Collections
Discover the best community collections!
Collections including paper arxiv:2405.10300
-
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
Paper • 2311.17049 • Published • 1 -
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Paper • 2405.04434 • Published • 14 -
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision
Paper • 2303.17376 • Published -
Sigmoid Loss for Language Image Pre-Training
Paper • 2303.15343 • Published • 6
-
ibm-granite/granite-34b-code-instruct-8k
Text Generation • Updated • 377 • 73 -
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
Paper • 2405.10300 • Published • 26 -
rain1011/pyramid-flow-sd3
Text-to-Video • Updated • 798 -
answerdotai/ModernBERT-large
Fill-Mask • Updated • 28.1k • 295
-
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Paper • 2404.04125 • Published • 27 -
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
Paper • 2404.08197 • Published • 27 -
Probing the 3D Awareness of Visual Foundation Models
Paper • 2404.08636 • Published • 12 -
AM-RADIO: Agglomerative Model -- Reduce All Domains Into One
Paper • 2312.06709 • Published • 1
-
LocalMamba: Visual State Space Model with Windowed Selective Scan
Paper • 2403.09338 • Published • 7 -
GiT: Towards Generalist Vision Transformer through Universal Language Interface
Paper • 2403.09394 • Published • 25 -
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Paper • 2402.19479 • Published • 32 -
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
Paper • 2405.10300 • Published • 26
-
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 • 40 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 20