Seguir
Kristian Georgiev
Kristian Georgiev
Dirección de correo verificada de mit.edu - Página principal
Título
Citado por
Citado por
Año
Trak: Attributing model behavior at scale
SM Park, K Georgiev, A Ilyas, G Leclerc, A Madry
arXiv preprint arXiv:2303.14186, 2023
1292023
Privacy induces robustness: Information-computation gaps and sparse mean estimation
K Georgiev, S Hopkins
Advances in neural information processing systems 35, 6829-6842, 2022
30*2022
On the convergence theory of debiased model-agnostic meta-reinforcement learning
A Fallah, K Georgiev, A Mokhtari, A Ozdaglar
Advances in Neural Information Processing Systems 34, 3096-3107, 2021
292021
Rethinking backdoor attacks
A Khaddaj, G Leclerc, A Makelov, K Georgiev, H Salman, A Ilyas, A Madry
International Conference on Machine Learning, 16216-16236, 2023
212023
The journey, not the destination: How data guides diffusion models
K Georgiev, J Vendrow, H Salman, SM Park, A Madry
arXiv preprint arXiv:2312.06205, 2023
172023
Implicit bias of linear equivariant networks
H Lawrence, K Georgiev, A Dienes, BT Kiani
arXiv preprint arXiv:2110.06084, 2021
162021
Contextcite: Attributing model generation to context
B Cohen-Wang, H Shah, K Georgiev, A Madry
Advances in Neural Information Processing Systems 37, 95764-95807, 2025
112025
Attribute-to-delete: Machine unlearning via datamodel matching
K Georgiev, R Rinberg, SM Park, S Garg, A Ilyas, A Madry, S Neel
arXiv preprint arXiv:2410.23232, 2024
22024
Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection
S Jain, K Hamidieh, K Georgiev, A Ilyas, M Ghassemi, A Madry
arXiv preprint arXiv:2406.16846, 2024
2*2024
Data Attribution: From Classifiers to Generative Models
K Georgiev
Massachusetts Institute of Technology, 2023
2023
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–10