How to Synthesize Text Data without Model Collapse? Paper β’ 2412.14689 β’ Published 7 days ago β’ 45 β’ 3
LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis Paper β’ 2412.15214 β’ Published 6 days ago β’ 14
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling Paper β’ 2412.05271 β’ Published 19 days ago β’ 121
view article Article Bridging the Gap Between Physical Numerical Simulations and Machine Learning: Introducing The Well By rubenohana β’ 23 days ago β’ 17
stabilityai/stable-video-diffusion-img2vid-xt-1-1 Image-to-Video β’ Updated Jul 10 β’ 66.5k β’ 794