Gritsevskiy, Andrew

2 publications

NeurIPSW 2024 SmileyLlama: Modifying Large Language Models \\for Directed Chemical Space Exploration Joe Cavanagh, Kunyang Sun, Andrew Gritsevskiy, Dorian Bagni, Teresa Head-Gordon, Thomas D. Bannister
NeurIPS 2024 Unelicitable Backdoors via Cryptographic Transformer Circuits Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani, Christian Schroeder de Witt