---

1. On the Proper Treatment of Units in Surprisal Theory
   Annual Meeting of the Association for Computational Linguistics2026-04-30alphaXiv arXiv S2
2. Prefix Parsing is Just Parsing
   Annual Meeting of the Association for Computational Linguistics2026-04-23alphaXiv arXiv S2
3. Faster LLM Inference via Sequential Monte Carlo
   arXiv.org2026-04-17alphaXiv arXiv S2
4. Transducing Language Models
   arXiv.org2026-03-05alphaXiv arXiv S2
5. Ensembling Language Models with Sequential Monte Carlo
   arXiv.org2026-03-05alphaXiv arXiv S2
6. Automating the Analysis and Improvement of Dynamic Programming Algorithms with Applications to Natural Language Processing
   arXiv.org2026-02-20alphaXiv arXiv S2
7. Automating the Analysis of Parsing Algorithms (and other Dynamic Programs)
   arXiv.org2025-12-29alphaXiv arXiv S2
8. Language Models over Canonical Byte-Pair Encodings
   International Conference on Machine Learning2025-06-09alphaXiv arXiv S2
9. Syntactic Control of Language Models by Posterior Inference
   Annual Meeting of the Association for Computational Linguistics2025-06-08alphaXiv arXiv S2
10. Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
    International Conference on Learning Representations2025-04-17alphaXiv arXiv S2
11. Better Estimation of the Kullback-Leibler Divergence Between Language Models
    Neural Information Processing Systems2025-04-14alphaXiv arXiv S2
12. Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling
    arXiv.org2025-04-07alphaXiv arXiv S2
13. From Language Models over Tokens to Language Models over Characters
    International Conference on Machine Learning2024-12-04alphaXiv arXiv S2
14. On the Proper Treatment of Tokenization in Psycholinguistics
    Conference on Empirical Methods in Natural Language Processing2024-10-03alphaXiv arXiv S2