Running on Zero Agents Featured 96 OvisOCR2 🔎 96 Stream structured Markdown from document images and PDFs.
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities Paper • 2505.02567 • Published May 5, 2025 • 82
Ovis2 Collection Our latest advancement in multi-modal large language models (MLLMs) • 15 items • Updated Mar 25, 2025 • 67