wangf3014

SCLIP. Official implementation of SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

ViT-5. Official implementation of ViT-5: Vision Transformers for The Mid-2020s

Mamba-Reg. Python

Adventurer. Python

Patch_Scaling. Official implementation of Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

VTok. Official implementation of VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents

CP2. Python