Fartash Faghri
Orcid: 0000-0001-5975-5158
According to our database1,
Fartash Faghri
authored at least 23 papers
between 2012 and 2023.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2023
Weight subcloning: direct initialization of transformers using larger pretrained ones.
CoRR, 2023
Label-efficient Training of Small Task-specific Models by Leveraging Vision Foundation Models.
CoRR, 2023
CoRR, 2023
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding.
CoRR, 2023
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
2022
Trans. Mach. Learn. Res., 2022
APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations.
CoRR, 2022
2021
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization.
J. Mach. Learn. Res., 2021
2020
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
2019
NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization.
CoRR, 2019
2018
Proceedings of the 6th International Conference on Learning Representations, 2018
Proceedings of the British Machine Vision Conference 2018, 2018
2017
2016
Proceedings of the 4th International Conference on Learning Representations, 2016
2012
Graph based semi-supervised human pose estimation: When the output space comes to help.
Pattern Recognit. Lett., 2012