An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper
•
2406.09415
•
Published
•
50
Vision Task
-
-
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
Paper • 2406.09406 • Published • 13 -
VideoGUI: A Benchmark for GUI Automation from Instructional Videos
Paper • 2406.10227 • Published • 9 -
What If We Recaption Billions of Web Images with LLaMA-3?
Paper • 2406.08478 • Published • 39 -
INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model
Paper • 2407.16198 • Published • 13 -
VideoGameBunny: Towards vision assistants for video games
Paper • 2407.15295 • Published • 21 -
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
Paper • 2407.15754 • Published • 19 -
Theia: Distilling Diverse Vision Foundation Models for Robot Learning
Paper • 2407.20179 • Published • 45 -
SHIC: Shape-Image Correspondences with no Keypoint Supervision
Paper • 2407.18907 • Published • 39 -
Matting by Generation
Paper • 2407.21017 • Published • 22 -
Improving 2D Feature Representations by 3D-Aware Fine-Tuning
Paper • 2407.20229 • Published • 7 -
Diffusion Models as Data Mining Tools
Paper • 2408.02752 • Published • 13 -
Segment Anything with Multiple Modalities
Paper • 2408.09085 • Published • 21 -
Sapiens: Foundation for Human Vision Models
Paper • 2408.12569 • Published • 88 -
HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments
Paper • 2408.10945 • Published • 6 -
Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos
Paper • 2410.16259 • Published • 4