-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 29 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 14 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 44 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 23
Collections
Discover the best community collections!
Collections including paper arxiv:2412.18653
-
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 91 -
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 224 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 202 -
Sharp Monocular View Synthesis in Less Than a Second
Paper • 2512.10685 • Published • 26
-
1.58-bit FLUX
Paper • 2412.18653 • Published • 86 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 627 -
BitNet a4.8: 4-bit Activations for 1-bit LLMs
Paper • 2411.04965 • Published • 69 -
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper • 2310.11453 • Published • 105
-
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
Paper • 2401.09048 • Published • 10 -
Improving fine-grained understanding in image-text pre-training
Paper • 2401.09865 • Published • 18 -
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Paper • 2401.10891 • Published • 62 -
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
Paper • 2401.13627 • Published • 78
-
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Paper • 2205.14135 • Published • 15 -
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Paper • 2307.08691 • Published • 9 -
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
Paper • 2407.08608 • Published • 1 -
1.58-bit FLUX
Paper • 2412.18653 • Published • 86
-
1.58-bit FLUX
Paper • 2412.18653 • Published • 86 -
Region-Adaptive Sampling for Diffusion Transformers
Paper • 2502.10389 • Published • 53 -
One-step Diffusion Models with f-Divergence Distribution Matching
Paper • 2502.15681 • Published • 8 -
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
Paper • 2502.20126 • Published • 19
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 29 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 14 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 44 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 23
-
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
Paper • 2401.09048 • Published • 10 -
Improving fine-grained understanding in image-text pre-training
Paper • 2401.09865 • Published • 18 -
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Paper • 2401.10891 • Published • 62 -
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
Paper • 2401.13627 • Published • 78
-
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 91 -
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 224 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 202 -
Sharp Monocular View Synthesis in Less Than a Second
Paper • 2512.10685 • Published • 26
-
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Paper • 2205.14135 • Published • 15 -
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Paper • 2307.08691 • Published • 9 -
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
Paper • 2407.08608 • Published • 1 -
1.58-bit FLUX
Paper • 2412.18653 • Published • 86
-
1.58-bit FLUX
Paper • 2412.18653 • Published • 86 -
Region-Adaptive Sampling for Diffusion Transformers
Paper • 2502.10389 • Published • 53 -
One-step Diffusion Models with f-Divergence Distribution Matching
Paper • 2502.15681 • Published • 8 -
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
Paper • 2502.20126 • Published • 19
-
1.58-bit FLUX
Paper • 2412.18653 • Published • 86 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 627 -
BitNet a4.8: 4-bit Activations for 1-bit LLMs
Paper • 2411.04965 • Published • 69 -
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper • 2310.11453 • Published • 105