Official checkpoints for "Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models".
-
Fourier-VLM: Compressing Vision Tokens in the Frequency Domain for Large Vision-Language Models
Paper • 2508.06038 • Published -
whyisverysmart/Fourier-LLaVA-v1.5-7B-256
7B • Updated • 45 -
whyisverysmart/Fourier-LLaVA-v1.5-7B-144
7B • Updated • 10 -
whyisverysmart/Fourier-LLaVA-v1.5-7B-64
7B • Updated • 16