PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

arXiv:2603.13663 · cs.LG · Submitted 2026-03-14 · Read on arXiv

cs.LG

Submitted: 2026-03-14

Updated: 2026-10-04

Code: https://github.com/facebookresearch/DiT

Terminology

• Transformer — 4× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes

Sources

• Spectral State Space Models
• Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
• Simple Hardware-Efficient Long Convolutions for Sequence Modeling
• It's Raw! Audio Generation with State-Space Models
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Improved Denoising Diffusion Probabilistic Models
• Scalable Diffusion Models with Transformers
• Simplified State Space Layers for Sequence Modeling
• Denoising Diffusion Implicit Models
• Consistency Models
• Long Range Arena: A Benchmark for Efficient Transformers
• Efficient Transformers: A Survey
• LLaMA: Open and Efficient Foundation Language Models

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