I am a PhD student at the Univeristy of Texas at Austin with a focus on efficient deep learning and model compression. I'm lucky to work with my advisor, Diana Marculescu, and fellow colleagues in the EnyAC group.
News
Internship at Meta Completed
August 11, 2023
I had the pleasure of working with Xiao Sun and Dhruv Choudhary at Meta and will continue to work with them as a Part-Time Researcher.
Evol-Q Accepted to ICCV 2023!
August 1, 2023
Our paper titled Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers will be presented in Paris. Many congrats to my co-authors, Dibakar Gope, and my advisor, Diana Marculescu.
Publications
Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
Natalia Frumkin, Dibakar Gope, Diana Marculescu
ICCV, 2023
MobileTL: On-device Transfer Learning with Inverted Residual Blocks
Hung-Yueh Chiang, Natalia Frumkin, Feng Liang, Diana Marculescu
AAAI, 2023
RL-Tune: A Deep Reinforcement Learning Assisted Layer-wise Fine-Tuning Approach for Transfer Learning
Tanvir Mahmud, Natalia Frumkin, Diana Marculescu
ICML Pre-Training Workshop, 2022
CNN-Based Indoor Occupant Localization via Active Scene Illumination
Jinyuan Zhao, Natalia Frumkin, Prakash Ishwar, Janusz Konrad
ICIP 2019
Privacy-Preserving Indoor Localization via Active Scene Illumination
Jinyuan Zhao, Natalia Frumkin, Janusz Konrad, Prakash Ishwar
CVPR Workshop, 2018
Work Experience
Meta
Research Scientist Intern
Summer 2023
Arm Research
Research Intern
Summer 2022
Advanced Micro Devices
Research Intern
Summer 2021
Los Alamos National Labs
Supercomputing Intern
Summer 2020
Red Hat
AI/Data Science Intern
Summer 2018
