LightOnOCR-2 🦉 Collection LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated 18 days ago • 25
PaddleOCR-VL-1.6 Collection Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training • 5 items • Updated 15 days ago • 8
PP-OCRv6 Collection From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 18 items • Updated 3 days ago • 49
view article Article The Open Source Community is backing OpenEnv for Agentic RL +15 burtenshaw, spisakjo, lysandre, darktex, willcb, qjoy, pawalt, cwing-nv, danielhanchen, andrewzhou, shimmyshimmer, Hamid-Nazeri, Sanyam, zkwentz, emre0, lewtun, sergiopaniego • 6 days ago • 78
view article Article LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR lightonai • Oct 23, 2025 • 74
view article Article DeepSeek-V4: a million-token context that agents can actually use burtenshaw • Apr 24 • 50