Research and Publications
10 peer-reviewed papers in TMLR, CVPR, ICRA, RA-L, ICASSP and BMVC · 498 citations · h-index 8 · i10-index 8 (Google Scholar, as of August 2026).
2025
Cybernaut: Towards Reliable Web Automation
Ankur Tomar, Hengyue Liang, Indranil Bhattacharya, Natalia Larios Delgado, Francesco Carbone
Accepted to the KDD 2025 Workshop on Evaluation and Trustworthiness of Agentic and Generative AI Models (Agentic & GenAI Evaluation @ KDD 2025)
A Baseline Method for Removing Invisible Image Watermarks using Deep Image Prior
Hengyue Liang, Taihui Li, Ju Sun
Accepted to Transactions on Machine Learning Research (TMLR), 2025
Robustness and Safety of Deep Learning Models
Hengyue Liang
Ph.D. dissertation, University of Minnesota, Twin Cities, 2025 (advisor: Ju Sun)
2024
Selective Classification Under Distribution Shifts
Hengyue Liang, Le Peng, Ju Sun
Accepted to Transactions on Machine Learning Research (TMLR), 2024
Automated Quantification of Eye Tics using Computer Vision and Deep Learning Techniques
Christine Conelea, Hengyue Liang, Megan DuBois, Brittany Raab, Mia Kellman, Brianna Wellen, Suma Jacob, Sonya Wang, Ju Sun, Kelvin Lim
“Movement Disorders” 39(1):183–191, 2024, the official journal of the International Parkinson and Movement Disorder Society (MDS)
2023
Early Stopping for Deep Image Prior
Hengkang Wang, Taihui Li, Zhong Zhuang, Tiancong Chen, Hengyue Liang, Ju Sun
Accepted to Transactions on Machine Learning Research (TMLR), 2023
Rethinking Transfer Learning for Medical Image Classification
Le Peng, Hengyue Liang, Gaoxiang Luo, Taihui Li, Ju Sun
Accepted to British Machine Vision Conference (BMVC), 2023 (Oral)
Implications of Solution Patterns on Adversarial Robustness
Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun
Accepted to “Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition” (CVPR 2023, workshop of adversarial machine learning)
Optimization for Robustness Evaluation beyond ℓp Metrics
Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun
Accepted to “2023 IEEE International Conference on Acoustics, Speech, and Signal Processing” (ICASSP)
Optimization and Optimizers for Adversarial Robustness
Hengyue Liang, Buyun Liang, Le Peng, Ying Cui, Tim Mitchell, Ju Sun
arXiv preprint arXiv:2303.13401, 2023
2021
Self-Validation: Early Stopping for Single-Instance Deep Generative Priors
Taihui Li, Zhong Zhuang, Hengyue Liang, Le Peng, Hengkang Wang, Ju Sun
Accepted to British Machine Vision Conference (BMVC) 2021
Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures
Hengyue Liang, Xibai Lou, Yang Yang, Changhyun Choi
Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2021, Xi'an
Attribute-Based Robotic Grasping with One-Grasp Adaptation
Yang Yang, Yuanhao Liu, Hengyue Liang, Xibai Lou, Changhyun Choi
Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2021, Xi'an
2020
A Deep Learning Approach to Grasping the Invisible
Yang Yang, Hengyue Liang, Changhyun Choi
Accepted to IEEE Robotics and Automation Letters (RA-L) 2020