Metraipolis › archive › dc_5802de0b362f

Visual Token Coding for Video Multimodal Large Language Models — arXiv:2608.28008

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28008
License (as archived)
CC0-1.0
Archived
2026-10-17T11:33:07.044Z
SHA-256 of the archived text
e6169d98225e158db74ab4b28f78175b7b810802be8e001e20a4cc304fc3fde6
Stable URL of this page
https://metraipolis.com/documento/dc_5802de0b362f

How to cite

Visual Token Coding for Video Multimodal Large Language Models — arXiv:2608.28008 — arXiv (en), https://arxiv.org/abs/2608.28008 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5802de0b362f (Metraipolis archive dc_5802de0b362f, sha256 e6169d98225e158db74ab4b28f78175b7b810802be8e001e20a4cc304fc3fde6)
BibTeX
@misc{dc5802de0b362f,
  title = {Visual Token Coding for Video Multimodal Large Language Models — arXiv:2608.28008},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28008},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5802de0b362f; sha256 e6169d98225e158db74ab4b28f78175b7b810802be8e001e20a4cc304fc3fde6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28008. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we propose a new token compression paradigm for video Multimodal Large Language Models (MLLMs), termed Visual Token Coding (VTC). Inspired by classical video coding principles, e.g., HEVC, VTC performs structured compression by predicting the I/P frames of a video and measuring their frame-wise residuals to estimate token redundancy. Based on this baseline framework, we also enhance VTC with a set of novel dynamic designs, such as Dynamic Resolution Input (DyRSO), Dynamic Token Allocation (DyTA), and Spatial Coverage Top-K (SC-TopK), and term this new approach $VTC_{Dy}$. To validate VTC, we apply it to three MLLMs and conduct experiments on multiple video understanding benchmarks. The experimental results show that VTC$_{\mathrm{Dy}}$ achieves an average performance retention of 100.1% with a 50% token budget for Qwen3-VL, while still retaining 97.8% of the average performance when the token budget is reduced to 25%. Moreover, as a plug-and-play design, VTC requires no additional tuning of MLLMs for token coding. Our code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28008 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T11:10:05.290Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).