TU Darmstadt & RIKEN-AIP Joint Workshop
Online joint workshop of RIKEN-AIP and TU Darmstadt's UKP Lab with research talks on LLM interpretability, AI oversight, agents and ML.
- When
- Tue, October 6, 2026 · 16:00–19:00 JST
- Where
- Online
- Organizer
- RIKEN Center for Advanced Intelligence Project
- Language
- EN
- Source
- Doorkeeper
Summary
RIKEN-AIP and the UKP Lab at TU Darmstadt hold a three-hour online joint workshop on October 6, 2026, from 16:00 to 19:00 JST (9:00 to 12:00 UTC+2). After short introductions to both labs by Iryna Gurevych and Masashi Sugiyama, researchers from each institute give a series of talks.
Topics include complementary human-AI intelligence, evaluation and oversight of increasingly capable AI systems, AI and automation in cybersecurity, linear representations in LLM interpretability, post-training dependable agents for conflicting evidence and long-term memory, exploration and test-time scaling via variational learning, and geometry-preserving machine learning for Hamiltonian dynamics.
About the community
RIKEN-AIP runs public research events such as seminars and joint workshops with partner universities abroad, aimed at AI and machine learning researchers, students of the field and practitioners following current research. Sessions are typically academic talks delivered in English, often online.
#machine-learning#llm#ai-safety#interpretability#ai-agents#research#academic-workshop#ai#online