中英双语、29项第一、像素级理解：360 FG-CLIP2登顶全球最强图文跨模态模型
"跨模态" 相关文章
UniSOT: A Unified Framework for Multi-Modality Single Object Tracking
FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video
视觉语言模型“扫地僧”：360低调开源FG-CLIP2登顶29项全球基准测试 | 甲子光年
PULSE: Privileged Knowledge Transfer from Electrodermal Activity to Low-Cost Sensors for Stress Monitoring
MIO: A Foundation Model on Multimodal Tokens
RAG-Anything: All-in-One RAG Framework
MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation
Centering Emotion Hotspots: Multimodal Local-Global Fusion and Cross-Modal Alignment for Emotion Recognition in Conversations
Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Unified Unsupervised Anomaly Detection via Matching Cost Filtering
AToken: A Unified Tokenizer for Vision
UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice
阿里云推出全球首个全模态 AI 模型 Qwen3-Omni
Cross-Modal Knowledge Distillation for Speech Large Language Models
AToken: A Unified Tokenizer for Vision
理解LLM系列：文字vs图像
