Marika NiihoriWe are delighted to share that seven papers from the van der Schaar Lab have been accepted across multiple workshops at the International Conference on Learning Representations (ICLR) 2026, taking place in Rio de Janeiro.
In addition to our papers accepted to the ICLR 2026 main conference track, these workshop acceptances further highlight the breadth and depth of the lab’s research contributions this year.
Our workshop papers span agent verification, steganographic reasoning, and autoregressive modelling – reflecting cutting-edge research advancing the development of robust and deployable AI systems.
Accepted workshop papers:
- GLEAN: Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification
Yichi Zhang, Nabeel Seedat, Yinpeng Dong, Peng Cui, Jun Zhu, Mihaela van der Schaar
Accepted at ICLR 2026 Workshops: Trustworthy AI, VerifAI-2, AIWILD, Reliable Autonomy - A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Usman Anwar, Julianna Piskorz, David D. Baek, David Demitri Africa, Jim Weatherall, Max Tegmark, Christian Schroeder de Witt, Mihaela van der Schaar, David Krueger
Accepted at ICLR 2026 Workshops: Trustworthy AI, AIWILD - Tiny Autoregressive Recursive Models
Paulius Rauba, Claudio Fanconi, Mihaela van der Schaar
Accepted at ICLR 2026 Workshop: LIT, RSI - Learning Reasoning Reward Models from Expert Demonstration via Inverse Reinforcement Learning
Claudio Fanconi, Nicolás Astorga, Mihaela van der Schaar
Accepted at ICLR 2026 Workshop: LLM Reasoning
Congratulations to the authors and all co-authors.
If you will be attending ICLR 2026, we would be very glad to connect.
