OpenSafetyLab

non-profit

https://open-trust-lab.vercel.app

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

adwardlee authored a paper about 17 hours ago

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

adwardlee submitted a paper about 21 hours ago

Toward Efficient Agents: Memory, Tool learning, and Planning

adwardlee submitted a paper 6 days ago

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

View all activity

Organization Card

Community About org cards

Edit this README.md markdown file to author your organization card.

spaces 2

Salad Bench Leaderboard

Display benchmark results for models across different taxonomies

models 3

OpenSafetyLab/MD-Judge-v0_2-internlm2_7b

Text Generation • 8B • Updated Mar 8, 2025 • 550 • 17

OpenSafetyLab/ImageGuard

Image-to-Text • Updated Jan 19, 2025 • 6

OpenSafetyLab/MD-Judge-v0.1

Text Generation • 7B • Updated May 20, 2024 • 932 • • 18

datasets 3

OpenSafetyLab/t2i_safety_dataset

Updated Aug 5, 2025 • 322

OpenSafetyLab/t2isafety_evaluation

Preview • Updated Feb 10, 2025 • 28

OpenSafetyLab/Salad-Data

Viewer • Updated Mar 29, 2024 • 30.4k • 823 • 26