5,523,126 AI resources indexedWorking toward the world’s largest AI resource index.

PDF

Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters

Research paper by Weizhi Wang and collaborators. Published 2024-03-05. Topics: Multimodal Language Models, MLM, CLIPScore, CLIP, BLIP2.

Resource information

Authors
Weizhi Wang, Khalil Mrini, Linjie Yang, Sateesh Kumar, Yu Tian, Xifeng Yan, Heng Wang
Research topics
Multimodal Language Models, MLM, CLIPScore, CLIP, BLIP2
Publication date
2024-03-05
Publication
arXiv
Last record update
Nov 3, 2026