Latest

'I trained three generations of ColQwen3.5, each with more sophisticated optimization than the last. The most optimized version barely beat the previous one on the primary benchmark (+0.0011 nDCG@5). Individual tasks reshuffled substantially, with per-task swings an order of magnitude larger than the aggregate gain.'

'Enterprise AI adoption has reached 88%, yet only 5% of pilots deliver measurable impact. Research from MIT, BCG, and RAND reveals what separates successful implementations from the rest. It's not the technology.'

'A deep dive into my recent research on spatially-grounded document retrieval using ColPali models and OCR bounding boxes, enabling precise region-level retrieval during inference time and without additional training.'

How Snappy evolved from the nextjs-fastapi-colpali template into a vision-first document retrieval system

Quick, practical notes to run the Vidore benchmark smoothly on a single 32GB GPU: dtype, batch size, and common OOM fixes.