Safactory: A Scalable Agentic Model Factory for Trustworthy Autonomous Intelligence，Including open-source training dataset and small-size model.
AI & ML interests
None defined yet.
Recent Activity
Papers
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
-
AI45Research/SafeWork-R1
Image-Text-to-Text • 73B • Updated • 9 • 5 -
AI45Research/SafeWork-R1-Qwen2.5VL-7B
Image-Text-to-Text • 8B • Updated • 55 • 1 -
AI45Research/SafeWork-R1-InternVL3-78B
Image-Text-to-Text • 78B • Updated • 5 • 1 -
AI45Research/SafeWork-R1-DeepSeek-70B
Image-Text-to-Text • 71B • Updated • 4
A Diagnostic Guardrail Framework for AI Agent Safety and Security
-
AI45Research/AgentDoG-Qwen3-4B
Text Classification • 4B • Updated • 445 • 23 -
AI45Research/AgentDoG-FG-Qwen3-4B
Text Classification • 4B • Updated • 144 • 9 -
AI45Research/AgentDoG-Qwen2.5-7B
Text Classification • 8B • Updated • 29 • 10 -
AI45Research/AgentDoG-FG-Qwen2.5-7B
Text Classification • 8B • Updated • 21 • 8
Safactory: A Scalable Agentic Model Factory for Trustworthy Autonomous Intelligence，Including open-source training dataset and small-size model.
A Diagnostic Guardrail Framework for AI Agent Safety and Security
-
AI45Research/AgentDoG-Qwen3-4B
Text Classification • 4B • Updated • 445 • 23 -
AI45Research/AgentDoG-FG-Qwen3-4B
Text Classification • 4B • Updated • 144 • 9 -
AI45Research/AgentDoG-Qwen2.5-7B
Text Classification • 8B • Updated • 29 • 10 -
AI45Research/AgentDoG-FG-Qwen2.5-7B
Text Classification • 8B • Updated • 21 • 8
-
AI45Research/SafeWork-R1
Image-Text-to-Text • 73B • Updated • 9 • 5 -
AI45Research/SafeWork-R1-Qwen2.5VL-7B
Image-Text-to-Text • 8B • Updated • 55 • 1 -
AI45Research/SafeWork-R1-InternVL3-78B
Image-Text-to-Text • 78B • Updated • 5 • 1 -
AI45Research/SafeWork-R1-DeepSeek-70B
Image-Text-to-Text • 71B • Updated • 4