Multiscale POD of Transformer Attention Fields: Scale-Selective Analysis via Morlet Scalogram

arXiv:2606.06573 · cs.LG, cs.CL, eess.SP, physics.flu-dyn · Submitted 2026-06-04 · Read on arXiv

cs.LG, cs.CL, eess.SP, physics.flu-dyn

Submitted: 2026-06-04

Updated: 2026-06-04

Terminology

• Transformer — 2× in this paper · explained in 2 episodes
• Effective Rank — 1× in this paper · explained in 2 episodes
• Proper Orthogonal Decomposition — 1× in this paper
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Wavelet Transform — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks