LightOn-rerank Collection LightOn-rerank models are unified cross-encoder rerankers: Qwen3.5 LoRAs scoring both text passages and document page images against a query. • 6 items • Updated 2 days ago • 3
view article Article One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker lightonai • 2 days ago • 11
view article Article NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval nvidia • 2 days ago • 38
view article Article Welcome Inkling by Thinking Machines +2 burtenshaw, merve, pcuenq, ariG23498 • 4 days ago • 85
Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing Paper • 2606.03565 • Published Jun 14 • 4
view article Article Native-speed vLLM transformers modeling backend hmellor, lysandre • 11 days ago • 53
Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models Paper • 2607.05803 • Published 12 days ago • 10
view article Article From Hugging Face to Amazon SageMaker Studio in one click amazon • 11 days ago • 13
view article Article After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint lightonai • 12 days ago • 13
Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search Paper • 2605.30917 • Published May 29 • 8
view article Article LeRobot v0.6.0: Imagine, Evaluate, Improve +7 imstevenpmwork, pepijn223, CarolinePascal, lilkm, maximellerbach, nepyope, nikodembartnik, Nico-robot, thomwolf • 12 days ago • 64
Ornith-1.0 Collection Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated 21 days ago • 347
DoctoBERT-fr Collection French medical encoders pretrained from scratch on curated and LLM-rephrased medical web data. • 6 items • Updated 12 days ago • 9
view article Article Where Does the Signal Live? <br> A Web Data Recipe for Medical Encoder Pretraining bofenghuang • 28 days ago • 9