Back to feed
arXiv cs.LG
arXiv cs.LG
7/10/2026
LLT: Local Linear Transformer for PDE Operator Learning

LLT: Local Linear Transformer for PDE Operator Learning

Short summary

Local Linear Transformer (LLT) combines linear global attention with local spatial mixing for efficient PDE operator learning. Tested on elasticity, plasticity, airfoil, pipe, and Darcy flow problems, it achieves competitive accuracy while reducing training time 1.8-2.5x vs. Transolver. Scales to 3D car aerodynamics with 32K-point unstructured meshes.

  • •LLT addresses quadratic scaling and lack of local bias in standard attention for PDEs
  • •Achieves 1.8-2.5x speedup vs. Transolver while maintaining competitive accuracy across discretizations
  • •Scales to 3D problems with 32K-point unstructured meshes across multiple problem types

Generated with AI, which can make mistakes.

#research-breakthrough#ai-tools
Read full article at arXiv cs.LG

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

The user wants me to rewrite a news headline for a mobile feed based on the original title and summary.
arXiv cs.LG
Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
arXiv cs.LG
The original title is "Flowing vs. Thinking: How Liquid Neural Networks Diverge from LLMs"
Dev.to
Joint discovery of governing partial differential equations from multi-source datasets by competitive optimization
arXiv cs.LG