WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding Paper • 2611.26409 • Published 3 days ago • 46
WeVisOne-VL: Unified Visual Perception from Objects to Pixels Paper • 2610.31329 • Published Oct 22 • 46
WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report Paper • 2608.24053 • Published Aug 25 • 73
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models Paper • 2606.03748 • Published Jun 2 • 28
ObjEmbed Collection ObjEmbed: Towards Universal Multimodal Object Embeddings • 4 items • Updated May 18
WeDetect Collection WeDetect: Fast Open-Vocabulary Object Detection as Retrieval • 7 items • Updated May 18 • 3
WeDetect Collection WeDetect: Fast Open-Vocabulary Object Detection as Retrieval • 7 items • Updated May 18 • 3
ObjEmbed Collection ObjEmbed: Towards Universal Multimodal Object Embeddings • 4 items • Updated May 18