ISLA: A Coordinate-Free, Measure-Weighted Transformer for Boundary-Driven PDEs
cs.LG, cs.CE, math-ph, math.MP, physics.flu-dyn
Submitted: 2026-11-12
Updated: 2026-11-15
Code: https://github.com/NVIDIA/physicsnemo
Terminology
Sources
- GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer
- Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
- AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers
- AhmedML: High-Fidelity Computational Fluid Dynamics Dataset for Incompressible, Low-Speed Bluff Body Aerodynamics
- DrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamics
- HiLiftAeroML: A High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics
- Fast, Expressive SE$(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space
- Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
- Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
- Geometric Algebra Transformer
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Choose a Transformer: Fourier or Galerkin
- PLAID: A Unified Data Model for Machine Learning on Heterogeneous Physics Simulations
- Equivariant Frames and the Impossibility of Continuous Canonicalization
- e3nn: Euclidean Neural Networks
- SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model
- Graph Neural PDE Solvers with Conservation and Similarity-Equivariance
- Transolver is a Linear Transformer: Revisiting Physics-Attention through the Lens of Linear Attention
- Perceiver IO: A General Architecture for Structured Inputs & Outputs
- Equivariance with Learned Canonicalization Functions
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis