A free, one-day workshop on technical AI safety organized by the Oxford Martin AI Governance Initiative and Noeon Research. TAIS welcomes attendees from all backgrounds regardless of prior research experience, with participants from academia, industry, and policy. Third iteration following TAIS 2024 and 2025.
Open calls for papers
Workshops, conferences, and fellowships with currently-open application deadlines. Sorted by deadline, soonest first.
Workshop at ICML 2026 exploring pluralistic AI alignment with diversity of human values. Addresses how to integrate diverse perspectives into AI alignment frameworks, examining multi-objective approaches and human-AI interaction workflows across communities. Welcomes interdisciplinary research from machine learning, HCI, philosophy, social sciences, and policy studies.
Third annual mechanistic interpretability workshop at ICML focusing on developing principled methods to analyze and understand neural network internals. The workshop addresses the challenge of understanding model decision-making mechanisms to better predict behavior and detect potential issues. Organized by researchers from Google DeepMind, Harvard, Northeastern, Imperial College London, Oxford, and other leading institutions.