Computer Science and Programming
GIF
fastvlm-handwriting.gif.mp4 · 58 KB · click to show
fastvlm-handwriting.gif.mp4 · 58 KB · click to show
FastVLM: Efficient Vision Encoding for Vision Language Models
Code: https://github.com/apple/ml-fastvlm
Paper: https://www.arxiv.org/abs/2412.13303
✅ @MachineLearning_Programming
18 · 6.6K ·