Profiles2020-2026
Ryan Cotterell
ETH Zürich
76Papers
45Last author
92Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers76
- Transformers are Inherently SuccinctAuthor 2 of 3ICLR 2026 · 5 citations
- Transducing Language ModelsAuthor 5 of 7ICLR 2026 · 3 citations
- Characterizing the Expressivity of Local Attention in TransformersAuthor 2 of 2ACL 2026 · 2 citations
- An Algebraic View of the Expressivity of Recurrent Language ModelsAuthor 2 of 3ICML 2026 · 1 citation
- Causally Evaluating the Learnability of Formal Language TasksAuthor 6 of 6ICML 2026
- On the Proper Treatment of Units in Surprisal TheoryAuthor 4 of 6ACL 2026
- Post-Training Language Models for Crosslingual ConsistencyAuthor 4 of 6ICML 2026
- Probing for Reading TimesAuthor 7 of 7ACL 2026
- Understanding the Parameter Space Geometry of Transformers Encoding Boolean FunctionsAuthor 5 of 5ICML 2026
- Characterizing the Expressivity of Fixed-Precision Transformer Language ModelsAuthor 2 of 2NeurIPS 2025 · 18 citations
- Better Estimation of the Kullback-Leibler Divergence Between Language ModelsAuthor 3 of 3NeurIPS 2025 · 12 citations
- Information Locality as an Inductive Bias for Neural Language ModelsAuthor 6 of 6ACL 2025 · 6 citations
- The Harmonic Structure of Information ContoursAuthor 7 of 10ACL 2025 · 6 citations
- Are Language Models Efficient Reasoners? A Perspective from Logic ProgrammingAuthor 7 of 8NeurIPS 2025 · 4 citations
- A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading BehaviorAuthor 5 of 6ACL 2025 · 2 citations
- The Foundations of Tokenization: Statistical and Computational ConcernsAuthor 6 of 7ICLR 2025 · 1 citation
- Variational Best-of-N AlignmentAuthor 4 of 4ICLR 2025 · 1 citation
- Controllable Context Sensitivity and the Knob Behind ItAuthor 7 of 9ICLR 2025
- Gumbel Counterfactual Generation From Language ModelsAuthor 4 of 4ICLR 2025
- How Persuasive Is Your Context?Author 4 of 4EMNLP 2025
- Training Neural Networks as Recognizers of Formal LanguagesAuthor 5 of 7ICLR 2025
- Activation Scaling for Steering and Interpreting Language ModelsAuthor 5 of 7EMNLP Findings 2024 · 5 citations
- What Do Language Models Learn in Context? The Structured Task HypothesisAuthor 4 of 4ACL 2024 · 5 citations
- Context versus Prior Knowledge in Language ModelsAuthor 6 of 7ACL 2024 · 3 citations
- Generalized Measures of Anticipation and Responsivity in Online Language ProcessingAuthor 3 of 3EMNLP Findings 2024 · 2 citations
- On Efficiently Representing Regular Languages as RNNsAuthor 4 of 4ACL Findings 2024 · 1 citation
- Efficiently Computing Susceptibility to Context in Language ModelsAuthor 4 of 4EMNLP Findings 2024
- On the Representational Capacity of Neural Language Models with Chain-of-Thought ReasoningAuthor 4 of 4ACL 2024
- Reverse-Engineering the ReaderAuthor 5 of 5EMNLP 2024
- What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular LanguagesAuthor 9 of 11ACL 2024
Showing the 30 most recent indexed papers.
