QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
Paper
• 2502.05178 • Published
• 10
Image-Text Alignment
-
-
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
Paper • 2502.14846 • Published • 14 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 158 -
Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features
Paper • 2504.00557 • Published • 15 -
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
Paper • 2504.07934 • Published • 21 -
Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction
Paper • 2505.02471 • Published • 15 -
FG-CLIP: Fine-Grained Visual and Textual Alignment
Paper • 2505.05071 • Published • 18 -
GenRecal: Generation after Recalibration from Large to Small Vision-Language Models
Paper • 2506.15681 • Published • 42 -
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Paper • 2507.04590 • Published • 17 -
MetaCLIP 2: A Worldwide Scaling Recipe
Paper • 2507.22062 • Published • 37 -
Adapting Vision-Language Models Without Labels: A Comprehensive Survey
Paper • 2508.05547 • Published • 11 -
Concept-Aware Batch Sampling Improves Language-Image Pretraining
Paper • 2511.20643 • Published • 3