GLiClass-v4 Collection The next generation of zero-shot classifiers. • 3 items • Updated about 7 hours ago • 2
view article Article Welcome Beam: a 501B open model you can own, customize, and scale +1 burtenshaw, merve, pcuenq • about 20 hours ago • 11
Beam 1.0 Collection Reflection’s first open-weight model, built for coding, reasoning, and agentic tasks • 4 items • Updated about 7 hours ago • 31
view article Article ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases QuentinJG • Nov 5, 2025 • 69
Timestral Collection Time series foundation models for zero-shot probabilistic forecasting. • 4 items • Updated 1 day ago • 22
view article Article UltraBERT: One Encoder for Classification and Retrieval dmis-lab • 3 days ago • 50
UltraBERT Collection UltraBERT: Beyond the Limit of BERT Pre-Training. Pre-trained 150M/380M encoders and a text embedding model, English, 32K context. • 4 items • Updated 3 days ago • 27
Nemotron Retriever Collection Formerly known as Nemotron RAG. Models for embedding, reranking, and document parsing for RAG and agentic retrieval. • 13 items • Updated 4 days ago • 112
Amos 1 Collection Open-weight decision models from 0.5B to 27B: typed questions in, a probability for every answer out. Apache 2.0. • 4 items • Updated 3 days ago • 12
view article Article UIBK-Embedding-v1: A Dense and a Late-Interaction Retriever in One Model, One Index and One Search abdoelsayed • 4 days ago • 13
[Sparse models] French SparseUp Collection French replication of Linkup-Platform/linkup-sparseup-embed-v1 sparse model. • 5 items • Updated 4 days ago • 1
view article Article Sparseup-fr: A French replication of Linkup's sparse embedding model alphaedge-ai • 4 days ago • 10
view article Article ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third lightonai • 4 days ago • 19
view article Article LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model lightonai • 8 days ago • 36
TermGrade Collection 1k graded terminal environments, 36k trajectories, and the RL run they trained. • 5 items • Updated 8 days ago • 6