LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling Feb 12 • 57
LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR Oct 23, 2025 • 74
lightonai/LightOnOCR-2-1B-bbox-soup Image-Text-to-Text • 1B • Updated about 24 hours ago • 9.32k • 14
Mechanistic Analysis of Alignment Algorithms in Language Models Paper • 2606.09850 • Published May 9 • 2
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting Paper • 2606.09809 • Published 23 days ago • 4
ECI_{sem}: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives Paper • 2603.20990 • Published 26 days ago • 1
Adaptive Chunking: Optimizing Chunking-Method Selection for RAG Paper • 2603.25333 • Published Mar 26 • 6
$\mathrm{ECI}_{\mathrm{sem}}$: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives Paper • 2603.20990 • Published 26 days ago • 1
LightOn Optical Processing Unit: Scaling-up AI and HPC with a Non von Neumann co-processor Paper • 2107.11814 • Published Jul 25, 2021
Is the Number of Trainable Parameters All That Actually Matters? Paper • 2109.11928 • Published Sep 24, 2021