EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment Paper • 2309.01151 • Published Sep 3, 2023 • 1
LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models Paper • 2309.01155 • Published Sep 3, 2023
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms Paper • 2603.28489 • Published 16 days ago • 30