2 21 4

Fangzhi Xu

xufangzhi

http://xufangzhi.github.io

AI & ML interests

Natural Language Processing, Large Language Models, Neural Symbolic

Recent Activity

upvoted a paper 1 day ago

Could Thinking Multilingually Empower LLM Reasoning?

updated a collection 6 days ago

Genius

updated a dataset 6 days ago

xufangzhi/OpenHermes_48K_train

View all activity

Organizations

xufangzhi's activity

upvoted a paper 1 day ago

Could Thinking Multilingually Empower LLM Reasoning?

Paper • 2504.11833 • Published 6 days ago • 22

updated a collection 6 days ago

Genius

Collection

The series of models trained with Genius • 5 items • Updated 6 days ago • 1

updated 2 datasets 6 days ago

xufangzhi/OpenHermes_48K_train

Viewer • Updated 6 days ago • 48k • 42

xufangzhi/Magpie_reasoning_150K_train

Viewer • Updated 6 days ago • 150k • 45

updated 2 models 6 days ago

xufangzhi/Genius_OpenHermes-32K_LLaMA3.1-8B-Instruct

Updated 6 days ago • 18

xufangzhi/Genius_Magpie-25K_LLaMA3.1-8B-Instruct

Updated 6 days ago • 16

upvoted a paper 6 days ago

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning

Paper • 2504.08672 • Published 11 days ago • 53

commented a paper 6 days ago

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning

Paper • 2504.08672 • Published 11 days ago • 53 •

upvoted a paper 7 days ago

Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

Paper • 2504.10127 • Published 8 days ago • 17

authored a paper 8 days ago

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning

Paper • 2504.08672 • Published 11 days ago • 53

updated a collection 8 days ago

Genius

Collection

The series of models trained with Genius • 5 items • Updated 6 days ago • 1

published 2 datasets 8 days ago

xufangzhi/OpenHermes_48K_train

Viewer • Updated 6 days ago • 48k • 42

xufangzhi/Magpie_reasoning_150K_train

Viewer • Updated 6 days ago • 150k • 45

updated a collection 8 days ago

Genius

Collection

The series of models trained with Genius • 5 items • Updated 6 days ago • 1

published 2 models 8 days ago

xufangzhi/Genius_OpenHermes-32K_LLaMA3.1-8B-Instruct

Updated 6 days ago • 18

xufangzhi/Genius_Magpie-25K_LLaMA3.1-8B-Instruct

Updated 6 days ago • 16

authored a paper 29 days ago

MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving

Paper • 2503.16905 • Published Mar 21 • 54

upvoted a paper 30 days ago

MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization

Paper • 2503.16874 • Published Mar 21 • 45