Talks and presentations

• Theoretical Perspectives of Efficient Learning for Large Foundation Models. Illinois Tech ECE Graduate Research Seminar, 2025. slides

• Theoretical Foundations of Chain-of-Thought with Trained Nonlinear Transformer Models. IBM-RPI FCRC Seminar Series, 2025. slides

• Theoretical Foundations of In-Context Learning and Chain-of-Thought Using Properly Trained Transformer Models. NJIT Data Science Seminar, 2024. slides

• Theoretical and Algorithmic Foundations of In-Context Learning Using Properly Trained Transformer Models. IBM-RPI FCRC Seminar Series, 2024. slides; poster

• A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity. ICLR 2023 poster presentation. video

• Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling. ICML 2022 short presentation. video