Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs Paper • 2504.17432 • Published 9 days ago • 38
Decoupled Global-Local Alignment for Improving Compositional Understanding Paper • 2504.16801 • Published 10 days ago • 15
UniME Collection UniME is a series of multimodal large language models trained for learning universal multimodal embedding. • 3 items • Updated 8 days ago • 4
Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC Paper • 2203.15565 • Published Mar 28, 2022 • 1
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published Feb 18 • 16
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published Feb 18 • 16