Jul 2026
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
HuyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks, and proposes Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development.
Gengluo Li, Xingyu Wan, Shangpin Peng et al.
· arXiv.org · 7 citations
· ⚡1