会员服务
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
Arxiv
0+阅读 · 4月3日
Preference-Driven Active 3D Scene Representation for Robotic Inspection in Nuclear Decommissioning
Arxiv
0+阅读 · 4月2日
SkyReels-A2: Compose Anything in Video Diffusion Transformers
SkyReels-A2: Compose Anything in Video Diffusion Transformers
Arxiv
0+阅读 · 4月3日
Towards Calibrating Financial Market Simulators with High-frequency Data
Arxiv
0+阅读 · 4月1日
Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation
Arxiv
0+阅读 · 4月2日
RealityAvatar: Towards Realistic Loose Clothing Modeling in Animatable 3D Gaussian Avatars
RealityAvatar: Towards Realistic Loose Clothing Modeling in Animatable 3D Gaussian Avatars
Arxiv
0+阅读 · 4月2日
GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
Arxiv
0+阅读 · 4月1日
UniViTAR: Unified Vision Transformer with Native Resolution
Arxiv
0+阅读 · 4月2日
Preparing graph states forbidding a vertex-minor
Arxiv
0+阅读 · 3月31日
Beyond a Single Mode: GAN Ensembles for Diverse Medical Data Generation
Arxiv
0+阅读 · 3月31日
Active Learning for Finite Element Simulations with Adaptive Non-Stationary Kernel Function
Arxiv
0+阅读 · 3月29日
Training-Free Text-Guided Image Editing with Visual Autoregressive Model
Arxiv
0+阅读 · 3月31日
Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging
Arxiv
0+阅读 · 3月31日
ViSketch-GPT: Collaborative Multi-Scale Feature Extraction for Sketch Recognition and Generation
ViSketch-GPT: Collaborative Multi-Scale Feature Extraction for Sketch Recognition and Generation
Arxiv
0+阅读 · 3月28日
Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization
Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization
Arxiv
0+阅读 · 3月28日
参考链接
微信扫码咨询专知VIP会员
Top