Methods › Computer Vision › Multi-Modal Methods › Vokenization

Vokenization

3 papers tagged archive 2025-07-28

Introduced by Hao Tan et al. in Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Vokenization is an approach for extrapolating multimodal alignments to language-only data by contextually mapping language tokens to their related images ("vokens") by retrieval. Instead of directly supervising the language model with visually grounded language datasets (e.g., MS COCO) these relative small datasets are used to train the vokenization processor (i.e. the vokenizer). Vokens are generated for large language corpora (e.g., English Wikipedia), and the visually-supervised language model takes the input supervision from these large datasets, thus bridging the gap between different data sources.

Paper Source

Papers archive 2025-07-28

3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling
21 Mar 2024 · 2 repositories · arXiv:2403.14551
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
6 Jul 2021 · 1 repository · arXiv:2107.02681
Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision
14 Oct 2020 · 1 repository · arXiv:2010.06775

Syntology ran 0 of 7 samples · 7 unverified

Tasks archive 2025-07-28

13 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Language Modeling	3
Language Modelling	3
Visual Grounding	2
Grounded language learning	1
Image Captioning	1
Image Retrieval	1
Knowledge Distillation	1
Language Acquisition	1
Retrieval	1
Sentence	1
Transfer Learning	1
Video Grounding	1
World Knowledge	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (3 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Multi-Modal Methods

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections