| VSE++: Improving Visual-Semantic Embeddings with Hard Negatives F Faghri, DJ Fleet, JR Kiros, S Fidler British Machine Vision Conference (BMVC), 2018 | 1457 | 2018 |
| Technical report on the cleverhans v2.1.0 adversarial examples library N Papernot, F Faghri, N Carlini, I Goodfellow, R Feinman, A Kurakin, ... arXiv preprint arXiv:1610.00768, 2018 | 967* | 2018 |
| Adversarial Spheres J Gilmer, L Metz, F Faghri, SS Schoenholz, M Raghu, M Wattenberg, ... International Conference on Learning Representations (ICLR), Workshop Track, 2018 | 449* | 2018 |
| Adversarial Manipulation of Deep Representations S Sabour, Y Cao, F Faghri, DJ Fleet International Conference on Learning Representations (ICLR), 2016 | 350 | 2016 |
| Adaptive Gradient Quantization for Data-Parallel SGD F Faghri, I Tabrizian, I Markov, D Alistarh, DM Roy, A Ramezani-Kebrya Advances in neural information processing systems (NeurIPS) 33, 3174-3185, 2020 | 86 | 2020 |
| SAM-CLIP: Merging Vision Foundation Models Towards Semantic and Spatial Understanding H Wang, PKA Vasu, F Faghri, R Vemulapalli, M Farajtabar, S Mehta, ... arXiv preprint arXiv:2310.15308, 2023 | 67 | 2023 |
| NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization A Ramezani-Kebrya, F Faghri, I Markov, V Aksenov, D Alistarh, DM Roy Journal of Machine Learning Research 22 (114), 1-43, 2021 | 55* | 2021 |
| A Study of Gradient Variance in Deep Learning F Faghri, D Duvenaud, DJ Fleet, J Ba NeurIPS Workshop on Beyond First Order Methods, Conference on Neural …, 2020 | 20* | 2020 |
| Adversarial robustness through regularization: A second-order approach A Ma, F Faghri, A Farahmand arXiv preprint arXiv:2004.01832, 2020 | 20* | 2020 |
| DataComp-LM: In search of the next generation of training sets for language models J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, S Gadre, H Bansal, E Guha, ... Advances in neural information processing systems (NeurIPS), 2024 | 15* | 2024 |
| MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training PKA Vasu*, H Pouransari*, F Faghri*, R Vemulapalli, O Tuzel Conference on Computer Vision and Pattern Recognition (CVPR), 2024 | 14 | 2024 |
| TiC-CLIP: Continual Training of CLIP Models S Garg, M Farajtabar, H Pouransari, R Vemulapalli, S Mehta, O Tuzel, ... International Conference on Learning Representations (ICLR), 2024 | 11 | 2024 |
| Weight Subcloning: Direct Initialization of Transformers Using Larger Pretrained Ones M Samragh, M Farajtabar, S Mehta, R Vemulapalli, F Faghri, D Naik, ... arXiv preprint arXiv:2312.09299, 2023 | 9 | 2023 |
| Bridging the Gap Between Adversarial Robustness and Optimization Bias F Faghri, S Gowal, C Vasconcelos, DJ Fleet, F Pedregosa, N Le Roux ICLR Workshop on Security and Safety in Machine Learning Systems …, 2021 | 9 | 2021 |
| Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement F Faghri, H Pouransari, S Mehta, M Farajtabar, A Farhadi, M Rastegari, ... International Conference on Computer Vision (ICCV), 2023 | 8 | 2023 |
| RangeAugment: Efficient online augmentation with range learning S Mehta, S Naderiparizi, F Faghri, M Horton, L Chen, A Farhadi, O Tuzel, ... arXiv preprint arXiv:2212.10553, 2022 | 6 | 2022 |
| MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks A Ramezani-Kebrya, I Tabrizian, F Faghri, P Popovski Transactions on Machine Learning Research (TMLR), 2022 | 6 | 2022 |
| Graph based semi-supervised human pose estimation: When the output space comes to help N Pourdamghani, HR Rabiee, F Faghri, MH Rohban Pattern Recognition Letters 33 (12), 1529-1535, 2012 | 4 | 2012 |
| Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models R Vemulapalli, H Pouransari, F Faghri, S Mehta, M Farajtabar, ... International Conference on Machine Learning (ICML), 2024 | 3* | 2024 |
| FastFill: Efficient Compatible Model Update F Jaeckle, F Faghri, A Farhadi, O Tuzel, H Pouransari International Conference on Learning Representations (ICLR), 2023 | 3 | 2023 |
David J FleetGoogle DeepMind; University of Toronto; Vector InstituteVerified email at cs.toronto.edu
