What matters when building vision-language models?
Paper
•
2405.02246
•
Published
•
103
vision
-
-
An Introduction to Vision-Language Modeling
Paper • 2405.17247 • Published • 90 -
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
Paper • 2405.19707 • Published • 8 -
Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations
Paper • 2410.08049 • Published • 8 -
Task Vectors are Cross-Modal
Paper • 2410.22330 • Published • 11 -
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Paper • 2411.14347 • Published • 15 -
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
Paper • 2412.04424 • Published • 63 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 118 -
iFormer: Integrating ConvNet and Transformer for Mobile Application
Paper • 2501.15369 • Published • 13 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 151 -
Optimal Brain Apoptosis
Paper • 2502.17941 • Published • 10 -
DINOv3
Paper • 2508.10104 • Published • 270 -
Real-Time Object Detection Meets DINOv3
Paper • 2509.20787 • Published • 10