Fartash Faghri's picture

21 2

Fartash Faghri

fartashf

·

AI & ML interests

None yet

Recent Activity

authored a paper 17 days ago

FastVLM: Efficient Vision Encoding for Vision Language Models

new activity 27 days ago

apple/MobileCLIP-S2:The inference speed of MobileCLIP-S2's image encoder is slower than OpenCLIP's ViT-B-32-256 model on both CPU and GPU

View all activity

Organizations

fartashf's activity

upvoted a paper 7 months ago

DataComp-LM: In search of the next generation of training sets for language models

Paper • 2406.11794 • Published Jun 17, 2024 • 50

upvoted a paper 9 months ago

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data

Paper • 2404.15653 • Published Apr 24, 2024 • 26