Guihong Li

According to our database, Guihong Li authored at least 19 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities.

Guihong Li, Duc Hoang, Kartikeya Bhardwaj, Ming Lin, Zhangyang Wang, Radu Marculescu

IEEE Trans. Pattern Anal. Mach. Intell., December, 2024

Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation.

Xiwen Wei, Guihong Li, Radu Marculescu

CoRR, 2024

Machine Unlearning for Image-to-Image Generative Models.

Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation.

Hsiang Hsu, Guihong Li, Shaohan Hu, Chun-Fu Chen

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Cache and Reuse: Rethinking the Efficiency of On-device Transfer Learning.

Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models.

Guihong Li, Hsiang Hsu, Chun-Fu Richard Chen, Radu Marculescu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

CANNON: Communication-Aware Sparse Neural Network Optimization.

A. Alper Goksoy, Guihong Li, Sumit K. Mandal, Ümit Y. Ogras, Radu Marculescu

IEEE Trans. Emerg. Top. Comput., 2023

Efficient Low-rank Backpropagation for Vision Transformer Adaptation.

Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

TIPS: Topologically Important Path Sampling for Anytime Neural Networks.

Guihong Li, Kartikeya Bhardwaj, Yuedong Yang, Radu Marculescu

Proceedings of the International Conference on Machine Learning, 2023

ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients.

Guihong Li, Yuedong Yang, Kartikeya Bhardwaj, Radu Marculescu

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Efficient On-Device Training via Gradient Filtering.

Yuedong Yang, Guihong Li, Radu Marculescu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

AudioIMU: Enhancing Inertial Sensing-Based Activity Recognition with Acoustic Models.

Dawei Liang, Guihong Li, Rebecca Adaimi, Radu Marculescu, Edison Thomaz

Proceedings of the 2022 ACM International Symposium on Wearable Computers, 2022

2021

FLASH: Fast Neural Architecture Search with Hardware Optimization.

Guihong Li, Sumit K. Mandal, Ümit Y. Ogras, Radu Marculescu

ACM Trans. Embed. Comput. Syst., 2021

How Does Topology Influence Gradient Propagation and Model Performance of Deep Networks With DenseNet-Type Skip Connections?

Kartikeya Bhardwaj, Guihong Li, Radu Marculescu

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020

RARA: Dataflow Based Error Compensation Methods with Runtime Accuracy-Reconfigurable Adder.

Shujuan Yin, Zheyu Liu, Guihong Li, Fei Qiao, Qi Wei, Yuanfeng Wu, Lianru Gao, Xinjun Liu, Huazhong Yang

Proceedings of the 21st International Symposium on Quality Electronic Design, 2020

A Hardware Prototype Targeting Distributed Deep Learning for On-device Inference.

Allen-Jasmin Farcas, Guihong Li, Kartikeya Bhardwaj, Radu Marculescu

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Concrete: A Per-layer Configurable Framework for Evaluating DNN with Approximate Operators.

Zheyu Liu, Guihong Li, Fei Qiao, Qi Wei, Ping Jin, Xinjun Liu, Huazhong Yang

Proceedings of the IEEE International Conference on Acoustics, 2019

2014

Design and complexity analysis of an improved adaptive filtering algorithm for non-sparse impulse response.

Songlin Sun, Tiantian Ran, Na Chen, Guihong Li, Chenglin Zhao

EURASIP J. Wirel. Commun. Netw., 2014

An improved channel estimation based on generalized DFT for OFDM system.

Guihong Li, Xiaojun Jing, Songlin Sun, Hai Huang

Proceedings of the 14th International Symposium on Communications and Information Technologies, 2014