-
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Paper • 2404.02905 • Published • 73 -
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
Paper • 2404.02733 • Published • 22 -
Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models
Paper • 2404.02747 • Published • 13 -
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
Paper • 2404.01367 • Published • 22
Chenxin Li
XGGNet
AI & ML interests
None yet
Organizations
None yet
AI4Science
Efficient&SSM
3D
-
3D Congealing: 3D-Aware Image Alignment in the Wild
Paper • 2404.02125 • Published • 10 -
FlexiDreamer: Single Image-to-3D Generation with FlexiCubes
Paper • 2404.00987 • Published • 23 -
ST-LLM: Large Language Models Are Effective Temporal Learners
Paper • 2404.00308 • Published • 8 -
InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds
Paper • 2403.20309 • Published • 19
Gen AI
-
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Paper • 2404.02905 • Published • 73 -
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
Paper • 2404.02733 • Published • 22 -
Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models
Paper • 2404.02747 • Published • 13 -
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
Paper • 2404.01367 • Published • 22
Efficient&SSM
AI4Science
3D
-
3D Congealing: 3D-Aware Image Alignment in the Wild
Paper • 2404.02125 • Published • 10 -
FlexiDreamer: Single Image-to-3D Generation with FlexiCubes
Paper • 2404.00987 • Published • 23 -
ST-LLM: Large Language Models Are Effective Temporal Learners
Paper • 2404.00308 • Published • 8 -
InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds
Paper • 2403.20309 • Published • 19