No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Paper
•
2404.04125
•
Published
•
27
Foundation Models
-
-
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
Paper • 2404.08197 • Published • 27 -
Probing the 3D Awareness of Visual Foundation Models
Paper • 2404.08636 • Published • 12 -
AM-RADIO: Agglomerative Model -- Reduce All Domains Into One
Paper • 2312.06709 • Published • 1 -
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
Paper • 2405.10300 • Published • 26 -
Depth Anything V2
Paper • 2406.09414 • Published • 95 -
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
Paper • 2412.04424 • Published • 55