Numerous papers accepted at ICLR 2026

Numerous papers of our department were accepted at the the International Conference on Learning Representations (ICLR) 2026.
Congratulations to all authors!

• “Automata Learning and Identification of the Support of Language Models”
  By Satwik Bhattamishra, Michael Hahn, Varun Kanade
• “Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation.”
  By  Yasser Hamidullah, Koel Dutta Chowdury, Yusser Al-Ghussin, Shakib Yazdani, Cennet Oguz, Josef van Genabith, Cristina España-Bonet
• “Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning”
  By  Xinting Huang, Michael Hahn
• “Softmax Transformers are Turing-Complete”
  By  Hongjian Jiang, Michael Hahn, Georg Zetzsche, Anthony Widjaja Lin
• “Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors”
  By  Mark Rofin, Jalal Naghiyev, Michael Hahn
• “Benefits and Limitations of Communication in Multi-Agent Reasoning”
  By  Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi, Guillaume Rabusseau, Michael Hahn
• “Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?”
  By  Yifan Wang, Mayank Jobanputra, Ji-Ung Lee, Soyoung Oh, Isabel Valera, Vera Demberg