Publications

1. Quantifying evolutionary novelty and design efficiency in generative genome design Black JR, Maiwald A, Pannu J, Crook OM (2026) Under review. Mentioned in The New York Times.
2. Decode-gLM: Tools to Interpret, Audit, and Steer Genomic Language Models Maiwald A*, Jedryszek P, Draye F, Schoelkopf B, Morris GM, Crook OM (2025) bioRxiv. doi:10.1101/2025.10.31.685860
3. Tracing engineered biothreats with AI forensics: Five steps to improve attribution Maiwald A*, Franz A*, Crook O (2025) Bulletin of the Atomic Scientists. Selected for the Bulletin's best biosecurity coverage of 2025.
4. Securing Dual-Use Pathogen Data of Concern Bloomfield D, Hanke MS, Maiwald A, Black JRM, Webster T, Hernandez-Boussard T, Berke A, Crook OM, Pannu J (2025) NeurIPS 2025 Workshop on Biosecurity Safeguards for Generative AI. OpenReview
5. Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning Black JRM, Hanke MS, Maiwald A, Hernandez-Boussard T, Crook OM, Pannu J (2025) NeurIPS 2025 Workshop on Biosecurity Safeguards for Generative AI. OpenReview
6. Decoding the physicochemical basis of taxonomy preferences in protein design models Dillon L, Maiwald A, Crook O (2025) bioRxiv. doi:10.1101/2025.10.21.683350
7. Dancing robots: aesthetic engagement is shaped by stimulus and knowledge cues to human animacy Darda KM*, Maiwald A*, Raghuram T, Cross ES (2024) Frontiers in Human Neuroscience, 18:1413066. doi:10.3389/fnhum.2024.1413066

* First author. See also my Google Scholar profile.