ForCenNet: Foreground-Centric Network for Document Image Rectification Paper • 2507.19804 • Published Jul 26 • 11 • 2
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs Paper • 2504.17432 • Published Apr 24 • 39 • 4
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs Paper • 2504.17432 • Published Apr 24 • 39 • 4
Decoupled Global-Local Alignment for Improving Compositional Understanding Paper • 2504.16801 • Published Apr 23 • 15 • 2
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published Feb 18 • 16 • 2