Tag
该论文在统一可控的基准框架下系统评估了多模态嵌入学习中的各类对比训练策略，发现大多数策略相比标准对齐基线仅有边际收益甚至带来负面影响，并提出结合难负样本挖掘、假负样本缓解与难批次构建的协同训练方案，在MMEB上以Qwen2-VL-2B平均提升6.0%。
Google DeepMind launches EmbeddingGemma 2, a 740M-parameter open (Apache 2.0) multimodal embedding model that unifies text, code, images, video, and audio into a shared embedding space optimized for on-device inference, built on the Gemma 4 architecture with 8K context and Matryoshka truncation for storage efficiency.
Google DeepMind released EmbeddingGemma 2, an open multimodal embedding model (740M params) that maps text, images, video, and audio into a unified 768-d vector space, designed for on-device search, RAG, and classification with Matryoshka truncation for reduced storage costs.
Omni-Embed-Mini presents a 0.9B-parameter omni-modal embedding model that maps text, speech, audio, images, video, and documents into a shared cosine space without updating any text-side parameters, using dense distillation from the frozen backbone's own caption embeddings. The 2.3B variant is competitive with Gemini Embedding-2, and all models, code, and data are released.
这篇论文提出 EviAlign，将语义证据生成与边界读出（Boundary Readout）耦合到共享的多模态大语言模型中，联合训练生成与对比检索目标，在 12 个 MMEB 检索任务上以 500K 训练对达到 76.9 的平均 Recall@1，同时保持单向量索引与打分。
An ex-YouTube engineer demonstrates rebuilding core YouTube features in 45 minutes, including home feed, video upload, playback, database, search with multimodal embeddings, and deployment to a real URL.
This paper compares natively multimodal embedding models (Gemini Embedding 2, Amazon Nova 2) against frontier LLMs (GPT-4.1, Claude Sonnet 4.6) for hard-negative text-to-image retrieval, finding comparable accuracy but much lower latency for embedding-based ranking.
This paper introduces jina-embeddings-v5-omni, a suite of multimodal embedding models that extend text embeddings to image, audio, and video using frozen-tower composition. The method trains only 0.35% of the total weights, maintaining text geometry while achieving competitive state-of-the-art performance with significantly lower computational cost.