1 result found Sort:

sdc17
CrossGET sdc17
0
26
unknown
6
[ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers.
framework transformer token-ensemble token-matching image-captioning visual-reasoning model-acceleration multimodal-learning image-text-retrieval text-image-retrieval efficient-deep-learning visual-question-answering vision-language-transformer
Created 2023-05-27
11 commits to main branch, last one about a year ago