#NaViT

'Baidu releases PaddleOCR-VL 0.9B, combining a NaViT-style native-resolution encoder with ERNIE-4.5-0.3B to deliver fast, accurate end-to-end parsing of multilingual documents into structured Markdown and JSON.'

'Alibaba's Ovis2.5 (9B and 2B) advances multimodal AI with a native-resolution vision transformer and an optional thinking mode, achieving top scores for open-source models under 40B and improved OCR and chart understanding.'