NRGPT: An Energy-based Alternative for GPT
- Nima Dehmamy
- Benjamin Hoover
- et al.
- 2026
- ICLR 2026
Conference paper
Nima Dehmamy
Bio
Nima Dehmamy is a Research Staff Member at IBM Research, Cambridge MA. His research focuses on AI for science, equivariant networks, optimization theory and graph neural networks. His recent projects include
- Symmetries, conserved quantities and flat minima in the loss landscape
- Generative adversarial symmetry discovery
- Coarse-graining in machine learning models
He earned his PhD in physics from Boston University in 2016. He was a research faculty at Northwestern University 2019-2022.
Publications
BOLTZMANN ROUTING FORENERGY-COMPATIBLE MIXTURE OFEXPERTS
- Bharat Runwal
- Bishwajit Saha
- et al.
- 2026
- ICLR 2026
Workshop paperAtlasD: Automatic Local Symmetry Discovery
- Manu Bhat
- Jonghyun Park
- et al.
- 2025
- ICML 2025
Conference paperUnderstanding Mode Connectivity via Parameter Space Symmetry
- Bo Zhao
- Nima Dehmamy
- et al.
- 2025
- ICML 2025
Conference paperSymmetry-Driven Discovery of Dynamical Variables in Molecular Simulations
- Jeet Mohapatra
- Nima Dehmamy
- et al.
- 2025
- ICML 2025
Conference paperSymmetry-Informed Governing Equation Discovery
- Jianke Yang
- Wang Rao
- et al.
- 2024
- NeurIPS 2024
Conference paperNeural Network Reparametrization for Accelerated Optimization in Molecular Simulations
- Nima Dehmamy
- Csaba Both
- et al.
- 2024
- NeurIPS 2024
Conference paperLatent Space Symmetry Discovery
- Jianke Yang
- Nima Dehmamy
- et al.
- 2024
- ICML 2024
Conference paperHessian Reparametrization for Coarse-grained Energy Minimization
- Nima Dehmamy
- Csaba Both
- et al.
- 2024
- ICLR 2024
Workshop paperCoarse-graining via reparametrization avoids force matching and back-mapping
- Nima Dehmamy
- Csaba Both
- et al.
- 2023
- NeurIPS 2023
Workshop paper
Top collaborators
MM
Mauro Martino
Principal Research Staff Member and Manager, Visual AI Lab