Fall 2025: Foundation models for spatial-time series

Zoom link

Course page

Telegram chat

YouTube playlist

Topics to discuss

1. State Space Models, Convolution, SSA, SSM (Spectral Submanifolds)
2. Neural and Controlled ODE, Neural PDE, Geometric Learning
3. Operator Learning, Physics-informed learning, and multimodeling
4. Spatial-Temporal Graph Modeling: Graph convolution and metric tensors
5. Riemmannian models; time series generation
6. AI for science: mathematical modelling principles

Student talks

Student	Title	Links
Dorin Daniil	Применение римановой геометрии для классификации пространственно-временных рядов	Slides, Code
Nikita Kiselev	Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion	Slides, Code
Petr Babkin	Modern State Space Models: S4, S5, MAMBA, HIPPO	Slides, Code

Student talks: physics informed learning

Student	Title	Links
Dorin Daniil	Решение двумерных задач Римана в газовой динамике	Slides
Nikita Kiselev	Rayleigh–Bénard Convection	Slides, Code
Petr Babkin	Модели с лагранжианом и гамильтонианом	Slides, Code