-
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 • 31 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 19
Collections
Discover the best community collections!
Collections including paper arxiv:2403.18361
-
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 48 -
BRAVE: Broadening the visual encoding of vision-language models
Paper • 2404.07204 • Published • 14 -
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 24 -
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Paper • 2405.09818 • Published • 92
-
Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation
Paper • 2403.16990 • Published • 24 -
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 48 -
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
Paper • 2404.01197 • Published • 29 -
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
Paper • 2404.01367 • Published • 19
-
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 101 -
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs
Paper • 2403.20041 • Published • 34 -
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 48
-
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 99 -
sDPO: Don't Use Your Data All at Once
Paper • 2403.19270 • Published • 31 -
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 48 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 40