| Large Language Models Are Human-Level Prompt Engineers Y Zhou*, AI Muresanu*, Z Han*, K Paster, S Pitis, H Chan, J Ba International Conference on Learning Representations (ICLR). 2023, 2022 | 983 | 2022 |
| Unlearnable algorithms for in-context learning A Muresanu, A Thudi, MR Zhang, N Papernot arXiv preprint arXiv:2402.00751, 2024 | 13 | 2024 |
| Benchmarks for Physical Reasoning AI A Melnik, R Schiewer, M Lange, A Muresanu, M Saeidi, A Garg, H Ritter Transactions on Machine Learning Research (TMLR). 2023, 2023 | 8 | 2023 |
| Steering Large Language Models using APE Y Zhou*, AI Muresanu*, Z Han*, K Paster, S Pitis, H Chan, J Ba NeurIPS ML Safety Workshop 2022, 2022 | 5 | 2022 |
| Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation A Sarkar, AI Muresanu, C Blair, A Sharma, RS Trivedi, GK Hadfield arXiv preprint arXiv:2405.19328, 2024 | 1 | 2024 |
| Altared Environments: The Role of Normative Infrastructure in AI Alignment R Trivedi, N Chandak, A Muresanu, S Zhu, A Sarkar, J Leibo, ... Submitted to International Conference on Learning Representations (ICLR). 2025, 2024 | | 2024 |
Keiran PasterUniversity of Toronto, Vector InstituteAdresse e-mail validée de cs.toronto.edu