Talk & Teach
Slides and tutorial materials, kept online for collaborators and students.
Talks & tutorials
- 2026From Networks to Neural Networks: What Internal Structure Tells Us About Generative Models TalkPhD Colloquium · Fall 2026 · Rochester Institute of Technology, Rochester, NYA tutorial-style talk on the ways a trained model gets changed after release (editing, stitching, merging, pruning, steering, unlearning, fine-tuning), why exams miss what breaks inside, and how reading the model as a graph helps.
- 2026Uncertainty Quantification for Dynamical Networks TutorialIEEE BigData 2026 · upcomingUncertainty quantification and state estimation for graph dynamics.
- 2024–2025Unifying Spectral and Spatial Graph Neural Networks Tutorial series机器之心 (Synced) online talk · 2024An operator-level view that connects spectral and spatial GNNs.
- 2023Understanding Influence Maximization via Higher-Order Decomposition Paper talkWith Zonghan Zhang. Sobol indices separate a seed's own effect from its interactions with other seeds.
- 2022Early Forecasting of the Impact of Traffic Accidents Using a Single Shot Observation Paper talkSIAM SDM 2022 · Minneapolis, MN
- 2021Studying Spread Patterns of COVID-19 Based on Spatiotemporal Data TutorialSIAM SDM 2021 · April · onlineWith Beiyu Lin and Xiaowei Jia. Spreading models for epidemics (GNN, RNN, SIR, PDE).
Courses
- CurrentCSCI 431.02 Intro to Computer Vision UndergraduateRochester Institute of TechnologyIntroductory computer vision for undergraduates.
- PastCSE 4633/6633 Artificial Intelligence Split-levelMississippi State UniversityIntroductory AI course spanning core concepts and methods.
- PastCSE 4693/6693 Intro to Machine Learning Split-levelMississippi State UniversityFoundations of machine learning for undergraduate and graduate students.
- PastCSE 8673 Machine Learning GraduateMississippi State UniversityGraduate-level machine learning with emphasis on principles and applications.
- PastCSE 8990 Graph Machine Learning GraduateMississippi State UniversityAdvanced topics in graph machine learning and networked intelligence.