MIMO: Multilingual Information Retrieval via Monolingual Objectives Paper • 2605.31171 • Published May 29 • 4
view article Article Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers +1 tomaarsen, NohTow, raphaelsty • 26 days ago • 110
view article Article GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval chungimungi • Aug 8 • 13
mDenseOn & mLateOn Collection A collection of open state-of-the-art single and multi-vector models and datasets for multilingual, long context and code retrieval • 19 items • Updated Aug 6 • 18
view article Article mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models lightonai • Jul 30 • 37
view article Article One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker lightonai • Jul 16 • 20
view article Article After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint lightonai • Jul 6 • 16
view article Article Party is over: regularizing ColBERT models to fix efficient ANN methods lightonai • Jun 16 • 23
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent Paper • 2603.13875 • Published Mar 14 • 36
Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval Paper • 2604.23734 • Published Apr 26 • 4
view article Article DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models lightonai • Apr 21 • 45
view article Article Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers tomaarsen • Apr 16 • 81
view article Article Multimodal Embedding & Reranker Models with Sentence Transformers tomaarsen • Apr 9 • 73
Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval Paper • 2604.04734 • Published Apr 6 • 16
view article Article BidirLM: Turning Generative LLMs into the Best Open-Source Omnimodal Encoders Nicolas-BZRD • Apr 7 • 28
BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs Paper • 2604.02045 • Published Apr 2 • 40