view article Article NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval nvidia • 6 days ago • 55
Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search Paper • 2605.30917 • Published May 29 • 8
jina-embeddings-v5-text: Task-Targeted Embedding Distillation Paper • 2602.15547 • Published Feb 17 • 31
Is Position Bias in Dense Retrievers Built In-or Learned from Data? Paper • 2605.26578 • Published May 26 • 20
DenseOn & LateOn Collection A collection of open state-of-the-art single and multi-vector models for English retrieval • 9 items • Updated 13 days ago • 13
view article Article DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models lightonai • Apr 21 • 44
view article Article Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers tomaarsen • Apr 16 • 75
e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings Paper • 2601.03666 • Published Jan 7 • 5
view article Article Multimodal Embedding & Reranker Models with Sentence Transformers tomaarsen • Apr 9 • 67
Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval Paper • 2604.04734 • Published Apr 6 • 16
Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment Paper • 2604.05684 • Published Apr 7 • 10
view article Article BidirLM: Turning Generative LLMs into the Best Open-Source Omnimodal Encoders Nicolas-BZRD • Apr 7 • 28
MILCO: Multilingual Learned Sparse Retrieval Collection MILCO maps queries and documents from different languages into a shared English lexical space via a multilingual connector. • 4 items • Updated May 15 • 4
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 918
jina-embeddings-v5-text Collection Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated Feb 27 • 41
pplx-embed Collection Diffusion-Pretrained Dense and Contextual Embeddings • 10 items • Updated May 26 • 100
KoViDoRe Benchmark (BEIR) v2 Collection Korean Vision Document Retrieval Benchmark • 4 items • Updated Mar 2 • 6
view article Article Nano-BEIR: A Multilingual Information Retrieval Benchmark with Quality-Enhanced Queries sionic-ai • Dec 22, 2025 • 12