SAILViT - a BytedanceDouyinContent Collection

BytedanceDouyinContent 's Collections

VGR

SAIL-VL

SAILViT

SAILViT

updated 12 days ago

Visual Foundation Models Powering Vision-Language Models

BytedanceDouyinContent/SAILViT-Large-300M-448px

Image Feature Extraction • 0.3B • Updated Jul 3 • 8 • 1
BytedanceDouyinContent/SAILViT-Huge-600M-448px

Image Feature Extraction • 0.7B • Updated Jul 3 • 10
SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement

Paper • 2507.01643 • Published Jul 2 • 1