Guihong Li
PhD Candidate
ECE, The University of Texas at Austin
lgh@utexas.edu
Bio
I'm a currently enrolled Ph.D. student at the SLD group at the University of Texas at Austin under the supervision of Dr. Radu Marculescu. I obtained my Bachelor's degree from Beijing University of Posts and Telecommunications (BUPT) in June 2018. My current research interests include:
- Trustworthy ML and Generative AI: Enhancing the trustworthiness of machine learning by exerting control over the training data and generated content in Generative AI.
- Efficient Deep Learning System Design: Accelerating both training and inference efficiency of large-scale models.
Recent News
• 01-2024 Two papers accepted to ICLR 2024.
• 09-2023 One paper accepted to NeurIPS 2023.
• 05-2023 One paper accepted to ICML 2023.
• 02-2023 One paper accepted to CVPR 2023.
• 01-2023 One paper accepted to ICLR 2023 as Spotlight.
Professional Experience
Applied Scientist Intern@JPMorgan Chase & Co New York, June 2023 - October 2023 Mentors: Dr. Richard CF. Chen, Dr. Hsiang Hsu
- Trustworthy Generative models: Control the contents generated by image generative models.
- Efficient Machine Unlearning: Build an efficient machine unlearning algorithm to quickly remove information from a trained model.
Research Scientist Intern@ARM ML Tech San Jose, May 2021 - August 2021 Mentors: Dr. Kartikeya Bhardwaj, Dr. Naveen Suda, Dr. Lingchuan Meng
- Hardware-aware NAS: Explored the neural architecture search technique to search for hardware-efficient models.
- Hardware Performance evaluation: Built a model to estimate neural networks' latency on neural accelerators.
Publications (Selected)
Full publications on Resume.
Machine Unlearning for Image-to-Image Generative Models
Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu
ICLR 2024: International Conference on Learning Representations
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
Hsiang Hsu, Guihong Li, Shaohan Hu, Chun-Fu Chen
ICLR 2024: International Conference on Learning Representations
Efficient Low-rank Backpropagation for Vision Transformer Adaptation
Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu
NeurIPS 2023: Conference on Neural Information Processing Systems
TIPS: Topologically Important Path Sampling for Anytime Neural Networks
Guihong Li, Kartikeya Bhardwaj, Yuedong Yang, Radu Marculescu
ICML 2023: International Conference on Machine Learning
Efficient On-device Training via Gradient Filtering
Yuedong Yang, Guihong Li, Radu Marculescu
CVPR 2023: Conference on Computer Vision and Pattern Recognition
ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients
Guihong Li, Yuedong Yang, Kartikeya Bhardwaj, Radu Marculescu
ICLR 2023 (Spotlight): International Conference on Learning Representations