view article Article ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third lightonai • 5 days ago • 19
view article Article LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model lightonai • 9 days ago • 39
SEA-CLIP-Tiny (ACCV 2026) Collection Weights, ablations and training data for SEA-CLIP-Tiny: a 46M-parameter multilingual text-vision embedding model for Southeast Asian languages. • 15 items • Updated 26 days ago • 1
Running on CPU Upgrade Agents 1 Clinical Consultation Assistant 🩺 1 Synthetic consultation documentation demo.
Running on CPU Upgrade Agents 1 Clinical Consultation Assistant 🩺 1 Synthetic consultation documentation demo.
Running on CPU Upgrade Agents 1 Clinical Consultation Assistant 🩺 1 Synthetic consultation documentation demo.
view article Article Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes erikkaum • Aug 7 • 20
view article Article mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models lightonai • Jul 30 • 40
view article Article BidirLM: Turning Generative LLMs into the Best Open-Source Omnimodal Encoders Nicolas-BZRD • Apr 7 • 28
CohereLabs/cohere-transcribe-03-2026 Automatic Speech Recognition • 2B • Updated 10 days ago • 123k • • 1.19k
Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures Paper • 2510.24081 • Published Oct 28, 2025 • 24