-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 25 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 12 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 36 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 19
Collections
Discover the best community collections!
Collections including paper arxiv:2410.10816
-
WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens
Paper • 2401.09985 • Published • 14 -
CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects
Paper • 2401.09962 • Published • 7 -
Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution
Paper • 2401.10404 • Published • 10 -
ActAnywhere: Subject-Aware Video Background Generation
Paper • 2401.10822 • Published • 13
-
Video Instruction Tuning With Synthetic Data
Paper • 2410.02713 • Published • 33 -
Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
Paper • 2410.02740 • Published • 51 -
LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
Paper • 2410.10816 • Published • 15
-
SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
Paper • 2407.09413 • Published • 9 -
MAVIS: Mathematical Visual Instruction Tuning
Paper • 2407.08739 • Published • 30 -
Kvasir-VQA: A Text-Image Pair GI Tract Dataset
Paper • 2409.01437 • Published • 70 -
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
Paper • 2409.05840 • Published • 45