Fourier-VLM: Compressing Vision Tokens in the Frequency Domain for Large Vision-Language Models
Paper • 2508.06038 • Published
Fourier Compressor
Official checkpoints for "Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models".
-
-
whyisverysmart/Fourier-LLaVA-v1.5-7B-256
7B • Updated • 5 -
whyisverysmart/Fourier-LLaVA-v1.5-7B-144
7B • Updated • 2 -
whyisverysmart/Fourier-LLaVA-v1.5-7B-64
7B • Updated • 4 -
whyisverysmart/Fourier-LLaVA-v1.5-7B-36
7B • Updated • 3 -
whyisverysmart/Fourier-LLaVA-v1.5-13B-144
13B • Updated • 3 -
whyisverysmart/Fourier-Qwen2-VL-2B-0.67
2B • Updated • 5 -
whyisverysmart/Fourier-Qwen2.5-VL-3B-0.67
4B • Updated • 13 • 1