware Video Tokenizer for Compact World Representation

Paper recorded by Signals 4 on 2026-09-11 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14

Category: cs.CV · 计算机视觉 · first seen 2026-09-14

Abstract

Video tokenizers have emerged as a cornerstone of modern video modeling, underpinning progress in compression, reconstruction and generation by mapping high-dimensional visual signals into compact latent spaces. However, despite this progress, current tokenization paradigms largely remain within the 2D visual domain, treating videos as image sequences rather than observations of an underlying dyna

Read on arXiv →

#75 most recent of 237 cs.CV papers we have recorded · ↑ newer: Learning Sign Language Recognition under Label Noise: A Study of Noise · ↓ older: A Multi-Vehicle Dataset with Camera, LiDAR, and Radar Sensors and Scan
Cite this page: VideoTok4D: A 4D-Aware Video Tokenizer for Compact World Representation: the #75 most recent of 237 cs.CV papers we have recorded (as of 2026-09-11). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/videotok4d-a-4d-aware-video-tokenizer-for-compact-world-representation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions