ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder Paper • 2510.18795 • Published 25 days ago • 10
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published Oct 9 • 108
Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval Paper • 2509.09118 • Published Sep 11 • 8
ForCenNet: Foreground-Centric Network for Document Image Rectification Paper • 2507.19804 • Published Jul 26 • 11
Region-based Cluster Discrimination for Visual Representation Learning Paper • 2507.20025 • Published Jul 26 • 19
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs Paper • 2504.17432 • Published Apr 24 • 39
Decoupled Global-Local Alignment for Improving Compositional Understanding Paper • 2504.16801 • Published Apr 23 • 14
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing Paper • 2504.02826 • Published Apr 3 • 68
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published Feb 18 • 16