Hahn, Michael

14 publications

ICLR 2026 Automata Learning and Identification of the Support of Language Models Satwik Bhattamishra, Michael Hahn, Varun Kanade

ICLR 2026 Benefits and Limitations of Communication in Multi-Agent Reasoning Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi, Guillaume Rabusseau, Michael Hahn

ICLR 2026 Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning Xinting Huang, Michael Hahn

ICLR 2026 SoftMax Transformers Are Turing-Complete Hongjian Jiang, Michael Hahn, Georg Zetzsche, Anthony Widjaja Lin

ICLR 2026 Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors Mark Rofin, Jalal Naghiyev, Michael Hahn

TMLR 2026 When Does LoRA Reuse Work? Theoretical Limits and Mechanisms for Recycling LoRAs Without Data Access Mei-Yen Chen, Thi Thu Uyen Hoang, Michael Hahn, M. Saquib Sarfraz

ICLR 2025 A Formal Framework for Understanding Length Generalization in Transformers Xinting Huang, Andy Yang, Satwik Bhattamishra, Yash Sarrof, Andreas Krebs, Hattie Zhou, Preetum Nakkiran, Michael Hahn

NeurIPS 2025 Born a Transformer -- Always a Transformer? on the Effect of Pretraining on Architectural Abilities Mayank Jobanputra, Yana Veitsman, Yash Sarrof, Aleksandra Bakalova, Vera Demberg, Ellie Pavlick, Michael Hahn

ICLRW 2025 Emergent Stack Representations in Modeling Counter Languages Using Transformers Utkarsh Tiwari, Aviral Gupta, Michael Hahn

ICML 2025 Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers Alireza Amiri Bavandpour, Xinting Huang, Mark Rofin, Michael Hahn

NeurIPS 2024 InversionView: A General-Purpose Method for Reading Information from Neural Activations Xinting Huang, Madhur Panwar, Navin Goyal, Michael Hahn

ICMLW 2024 InversionView: A General-Purpose Method for Reading Information from Neural Activations Xinting Huang, Madhur Panwar, Navin Goyal, Michael Hahn

NeurIPS 2024 Separations in the Representational Capabilities of Transformers and Recurrent Architectures Satwik Bhattamishra, Michael Hahn, Phil Blunsom, Varun Kanade

NeurIPS 2024 The Expressive Capacity of State Space Models: A Formal Language Perspective Yash Sarrof, Yana Veitsman, Michael Hahn