SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment
"跨模态对齐" 相关文章
轻量高效，即插即用：Video-RAG为长视频理解带来新范式
Topological Alignment of Shared Vision-Language Embedding Space
TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data
小米开源首个原生端到端语音大模型 Xiaomi-MiMo-Audio
Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment
Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
首篇多模态 RAG 全栈技术综述出炉~
Ola: A State-of-the-Art Omni-Modal Understanding Model with Advanced Progressive Modality Alignment Strategy
高效评估多模态预训练对齐质量，中科大提出模态融合率MIR
