AIMv2 Collection A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated 6 days ago • 56
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model Paper • 2409.01704 • Published Sep 3 • 82
Wolf: Captioning Everything with a World Summarization Framework Paper • 2407.18908 • Published Jul 26 • 31