Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models Paper • 2506.05176 • Published Jun 5, 2025 • 84
AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents Paper • 2407.18901 • Published Jul 26, 2024 • 36
view article Article Party is over: regularizing ColBERT models to fix efficient ANN methods lightonai • 10 days ago • 23
view article Article Ettin Suite: SoTA Paired Encoders and Decoders +4 orionweller, kdricci, mmarone, NohTow, dlawrie, vandurme • Jul 16, 2025 • 81
view article Article Gaia2 and ARE: Empowering the community to study agents +9 clefourrier, gregmialz, mlcu, mortimerp9, XciD, tfrere, evijit, RomainFroger, dheeraj7596, CarolinePascal, upiter • Sep 22, 2025 • 136
Experiential Reflective Learning for Self-Improving LLM Agents Paper • 2603.24639 • Published Mar 25 • 3
Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models Paper • 2603.26259 • Published Mar 27 • 8
gliner2 family Collection GLiNER2 extends the original GLiNER architecture to support multi-task information extraction with a schema-driven interface. • 7 items • Updated May 16 • 53
view article Article A framework and leaderboard for Retrieval Pipelines evaluation on ViDoRe v3 antoineedy • Feb 27 • 12
view article Article Nemotron ColEmbed V2: Raising the Bar for Multimodal Retrieval with ViDoRe V3’s Top Model nvidia • Feb 4 • 28
view article Article RexRerankers: SOTA Rankers for Product Discovery and AI Assistants thebajajra • Jan 24 • 44
ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios Paper • 2601.08620 • Published Jan 13 • 12
view article Article Llama‑Embed‑Nemotron‑8B Text Embedding Model Ranks First on Multilingual MTEB Leaderboard nvidia • Oct 21, 2025 • 14
view article Article ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval manu • Mar 18, 2025 • 16
ViDoRe Benchmark V3 Collection ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. • 8 items • Updated Jan 14 • 22
view article Article ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases QuentinJG • Nov 5, 2025 • 67
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing Paper • 1808.06226 • Published Aug 19, 2018 • 3