-
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 95 -
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 238 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 219 -
Sharp Monocular View Synthesis in Less Than a Second
Paper • 2512.10685 • Published • 28
Collections
Discover the best community collections!
Collections including paper arxiv:2512.04677
-
SAM 3: Segment Anything with Concepts
Paper • 2511.16719 • Published • 129 -
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Paper • 2512.08765 • Published • 132 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 171 -
LongCat-Image Technical Report
Paper • 2512.07584 • Published • 23
-
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 238 -
REASONEDIT: Towards Reasoning-Enhanced Image Editing Models
Paper • 2511.22625 • Published • 47 -
Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
Paper • 2511.22677 • Published • 33 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 171
-
Test-Time Scaling with Reflective Generative Model
Paper • 2507.01951 • Published • 108 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 152 -
Autoregressive Diffusion Models
Paper • 2110.02037 • Published -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 8
-
One Shot, One Talk: Whole-body Talking Avatar from a Single Image
Paper • 2412.01106 • Published • 24 -
MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation
Paper • 2412.04448 • Published • 10 -
IDOL: Instant Photorealistic 3D Human Creation from a Single Image
Paper • 2412.14963 • Published • 6 -
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper • 2502.01061 • Published • 223
-
SPATIALGEN: Layout-guided 3D Indoor Scene Generation
Paper • 2509.14981 • Published • 28 -
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
Paper • 2511.14993 • Published • 231 -
Kling-Omni Technical Report
Paper • 2512.16776 • Published • 170 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 171
-
StyleMaster: Stylize Your Video with Artistic Generation and Translation
Paper • 2412.07744 • Published • 20 -
Video Motion Transfer with Diffusion Transformers
Paper • 2412.07776 • Published • 17 -
ObjCtrl-2.5D: Training-free Object Control with Camera Poses
Paper • 2412.07721 • Published • 9 -
MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance
Paper • 2412.05355 • Published • 8
-
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 • 15 -
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
-
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 95 -
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 238 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 219 -
Sharp Monocular View Synthesis in Less Than a Second
Paper • 2512.10685 • Published • 28
-
SAM 3: Segment Anything with Concepts
Paper • 2511.16719 • Published • 129 -
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Paper • 2512.08765 • Published • 132 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 171 -
LongCat-Image Technical Report
Paper • 2512.07584 • Published • 23
-
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 238 -
REASONEDIT: Towards Reasoning-Enhanced Image Editing Models
Paper • 2511.22625 • Published • 47 -
Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
Paper • 2511.22677 • Published • 33 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 171
-
SPATIALGEN: Layout-guided 3D Indoor Scene Generation
Paper • 2509.14981 • Published • 28 -
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
Paper • 2511.14993 • Published • 231 -
Kling-Omni Technical Report
Paper • 2512.16776 • Published • 170 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 171
-
Test-Time Scaling with Reflective Generative Model
Paper • 2507.01951 • Published • 108 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 152 -
Autoregressive Diffusion Models
Paper • 2110.02037 • Published -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 8
-
StyleMaster: Stylize Your Video with Artistic Generation and Translation
Paper • 2412.07744 • Published • 20 -
Video Motion Transfer with Diffusion Transformers
Paper • 2412.07776 • Published • 17 -
ObjCtrl-2.5D: Training-free Object Control with Camera Poses
Paper • 2412.07721 • Published • 9 -
MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance
Paper • 2412.05355 • Published • 8
-
One Shot, One Talk: Whole-body Talking Avatar from a Single Image
Paper • 2412.01106 • Published • 24 -
MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation
Paper • 2412.04448 • Published • 10 -
IDOL: Instant Photorealistic 3D Human Creation from a Single Image
Paper • 2412.14963 • Published • 6 -
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper • 2502.01061 • Published • 223
-
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 • 15 -
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