2 25 4

Fangzhi Xu

xufangzhi

http://xufangzhi.github.io

AI & ML interests

Natural Language Processing, Large Language Models, Neural Symbolic

Recent Activity

upvoted a paper 5 days ago

A Controllable Examination for Long-Context Language Models

upvoted a paper 5 days ago

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

authored a paper 12 days ago

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

View all activity

Organizations

xufangzhi's activity

upvoted 2 papers 5 days ago

A Controllable Examination for Long-Context Language Models

Paper • 2506.02921 • Published 6 days ago • 31

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Paper • 2506.03143 • Published 5 days ago • 39

authored a paper 12 days ago

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

Paper • 2505.19897 • Published 14 days ago • 101

upvoted a paper 12 days ago

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

Paper • 2505.19897 • Published 14 days ago • 101

upvoted a paper 20 days ago

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

Paper • 2505.13227 • Published 20 days ago • 45

upvoted a paper about 2 months ago

Could Thinking Multilingually Empower LLM Reasoning?

Paper • 2504.11833 • Published Apr 16 • 28

updated a collection about 2 months ago

Genius

Collection

The series of models trained with Genius • 5 items • Updated Apr 16 • 1

updated 2 datasets about 2 months ago

xufangzhi/OpenHermes_48K_train

Viewer • Updated Apr 16 • 48k • 35

xufangzhi/Magpie_reasoning_150K_train

Viewer • Updated Apr 16 • 150k • 39

updated 2 models about 2 months ago

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

Updated Apr 16 • 6

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

Updated Apr 16 • 3

upvoted a paper about 2 months ago

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

Paper • 2504.08672 • Published Apr 11 • 55

commented a paper about 2 months ago

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

Paper • 2504.08672 • Published Apr 11 • 55 •

upvoted a paper about 2 months ago

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

Paper • 2504.10127 • Published Apr 14 • 17

authored a paper about 2 months ago

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

Paper • 2504.08672 • Published Apr 11 • 55

updated a collection about 2 months ago

Genius

Collection

The series of models trained with Genius • 5 items • Updated Apr 16 • 1

published 2 datasets about 2 months ago

xufangzhi/OpenHermes_48K_train

Viewer • Updated Apr 16 • 48k • 35

xufangzhi/Magpie_reasoning_150K_train

Viewer • Updated Apr 16 • 150k • 39

updated a collection about 2 months ago

Genius

Collection

The series of models trained with Genius • 5 items • Updated Apr 16 • 1