Zhipu AI and Tsinghua University introduce GLM-OCR, a compact 0.9B parameter multimodal model for document understanding. It handles mixed layouts, tables, and formulas with 50% faster throughput via Multi-Token Prediction, aiming to balance quality with lower computational cost. https://www.marktechpost.com/2026/03/15/zhipu-ai-introduces-glm-ocr-a-0-9b-multimodal-ocr-model-for-document-parsing-and-key-information-extraction-kie/ #AIagent #AI #GenAI #AIResearch #ZhipuAI