Samir Khaki
About Me
Engineers live their lives considering the ‘what-ifs’ of applied science, with the primary goal being to improve life. This mindset begins with asking: How do things work and can I make them better?
As a researcher and engineer, I can appreciate the complexity and depth required to answer these questions. My passion stems from an innate drive to ‘look beyond what is’.
Research Interests
- Efficient Deep Learning: efficient inferencing, knowledge/data distillation, model compression
- Computer Vision: image recognition, image generation, foundation models
- Machine Learning: meta-learning, continual learning, contrastive learning
News
| [Jan. 2024] | My paper on efficient model compression for transformers is accepted to ICLR 2024. |
| [Dec. 2023] | My paper on efficient probabilistic contrastive learning is accepted to ICASSP 2024. |
| [Jul. 2023] | My paper on dataset distillation is accepted to ICCV 2023. |
| [May 2023] | My paper on Frequency-based Model Compression is accepted to ECV-CVPR 2023. |
Recent Publications
* Equal Contribution
-
ICLR
International Conference on Learning Representations (ICLR), 2024. -
ICASSP
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. -
ICCV
IEEE/CVF International Conference on Computer Vision (ICCV), 2023. -
CVPR-ECV
IEEE/CVF Conference on Computer Vision and Pattern Recognition: Efficient Computer Vision Workshop (CVPR-ECV), 2023. -
Arxiv
Arxiv Pre-Print, 2023.
See full publication list on Google Scholar
Industry Positions
- IBM [May 2022 - Ongoing]: Machine Learning Engineer
- Amazon [May 2023 - Sept. 2023] Software Development Engineer
Services
Conference Reviewers
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021-2024 European Conference on Computer Vision (ECCV) 2022
Powered by Jekyll and Minimal Light theme.