-
OmnimatteRF: Robust Omnimatte with 3D Background Modeling
Paper • 2309.07749 • Published • 8 -
AudioSR: Versatile Audio Super-resolution at Scale
Paper • 2309.07314 • Published • 28 -
Generative Image Dynamics
Paper • 2309.07906 • Published • 53 -
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Paper • 2309.06895 • Published • 27
Dushwe
Dushwe
AI & ML interests
diffusion
Organizations
text-to-3D
-
X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation
Paper • 2312.00085 • Published • 9 -
ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
Paper • 2312.02201 • Published • 34 -
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
Paper • 2312.03611 • Published • 9 -
MVDD: Multi-View Depth Diffusion Models
Paper • 2312.04875 • Published • 10
llm
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Paper • 2310.09478 • Published • 21 -
Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams
Paper • 2310.08678 • Published • 14 -
Llama 2: Open Foundation and Fine-Tuned Chat Models
Paper • 2307.09288 • Published • 244 -
LLaMA: Open and Efficient Foundation Language Models
Paper • 2302.13971 • Published • 17
SSM
aigc
-
OmnimatteRF: Robust Omnimatte with 3D Background Modeling
Paper • 2309.07749 • Published • 8 -
AudioSR: Versatile Audio Super-resolution at Scale
Paper • 2309.07314 • Published • 28 -
Generative Image Dynamics
Paper • 2309.07906 • Published • 53 -
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Paper • 2309.06895 • Published • 27
llm
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Paper • 2310.09478 • Published • 21 -
Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams
Paper • 2310.08678 • Published • 14 -
Llama 2: Open Foundation and Fine-Tuned Chat Models
Paper • 2307.09288 • Published • 244 -
LLaMA: Open and Efficient Foundation Language Models
Paper • 2302.13971 • Published • 17
text-to-3D
-
X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation
Paper • 2312.00085 • Published • 9 -
ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
Paper • 2312.02201 • Published • 34 -
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
Paper • 2312.03611 • Published • 9 -
MVDD: Multi-View Depth Diffusion Models
Paper • 2312.04875 • Published • 10
SSM