Hadi Salman
Massachusetts Institute of Technology
H-index: 20
North America-United States
Top articles of Hadi Salman
Extra Training Provides a Strong Baseline for CLIP
2023/12/12
The journey, not the destination: How data guides diffusion models
arXiv preprint arXiv:2312.06205
2023/12/11
Your CLIP Model Might Be Undertrained
2023/10/13
Rethinking backdoor attacks
2023/7/3
Raising the cost of malicious ai-powered image editing
arXiv preprint arXiv:2302.06588
2023/2/13
A data-based perspective on transfer learning
2023
3db: A framework for debugging computer vision models
Advances in Neural Information Processing Systems
2022/12/6
When does bias transfer in transfer learning?
arXiv preprint arXiv:2207.02842
2022/7/6
Hadi Salman
H-Index: 10
Saachi Jain
H-Index: 3
Andrew Ilyas
H-Index: 15
Logan Engstrom
H-Index: 15
Eric Wong
H-Index: 8
Causalcity: Complex simulations with agency for causal discovery and reasoning
2022/6/28
Missingness bias in model debugging
arXiv preprint arXiv:2204.08945
2022/4/19
FFCV: Accelerating Training by Removing Data Bottlenecks
2023
Certified patch robustness via smoothed vision transformers
2022
Unadversarial examples: Designing objects for robust vision
Advances in Neural Information Processing Systems
2021/12/6
Randomized smoothing of all shapes and sizes
2020/11/21
Improved image wasserstein attacks and defenses
International Conference on Learning Representations - Workshop
2020/4/26
Hadi Salman
H-Index: 10
Denoised smoothing: A provable defense for pretrained classifiers
Advances in Neural Information Processing Systems
2020
Do adversarially robust imagenet models transfer better?
Advances in Neural Information Processing Systems
2020