 |
 Unique Hard Attention: A Tale of Two SidesAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Looped ReLU MLPs May Be All You Need as Practical Programmable ComputersInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |
 Training Neural Networks as Recognizers of Formal LanguagesInternational Conference on Learning Representations (ICLR), 2024 |
 How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Mechanistic?BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2024 |
 Fundamental Limitations on Subquadratic Alternatives to TransformersInternational Conference on Learning Representations (ICLR), 2024 |
 |
 What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular LanguagesAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
