['ACL 2024 Best Paper Award for "Why are Sensitive Functions Hard for Transformers?", also accepted to ACL 2024.', 'Short paper "On the Emergence of 'Useless' Features in Next Token Predictors" accepted as a spotlight at ICML 2025 Workshop on Assessing and Evaluating World Models.', 'Paper "Vote’n’Rank: Revision of Benchmarking with Social Choice Theory" accepted to EACL 2023.', 'Preprint on required Chain-of-Thought length for algorithmic reasoning in Transformers accepted to ICML 2025.', 'Preprint (Feb 2024) providing theoretical and empirical explanation for Transformers’ difficulty with sensitive functions like Parity.']