Guihong Li

33 papers A* 7A 1Misc 2Journal 17Unranked 6
YearRankTypeTitle / Venue / Authors
2025 J jnl
FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models.
CoRR
Yonatan Dukler, Guihong Li, Deval Shah, Vikram Appia, Emad Barsoum
2025 — conf
From Data to Design: Leveraging Frequency Statistics for Efficient Neural Network Architectures.
CVPR Workshops
Mustafa Munir, Guihong Li, Md Mostafijur Rahman, Alex Zhang, Radu Marculescu
2025 A conf
Online-LoRA: Task-Free Online Continual Learning via Low Rank Adaptation.
WACV
Xiwen Wei, Guihong Li, Radu Marculescu
2025 J jnl
X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression.
CoRR
Guihong Li, Mehdi Rezagholizadeh, Mingyu Yang, Vikram Appia, Emad Barsoum
2025 J jnl
Zebra-Llama: Towards Extremely Efficient Hybrid Models.
CoRR
Mingyu Yang, Mehdi Rezagholizadeh, Guihong Li, Vikram Appia, Emad Barsoum
2024 — conf
Cache and Reuse: Rethinking the Efficiency of On-device Transfer Learning.
CVPR Workshops
Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu
2024 A* conf
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation.
ICLR
Hsiang Hsu, Guihong Li, Shaohan Hu, Chun-Fu Chen
2024 J jnl
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation.
CoRR
Hsiang Hsu, Guihong Li, Shaohan Hu, Chun-Fu Chen
2024 — conf
Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models.
CVPR Workshops
Guihong Li, Hsiang Hsu, Chun-Fu Richard Chen, Radu Marculescu
2024 A* conf
Machine Unlearning for Image-to-Image Generative Models.
ICLR
Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu
2024 J jnl
Machine Unlearning for Image-to-Image Generative Models.
CoRR
Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu
2024 J jnl
Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation.
CoRR
Xiwen Wei, Guihong Li, Radu Marculescu
2024 J jnl
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities.
IEEE Trans. Pattern Anal. Mach. Intell.
Guihong Li, Duc Hoang, Kartikeya Bhardwaj, Ming Lin, Zhangyang Wang, Radu Marculescu
2023 J jnl
CANNON: Communication-Aware Sparse Neural Network Optimization.
IEEE Trans. Emerg. Top. Comput.
A. Alper Goksoy, Guihong Li, Sumit K. Mandal, Ümit Y. Ogras, Radu Marculescu
2023 A* conf
Efficient Low-rank Backpropagation for Vision Transformer Adaptation.
NeurIPS
Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu
2023 J jnl
Efficient Low-rank Backpropagation for Vision Transformer Adaptation.
CoRR
Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu
2023 A* conf
Efficient On-Device Training via Gradient Filtering.
CVPR
Yuedong Yang, Guihong Li, Radu Marculescu
2023 J jnl
Efficient On-device Training via Gradient Filtering.
CoRR
Yuedong Yang, Guihong Li, Radu Marculescu
2023 J jnl
Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models.
CoRR
Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu
2023 A* conf
TIPS: Topologically Important Path Sampling for Anytime Neural Networks.
ICML
Guihong Li, Kartikeya Bhardwaj, Yuedong Yang, Radu Marculescu
2023 J jnl
TIPS: Topologically Important Path Sampling for Anytime Neural Networks.
CoRR
Guihong Li, Kartikeya Bhardwaj, Yuedong Yang, Radu Marculescu
2023 J jnl
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities.
CoRR
Guihong Li, Duc Hoang, Kartikeya Bhardwaj, Ming Lin, Zhangyang Wang, Radu Marculescu
2023 J jnl
ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients.
CoRR
Guihong Li, Yuedong Yang, Kartikeya Bhardwaj, Radu Marculescu
2023 A* conf
ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients.
ICLR
Guihong Li, Yuedong Yang, Kartikeya Bhardwaj, Radu Marculescu
2022 Misc conf
AudioIMU: Enhancing Inertial Sensing-Based Activity Recognition with Acoustic Models.
ISWC
Dawei Liang, Guihong Li, Rebecca Adaimi, Radu Marculescu, Edison Thomaz
2021 J jnl
FLASH: Fast Neural Architecture Search with Hardware Optimization.
CoRR
Guihong Li, Sumit K. Mandal, Ümit Y. Ogras, Radu Marculescu
2021 J jnl
FLASH: Fast Neural Architecture Search with Hardware Optimization.
ACM Trans. Embed. Comput. Syst.
Guihong Li, Sumit K. Mandal, Ümit Y. Ogras, Radu Marculescu
2021 A* conf
How Does Topology Influence Gradient Propagation and Model Performance of Deep Networks With DenseNet-Type Skip Connections?
CVPR
Kartikeya Bhardwaj, Guihong Li, Radu Marculescu
2020 — conf
A Hardware Prototype Targeting Distributed Deep Learning for On-device Inference.
CVPR Workshops
Allen-Jasmin Farcas, Guihong Li, Kartikeya Bhardwaj, Radu Marculescu
2020 — conf
RARA: Dataflow Based Error Compensation Methods with Runtime Accuracy-Reconfigurable Adder.
ISQED
Shujuan Yin, Zheyu Liu, Guihong Li, Fei Qiao, Qi Wei, Yuanfeng Wu, Lianru Gao, Xinjun Liu, Huazhong Yang
2019 Misc conf
Concrete: A Per-layer Configurable Framework for Evaluating DNN with Approximate Operators.
ICASSP
Zheyu Liu, Guihong Li, Fei Qiao, Qi Wei, Ping Jin, Xinjun Liu, Huazhong Yang
2014 — conf
An improved channel estimation based on generalized DFT for OFDM system.
ISCIT
Guihong Li, Xiaojun Jing, Songlin Sun, Hai Huang
2014 J jnl
Design and complexity analysis of an improved adaptive filtering algorithm for non-sparse impulse response.
EURASIP J. Wirel. Commun. Netw.
Songlin Sun, Tiantian Ran, Na Chen, Guihong Li, Chenglin Zhao