MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe Paper โข 2509.18154 โข Published Sep 16, 2025 โข 56
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents Paper โข 2410.10594 โข Published Oct 14, 2024 โข 29
GUICourse: From General Vision Language Models to Versatile GUI Agents Paper โข 2406.11317 โข Published Jun 17, 2024 โข 2
view post Post 2670 Introducing GUICourse! ๐ By leveraging extensive OCR pretraining with grounding ability, we unlock the potential of parsing-free methods for GUIAgent. ๐ Paper: ( GUICourse: From General Vision Language Models to Versatile GUI Agents (2406.11317))๐ Github Repo: (https://github.com/yiye3/GUICourse)๐ Dataset: ( yiye2023/GUIAct) / ( yiye2023/GUIChat) / ( yiye2023/GUIEnv)๐ฏ Model: ( RhapsodyAI/minicpm-guidance) / ( RhapsodyAI/qwen_vl_guidance) 16 replies ยท ๐ฅ 5 5 ๐ 4 4 ๐ 2 2 + Reply