Hugging Face's logo
Activity Feed

AI & ML interests

AI Safety, AI alignment

Recent Activity
rank-and-file  updated a dataset about 12 hours ago
aisa-group/PostTrainBench-Trajectories
hrdkbhatnagar  updated a dataset about 13 hours ago
aisa-group/PostTrainBench-Trajectories
imadreamerboy  updated a collection about 1 month ago
Agent Trajectories
View all activity

Papers

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

View all Papers

Organization Card
Community About org cards

ELLIS Institute Tübingen

AI Safety and Alignment Group

AI safety · alignment · evaluation

The AI Safety and Alignment Group is based at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems. This Hub hosts our public datasets and trajectory releases for work on AI-agent evaluation, safety, and alignment.

Research projects

Project Paper Dataset
ResearchArena arXiv Trajectories
PostTrainBench arXiv Trajectories
InferenceBench arXiv Trajectories
Instrumental Choices arXiv Agent traces
Evaluation awareness arXiv EvalAwareBench

Browse all GitHub repositories, follow the group on Substack, or visit the group page.

Collections 2

models 0

None public yet