UI-Genie [NeurIPS 2025] UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents HanXiao1999/UI-Genie-Agent-3B Image-Text-to-Text • 4B • Updated May 29, 2025 • 4 • 5 HanXiao1999/UI-Genie-Agent-7B Image-Text-to-Text • 8B • Updated May 29, 2025 • 3 HanXiao1999/UI-Genie-Agent-16k Preview • Updated Nov 29, 2025 • 111 HanXiao1999/UI-Genie-RM-517k Viewer • Updated Nov 27, 2025 • 473k • 21
DocMark Models and Dataset for CVPR 2025 paper: Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding HanXiao1999/DocMark-Pretrain-2B Image-Text-to-Text • 2B • Updated Jun 23, 2025 • 3 HanXiao1999/DocMark-Pile Viewer • Updated Jun 13, 2025 • 1.3M • 7 • 1 HanXiao1999/DocMark-Instruct Viewer • Updated Jun 16, 2025 • 614k • 10
UI-Genie [NeurIPS 2025] UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents HanXiao1999/UI-Genie-Agent-3B Image-Text-to-Text • 4B • Updated May 29, 2025 • 4 • 5 HanXiao1999/UI-Genie-Agent-7B Image-Text-to-Text • 8B • Updated May 29, 2025 • 3 HanXiao1999/UI-Genie-Agent-16k Preview • Updated Nov 29, 2025 • 111 HanXiao1999/UI-Genie-RM-517k Viewer • Updated Nov 27, 2025 • 473k • 21
DocMark Models and Dataset for CVPR 2025 paper: Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding HanXiao1999/DocMark-Pretrain-2B Image-Text-to-Text • 2B • Updated Jun 23, 2025 • 3 HanXiao1999/DocMark-Pile Viewer • Updated Jun 13, 2025 • 1.3M • 7 • 1 HanXiao1999/DocMark-Instruct Viewer • Updated Jun 16, 2025 • 614k • 10