Scholar
Vincent-Daniel Yun (J. Yun)
Google Scholar ID: mlfYKfgAAAAJ
Graduate Research Assistant at USC (ML Theory)
Citations & Impact
Citations
42
H-index
4
i10-index
2
Publications
12
Co-authors
13
list available
Resume
Academic Achievements
- - May 2025, submitted two papers to an ML conference (Core Rank: A).
- - May 2025, 'Stochastic Gradient Sampling for Enhancing Neural Networks Training' accepted at Neural Computing and Application (IF: 4.5).
- - April 2025, submitted one paper to an ML conference (Core Rank: B).
- - January 2025, launched the Open Neural Network Research Lab, supported by the Brian Impact Foundation.
- - December 2024, 'ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification' accepted at AAAI 2025 Workshops.
- - November 2024, 'Mitigating Gradient Overlap in Deep Residual Networks with Gradient Normalization for Improved Non-Convex Optimization' accepted at IEEE BigData 2024.
- - July 2024, 'Analysis and Predictive Modeling of Solar Coronal Holes Using Computer Vision and ARIMA-LSTM Networks' accepted at European Space Agency (ESA) SPAICE 2024.
- - April 2024, 'Uncertainty Estimation for Tumor Prediction with Unlabeled Data' accepted at CVPR 2024 Workshops.
- - March 2024, 'Robust Neural Pruning with Gradient Sampling Optimization for Residual Neural Networks' accepted at IJCNN 2024.
Research Experience
- - BMI Center at Stony Brook University: Research Assistant, September 2023 - May 2025, Advisor: Prof. Chao Chen. Conducted research to enhance uncertainty estimation in breast cancer tumor prediction for digital pathology.
- - DNI Lab at Stony Brook University: Research Assistant, May 2022 - August 2023, Co-Advisor: Prof. Zhoulai Fu and Prof. Francois Rameau.
Education
- M.S. student in Computer Science at the University of Southern California; previously studied Computer Science and Applied Mathematics at Stony Brook University, where he worked as a research assistant at the Biomedical Informatics Center (BMI) under Prof. Chao Chen.
Background
- Research interests include neural network theory, learning theory, and optimization, particularly enhancing gradient descent and improving neural network generalization. Interests also include quantization, pruning, and neural architecture search (NAS) to accelerate training and inference while preserving performance.
Miscellany
- Contact: juyoung.yun@usc.edu, +1 631-352-6530, East Setauket, New York, United States
