Events
Join us at our upcoming events, conferences, and community gatherings.
Upcoming Events
AI Transparency Days 2027
Three-day research hackathon in early 2027 on one shared frame: loss of control through autonomous agents.
Scientific research instead of MVPs — the focus is on open research questions, with promising work continued in a mentoring programme towards publication.
Location: Nuremberg, Germany · Admission: TBD
Exact dates, venue and pricing not yet confirmed — details to follow.
Event details →AI Transparency Conference (AITC 2027)
Three-day international research conference on transparent and human-compatible AI systems. Themes: Detect (Agent Behaviour & Collaboration), Understand (Transparency & Interpretability), Control (AI Control & AI Safety).
Submissions open on 1 December 2026 via OpenReview in three tracks: Main Track (deadline 31 March 2027), Early Track and Autonomous AI Research Track (deadline 31 January 2027). Accepted papers are published in the AI Transparency Journal (AITJ).
Programme, call for papers and registration are published at aitc2027.cc.
Location: Germanisches Nationalmuseum, Nuremberg, Germany · Admission: Registration opening soon
Go to aitc2027.cc →Past Events
AI Transparency Conference (AITC 2026)
Two-day on-site research conference on transparent and human-compatible AI systems. Tracks: Detect (Agent Behaviour), Understand (Interpretability), Control (AI Safety).
Three keynotes, ten paper talks, and two poster sessions across both days, with contributions from researchers across Europe and beyond.
Talk recordings are now online — keynotes and paper talks published with the speakers’ consent.
Location: Nuremberg, Germany · Admission: Free
Conference archive →Lange Nacht der Wissenschaft
When AI agents go haywire! How we can create a safe and autonomous agent world.
We presented our current research activities and described what we can and must do to balance opportunities and risks. 17:00–24:00 in Nuremberg and Erlangen.
Event page →AI Transparency Days
Three-day community event with focused working sessions, talks and hands-on hacking toward transparent & safe AI.
Track 1: AI Governance & AI Control — Developing frameworks, policies, and tools to ensure responsible AI deployment.
Track 2: Mechanistic Interpretability — Hands-on experiments with large AI models, using tools like NNsight and the eDIF cluster.
Event page →