Research Group Suvrit Sra
Suvrit Sra
Prof. Dr.
Core PI
Suvrit Sra
is Professor for Resource Aware Machine Learning at TU Munich.
He specializes in robust, reliable, and resource-efficient machine learning methods. His research focuses, in particular, on solving optimization problems for machine learning with multiple parameters. For example, these complex optimization problems are used in autonomous driving so that a car can reliably distinguish a sign from a person.
Team members @MCML
PostDocs
Maria-Luiza Vladarean
Dr.
→ Group Suvrit Sra
Resource Aware Machine Learning
PhD Students
Pouria Fatemi
→ Group Suvrit Sra
Resource Aware Machine Learning
Sai Niranjan Ramachandran
→ Group Suvrit Sra
Resource Aware Machine Learning
Xuhui Zhang
→ Group Suvrit Sra
Resource Aware Machine Learning
Recent News @MCML
Publications @MCML
2026
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL
Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success.
Preprint (Jun. 2026). arXiv GitHub
On learning linear dynamical systems in context with attention layers.
ICLR 2026 - 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. URL
2025
Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. URL
A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability.
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL
A projection-based framework for gradient-free and parallel learning.
Preprint (Jun. 2025). arXiv
©all images: LMU | TUM
2024-12-27 - Last modified: 2026-07-03