June 5–6, 2026 · Nuremberg, Germany

AI Transparency Conference

cosponsored by

Keynote Speakers

Vera Schmitt

Research group lead
XplaiNLP Group, TU Berlin

Joel Z. Leibo

Senior staff research scientist
Google DeepMind

The AI Transparency Conference is an international research conference focused on advancing transparent and human-compatible AI systems. It brings together researchers working on interpretability, AI safety, control, and governance.

Designed as an on-site event, the conference prioritizes depth and shared understanding. It is aimed at PhD students, postdoctoral researchers, faculty, and research institutes. Attendance is free of charge. Please register to secure your spot.

The conference addresses three core themes

Detect

Agent Behaviour & Collaboration

Methods for observing, measuring, and characterizing the behavior of autonomous AI agents, including multi-agent interactions and emergent collaboration patterns.

Understand

Transparency & Interpretability

Techniques for making AI decision-making processes legible to humans — from mechanistic interpretability to explanation interfaces and audit tools.

Control

AI Control & AI Safety

Frameworks and mechanisms for maintaining meaningful human oversight of AI systems, including alignment verification, safety testing, and governance protocols.

Call for Submissions

We invite submissions for papers and posters. All submissions undergo double-blind peer review. Accepted papers will be published in a peer-reviewed journal.

The entire submission and review process is handled through OpenReview. In line with our commitment to maximum transparency, all reviews, discussions, and decisions will be openly accessible on the platform.

Important Dates

Submission Opens (Extended Abstract)	February 23, 2026 (00:00 CET)
Submission Deadline (Extended Abstract)	April 30, 2026 (23:59 CET)
Author Notification	May 07, 2026 (23:59 CET)
Camera-Ready Deadline	May 15, 2026 (23:59 CET)
Conference	June 05/06, 2026

Author Guidelines Contact for Questions

As AI systems become more capable and autonomous, the need for transparency has never been greater. Understanding how these systems behave, interpret information, and can be controlled is essential for building AI that is safe and aligned with human values.

The AI Transparency Conference provides a dedicated space for researchers to share findings, challenge ideas, and shape the future of transparent AI — together.