Numerous publications accepted at the ICML 2026

Numerous scientific publications from our department were accepted at the the International Conference on Machine Learning (ICML)
Congratulations to all authors!

• “Provably Learning Attention with Queries” by
  Satwik Bhattamishra, Kulin Shah, Michael Hahn, Varun Kanade.
• “Discovering Interpretable Algorithms by Decompiling Transformers to RASP” by
  Xinting Huang, Aleksandra Bakalova, Satwik Bhattamishra, William Merrill, Michael Hahn.
• “A Framework for Understanding Learnability in Transformers” by
  Blanka Kövér, Alexandra Butoi, Anej Svete, Michael Hahn, Ryan Cotterell.
• “On the Ability of Transformers to Verify Plans” by
  Yash Sarrof, Yupei Du, Katharina Stein, Alexander Koller, Sylvie Thiebaux, Michael Hahn.
• “GRPO is secretly a Process Reward Model” by
  Michael Sullivan, Alexander Koller.
• “How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning” by
  Entang Wang, Yiwei Wang, Aleksandra Bakalova, Michael Hahn.