Jinhong Lin
PhD Candidate
University of Wisconsin-Madison
Dept. of Electrical and Computer Engineering
I am a second-year PhD candidate at the University of Wisconsin-Madison, under the supervision of Prof. Yin Li and Pedro Morgado.
My primary research focus lies at the intersection of computer vision and machine learning, with a particular interest in:
- Enhancing training and inference efficiency
- Integrating multiple sensory modalities to understand the world
- Efficiently identifying high-quality datasets.
News
- (Mar 2025) Received a conference presentation travel award from the Office of Access, Engagement and Funding in the Graduate School.
Teaching
- CS/ECE 539 - Intro to Artificial Neural Networks (Head TA - Fall 2024)
- CS/ECE 539 - Intro to Artificial Neural Networks (TA - Fall 2023)
- CS/ECE 540 - Intro to Artificial Intelligence (Undergraduate TA - Spring 2021)
Publications
* Denotes equal contribution
From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Nashville, 2025.
Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP Inference
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, 2025.
Accelerating Augmentation Invariance Pretraining
Neural Information Processing Systems (NeurIPS), Vancouver, 2024.
TrackVerse: A Large-Scale Object-Centric Video Dataset
IEEE/CVF International Conference on Computer Vision (ICCV), 2025