The report introduces pplx-embed-v2-late, a pair of multilingual and multimodal late‑interaction models sized at 0.6B and 9B parameters. Both models achieve state‑of‑the‑art performance on text, image, and visual document retrieval benchmarks, with the 0.6B model matching larger models on visual document tasks. They are trained via representation distillation from an 18B teacher, enabling a shared embedding space that allows documents to be indexed with the 9B model and queried with the low‑latency 0.6B model.
arXiv:2608. 11343v1 Announce Type: new Abstract: Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder models that align visual and textual representations through contrastive learning.
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space for applications such as retrieval, recommendatio...
CausalEmbed is an auto‑regressive method for generating compact multi‑vector embeddings in visual document retrieval. By using iterative margin loss during contrastive training, it reduces the number of visual tokens needed by 30‑155× while keeping performance competitive across different backbones and benchmarks. The approach offers efficient training, scalable test‑time performance, and a flexible scaling strategy for multi‑vector representations.
Omni-Embed-Mini is a 0.9B‑parameter model that embeds text, speech, audio, images, video, and visually‑rich documents into a single shared cosine space without updating any text‑side parameters. It uses a dense cascaded caption as a teacher signal, allowing the teacher and student to share identical backbone weights and requiring only lightweight projectors and phased LoRA adapters for alignment. The model achieves strong text retrieval performance (49.57 nDCG@10 on MTEB‑v2 BEIR‑8) while extending to five additional modalities and is significantly smaller than other open omni‑modal embedders.
arXiv:2608.24053v1 Announce Type: new Abstract: Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space...
arXiv:2604.18508v2 Announce Type: replace-cross Abstract: Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the un...
arXiv:2610.27273v1 Announce Type: cross Abstract: Multi-vector retrieval models such as ColBERT often outperform single-vector models of comparable scale by matching queries and documents at the toke...
arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.
arXiv:2609.37225v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods eith...
The paper introduces DEPT, a method that trains a single decoder-only large language model to both expand queries and encode documents for retrieval. By preserving document embeddings close to their initial cached values while allowing gradients to flow through the generator, DEPT stabilizes retrieval targets and enables efficient index reuse and online hard‑negative mining. Experiments on the BEIR benchmark with Qwen3‑4B‑Instruct‑2507 and LLaMA‑3.2‑3B‑Instruct show that DEPT outperforms training‑free, independently trained, and staged unified baselines, with ablations confirming the benefits of preservation, whitening, end‑to‑end expansion training, and online negatives.
arXiv:2606. 04240v1 Announce Type: cross Abstract: Retrieval over visually-rich documents, pages that interleave text with figures, tables, and charts, is essential for multimodal retrieval-augmented generation, yet most retrievers still discard the visual channel.
Visual document retrieval has recently become increasingly important in applications such as enterprise search, scientific literature discovery, and retrieval-augmented generation. These applications depend on efficiently identifying query-relevant pages across large collections of visually rich documents.