- Stochastic Dynamics for AI: Continuous-Time Methods for Learning, Sampling, Generation, and Control
- Geometric Foundations of AI (I): Parameter Spaces, Statistical Manifolds, and Optimization
- Deployment-Time Optimization of AI: Robustness, Compression, Evaluation, Inference, and Adaptive Environments
- Training-Time Optimization of AI: Data, Dynamics, Scaling, and Post-Training
- Geometric Foundations of AI (II): Data Manifolds, Symmetry, and Learned Representations












