Tanya Marwah

Pre-Generating Multi-Difficulty PDE Data For Few-Shot Neural PDE Solvers

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation

On the Benefits of Memory for Modeling Time-Dependent PDEs

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

Towards characterizing the value of edge embeddings in Graph Neural Networks

Chimera: State Space Models Beyond Sequences

Towards characterizing the value of edge embeddings in graph neural networks