Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes
"模态差距" 相关文章
Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding
Multimodal RAG Enhanced Visual Description
KinMo: Kinematic-aware Human Motion Understanding and Generation
GIIFT: Graph-guided Inductive Image-free Multimodal Machine Translation
