Paper Detail

Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation

Yeonkyeong Lee, Hyunsung Go, Jongmin Kim, Sewoong Lim, Donghoon Lee

huggingface Score 6.5

Published 2026-08-25 · First seen 2026-09-01

General AI

Abstract

Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with variational autoencoders (VAEs) to enhance computational efficiency without compromising visual quality. However, conventional VAEs are suboptimal for video data as they employ fixed compression ratios that cannot adapt to the varying complexity of spatio-temporal content. We present KATok (Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation), a transformer-based VAE that incorporates an adaptive token selector which is jointly learned with latent tokens. By evaluating each token's content-richness as keep-or-drop probability, the token selector effectively discards uninformative tokens, naturally allowing data-dependent compression. Applying adaptive tokenization to diffusion models may cause spatial misalignment, as token dropping can disturb the original spatio-temporal structure. To alleviate this issue, we propose two position-prediction strategies: cascaded and joint generation, to ensure spatial consistency. We empirically show that our model achieves strong reconstruction and generation quality at a state-of-the-art compression ratio. Further analysis on video data reveals that this improvement is primarily achieved by reducing spatio-temporal redundancy and removing uninformative tokens, as supported by both quantitative and qualitative results.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{lee2026keep,
  title = {Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation},
  author = {Yeonkyeong Lee and Hyunsung Go and Jongmin Kim and Sewoong Lim and Donghoon Lee},
  year = {2026},
  abstract = {Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with variational autoencoders (VAEs) to enhance computational efficiency without compromising visual quality. However, conventional VAEs are suboptimal for video data as they employ fixed compression ratios that cannot adapt to the varying complexity of spatio-temporal content. We present KATok (Keep-or-Drop? Adaptive Tokenizer for Compact Video Representat},
  url = {https://huggingface.co/papers/2608.24293},
  keywords = {latent diffusion models, variational autoencoders, adaptive token selector, keep-or-drop probability, position-prediction strategies, cascaded generation, joint generation, spatio-temporal redundancy, huggingface daily},
  eprint = {2608.24293},
  archiveprefix = {arXiv},
}

Metadata

{}