-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 21 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 9 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 33 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 19
Collections
Discover the best community collections!
Collections including paper arxiv:2404.16030
-
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Paper • 2404.16821 • Published • 49 -
Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings
Paper • 2404.16820 • Published • 15 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 11
-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 25 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 11 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 44 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 26