ViTAR: Vision Transformer with Any Resolution
Paper
•
2403.18361
•
Published
•
52
vision foundation modesl
vision foundation models
-
-
BRAVE: Broadening the visual encoding of vision-language models
Paper • 2404.07204 • Published • 18 -
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 26 -
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Paper • 2405.09818 • Published • 126 -
Many-Shot In-Context Learning in Multimodal Foundation Models
Paper • 2405.09798 • Published • 26 -
ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Paper • 2405.15738 • Published • 43 -
Matryoshka Multimodal Models
Paper • 2405.17430 • Published • 31 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 50