AI Research Jun 3, 2026
Direct Preference Optimization Beyond Chatbots
Research shows Direct Preference Optimization can fix text degeneration in OCR models, cutting repetition-loop failures by an average 59.4 percent across five model families after fine-tuning.
AI Research May 22, 2026
Specialization Beats Scale: A Strategic Variable Most AI Procurement Decisions Overlook
Dharma-AI research shows a specialized 3-billion-parameter model beat all commercial frontier APIs on structured OCR, scoring 0.911 versus 0.833 for Claude Opus 4.6 at about 52x lower cost.
Open Source AI May 18, 2026
PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
PaddleOCR 3.5 adds Hugging Face Transformers as a document parsing inference backend, letting PP-OCRv5 and PaddleOCR-VL 1.5 models run wherever the engine parameter is set.