Show all

2024

6.

Munir, Mustafa; Modi, Saloni; Cooper, Geffen; Kim, Huntae; Marculescu, Radu

Three Decades of Low Power: From Watts to Wisdom Journal Article

In: IEEE Access, vol. 12, pp. 19447-19458, 2024.

Links | BibTeX | Tags: Dynamic networks, Edge AI, Featured, Graph Neural Network

2023

5.

Li, Guihong; Bhardwaj, Kartikeya; Yang, Yuedong; Marculescu, Radu

TIPS: Topologically Important Path Sampling for Anytime Neural Networks Conference

International Conference on Machine Learning (ICML), 2023.

Links | BibTeX | Tags: Dynamic networks, Edge AI, Featured, Internet of Things, Model Compression & Optimization, Neural Architecture Search

4.

Li, Guihong; Yang, Yuedong; Bhardwaj, Kartikeya; Marculescu, Radu

ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients Conference

International Conference on Learning Representations (ICLR), 2023.

Links | BibTeX | Tags: Edge AI, Featured, Neural Architecture Search

2021

3.

Bhardwaj, Kartikeya.; Li, Guihong.; Marculescu, Radu.

How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections? Conference

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Links | BibTeX | Tags: Featured, Model Compression & Optimization, Neural Architecture Search

2020

2.

Krishnakumar, A.; Arda, S. E.; Goksoy, A. A.; Mandal, S. K.; Ogras, U. Y.; Sartor, A. L.; Marculescu, R.

Runtime Task Scheduling Using Imitation Learning for Heterogeneous Many-Core Systems Journal Article

In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 39, no. 11, pp. 4064-4077, 2020.

Links | BibTeX | Tags: Embedded Systems, Featured, Systems

2019

1.

Bhardwaj, Kartikeya; Lin, Ching-Yi; Sartor, Anderson; Marculescu, Radu

Memory-and communication-aware model compression for distributed deep learning inference on iot Journal Article

In: ACM Transactions on Embedded Computing Systems (TECS), vol. 18, no. 5s, pp. 1–22, 2019.

Links | BibTeX | Tags: Edge AI, Featured, Model Compression & Optimization, Networks