Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs Paper • 2504.17432 • Published 3 days ago • 32
Decoupled Global-Local Alignment for Improving Compositional Understanding Paper • 2504.16801 • Published 3 days ago • 14
UniME Collection UniME is a series of multimodal large language models trained for learning universal multimodal embedding. • 3 items • Updated 2 days ago • 3
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models Paper • 2504.10479 • Published 12 days ago • 242
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published Feb 18 • 16