Hi! I am a Research Fellow at the Simons Foundation working with Polymathic AI. I recently graduated with a PhD from the Machine Learning Department at Carnegie Mellon University co-advised by Prof. Andrej Risteski and Prof. Zachary Lipton. Previously, I was masters student in the Robotics Institute at CMU and was a Siebel Scholar.

I work on the empirical and theoretical foundations of Machine Learning and its applications to scientific domains. My current interests are around generative modeling of scientific phenomena, inverse problems and building scientific agents. My ultimate goal is to develop ML algorithms and methods that help us accelerate the scientific process and enable scientific discovery.

You can find my CV here.

---

Selected Publications

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation
Shanda Li, Tanya Marwah, Junhong Shen, Weiwei Sun, Andrej Risteski, Yiming Yang, Ameet Talwalkar
In Submission

Towards characterizing the value of edge embeddings in GNNs
Dhruv Rohatgi, Tanya Marwah, Zachary C. Lipton, Jianfeng Lu, Ankur Moitra, Andrej Risteski
NeurIPS Mathematics of Modern Machine Learning Workshop, 2024 (Oral)
International Conference on Machine Learning, 2025 (ICML)

On the Benefits of Memory for Modeling Time-Dependent PDEs
Ricardo Buitrago Ruiz, Tanya Marwah, Albert Gu, Andrej Risteski
International Conference on Learning Representations (ICLR), 2025 (Oral)

UPS: Towards Foundation Models for PDE Solving via Cross-Modal Adaptation
Junhong Shen, Tanya Marwah, Ameet Talwalkar
ICML AI4Science Workshop, 2024 (Spotlight)
Transactions on Machine Learning Research (TMLR), 2024

Deep Equilibrium Based Neural Operators for Steady-State PDEs
Tanya Marwah^*, Ashwini Pokle^*, J. Zico Kolter, Zachary C. Lipton, Jianfeng Lu, Andrej Risteski
Neural Information Processing Systems (NeurIPS), 2023

Neural Network approximations of PDEs Beyond Linearity: A Representational Perspective
Tanya Marwah, Zachary C. Lipton, Jianfeng Lu, Andrej Risteski
International Conference on Machine Learning (ICML), 2023

Disentangling the Mechanisms Behind Implicit Regularization in SGD
Zachary Novack, Simran Kaur, Tanya Marwah, Saurabh Garg, Zachary C. Lipton
International Conference on Learning Representations (ICLR), 2023

Parametric Complexity Bounds for Approximating PDEs with Neural Networks
Tanya Marwah, Zachary C. Lipton, Andrej Risteski
Neural Information Processing Systems (NeurIPS), 2021 (Spotlight)

Attentive Semantic Video Generation using Captions
Tanya Marwah^*, Gaurav Mittal^*, Vineeth N Balasubramanian
IEEE International Conference on Computer Vision (ICCV), 2017

---

Working Paper

Chimera: State Space Models Beyond Sequences
Aakash Lahoti^*, Tanya Marwah^*, Albert Gu
In Submission

Improving Zero-Shot Reasoning Using Dynamic Non-Verbal Tokens
Tanya Marwah, Zhili Feng, Lester Mackey, Nicolo Fusi, David Alvarez-Melis