Publications

11 papers  ·  CoLM · SIGIR · AAAI · CAMLIS · MALWARE
// 2025
2025 arXiv
SEQR: Secure and Efficient QR-based LoRA Routing
William Fleshman, Benjamin Van Durme
2025 arXiv
LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks
William Fleshman, Benjamin Van Durme
2025 CoLM
SpectR: Dynamically Composing LM Experts with Spectral Routing
William Fleshman, Benjamin Van Durme
2025 SIGIR
RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation
William Fleshman, Benjamin Van Durme
// 2024
2024 arXiv
RE-Adapt: Reverse Engineered Adaptation of Large Language Models
William Fleshman, Benjamin Van Durme
2024 CAMLIS
AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees
William Fleshman, Aleem Khan, Marc Marone, Benjamin Van Durme
// 2023
2023 arXiv
Toucan: Token-Aware Character Level Language Modeling
William Fleshman, Benjamin Van Durme
// 2021
2021 AAAI
Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detection
Raff, E., Fleshman, W., Zak, R., Anderson, H. S., Filar, B., McLean, M.
2021 NSA TNW
Deception and the Strategy of Influence
B., B., Fleshman, W., H., K., Kaliszewski, R., R.S.  —  NSA's The Next Wave, Vol. 23 No. 1
// 2019
2019 AAAI-AICS
Non-Negative Networks Against Adversarial Attacks
Fleshman, W., Raff, E., Sylvester, J., Forsyth, S., McLean, M.
// 2018
2018 MALWARE
Static Malware Detection & Subterfuge: Quantifying the Robustness of Machine Learning and Current Anti-Virus
Fleshman, W., Raff, E., Zak, R., McLean, M., Nicholas, C.