Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis Paper • 2404.13686 • Published Apr 21, 2024 • 28
PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation Paper • 2404.13026 • Published Apr 19, 2024 • 24
BRAVE: Broadening the visual encoding of vision-language models Paper • 2404.07204 • Published Apr 10, 2024 • 19
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD Paper • 2404.06512 • Published Apr 9, 2024 • 30