研究人员推出 OmniRetriever-7B，这是一款专为跨音频、视频和文本模态的任意到任意检索设计的新模型。该模型采用新颖的 Fusion-as-Teacher 蒸馏技术来改进联合表示学习。在六个基准的评估中，OmniRetriever-7B 在零样本检索任务上的表现优于 Gemini Embedding 2。 AI
影响 增强了跨模态检索能力，可能改进多模态 RAG 系统和搜索功能。
排序理由 该集群描述了一篇关于新模型和多模态检索基准的最新研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) encoders extend this setting to three modalities. Such encoders can produce a joint (T,V,A) embedding whenever all three modaliti…
arXiv:2605.26641v1 Announce Type: new Abstract: Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) encoders extend this setting to three modalities. Such encoders can produce a joi…
Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) encoders extend this setting to three modalities. Such encoders can produce a joint (T,V,A) embedding whenever all three modaliti…