H Company released NeoMME, a family of 260M and 800M multilingual multimodal encoders that process text and images with a single bidirectional Transformer, trained from scratch with a masked discrete-…
Weaviate introduces a late-interaction multi-vector retrieval approach that embeds entire PDF pages—including charts and tables—as single units, eliminating the need for OCR and text chunking in RAG p…
Researchers introduced L"etzCross, a benchmark for cross-lingual page-level retrieval over Luxembourgish PDF documents, and found that ColPali-style page-image retrievers outperform OCR-based text-onl…
Tencent released EVE Preview 4.5B, a 4.5 billion parameter visual document retriever that matches text queries against document page images directly without OCR, ranking first on ViDoRe V3 and earlier…
Hugging Face released Sentence Transformers v6.0, adding a MultiVectorEncoder that natively supports ColBERT-style late interaction and ColPali visual document retrieval checkpoints. The update enable…
A new arXiv preprint introduces ColGraphRAG, a late-interaction evidence retrieval method for multimodal GraphRAG that replaces single-vector bi-encoder similarity with MaxSim-style multi-vector scori…
A study benchmarking six RAG architectures on a financial PDF reveals that Vision RAG achieves the highest answer correctness (0.823) but low faithfulness (0.538), while Graph RAG is the most faithful…