Foundation Text-Generation Models Below 360M Parameters Collection Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters. • 43 items • Updated 5 days ago • 45
Adaptive Chunking: Optimizing Chunking-Method Selection for RAG Paper • 2603.25333 • Published Mar 26 • 4
(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models Paper • 2604.16429 • Published 15 days ago • 2
DeAR-Reranking Collection DeAR (Deep Agent Rank): Dual-Stage Document Reranking with Reasoning Agents Accepted at EMNLP Findings 2025 • 12 items • Updated Oct 21, 2025 • 2
view article Article OlmoEarth v1.1: A more efficient family of Earth observation models allenai • 8 days ago • 19
view article Article Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality ibm-granite • 13 days ago • 31
Precise Zero-Shot Dense Retrieval without Relevance Labels Paper • 2212.10496 • Published Dec 20, 2022 • 6
BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation Paper • 2508.06781 • Published Aug 9, 2025 • 1
view article Article Unlocking asynchronicity in continuous batching +1 ror, pcuenq, ariG23498 • 14 days ago • 55
view article Article SSE Retrieval MRL v2: Regularization of Representation Space and Performance Improvement via Hyperparameter Optimization RikkaBotan • 14 days ago • 2
Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient? Paper • 2605.10848 • Published 17 days ago • 5
A Causal Language Modeling Detour Improves Encoder Continued Pretraining Paper • 2605.12438 • Published 16 days ago • 7
jina-embeddings-v5-omni Collection Multimodal (text + image + video + audio) embedding models aligned with jina-embeddings-v5-text-*. Two sizes, four task variants each. • 27 items • Updated 15 days ago • 36
view article Article The State of Arabic Multimodal Embedding — What a 2B Finetune Taught Us Omartificial-Intelligence-Space • Apr 23 • 3
view article Article EMO: Pretraining mixture of experts for emergent modularity allenai • 19 days ago • 38