Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis Paper • 2404.13686 • Published Apr 21 • 27
PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation Paper • 2404.13026 • Published Apr 19 • 23
BRAVE: Broadening the visual encoding of vision-language models Paper • 2404.07204 • Published Apr 10 • 18
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD Paper • 2404.06512 • Published Apr 9 • 29