SOTAVerified

cross-modal alignment

Papers

Showing 125 of 342 papers

TitleStatusHype
Skywork-R1V3 Technical ReportCode7
Phantom: Subject-consistent video generation via cross-modal alignmentCode5
Flash-VStream: Efficient Real-Time Understanding for Long Video StreamsCode3
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical ReasoningCode3
GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and ImagesCode3
CrossOver: 3D Scene Cross-Modal AlignmentCode3
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented GenerationCode3
Ola: Pushing the Frontiers of Omni-Modal Language ModelCode3
Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsCode3
Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object DetectionCode3
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal AlignmentCode2
ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single ModelCode2
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic DataCode2
Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration RateCode2
Melody-Guided Music GenerationCode2
Law of Vision Representation in MLLMsCode2
Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion ApproachCode2
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIPCode2
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language ModelsCode2
Seeing the Image: Prioritizing Visual Correlation by Contrastive AlignmentCode2
HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual GroundingCode2
MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wildCode2
Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio GenerationCode2
Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal AlignmentCode2
CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object DetectionCode2
Show:102550
← PrevPage 1 of 14Next →

No leaderboard results yet.