Pith. sign in

REVIEW 3 cited by

Real-time Inference and Extrapolation via a Diffusion-inspired Temporal Transformer Operator (DiTTO)

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.09072 v2 pith:WTEUNPMW submitted 2023-07-18 cs.LG cs.AIcs.CEcs.NAmath.NA

classification cs.LGcs.AIcs.CEcs.NAmath.NA
keywords extrapolationtemporaldittooperatortimetransformerarounddemonstrate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Extrapolation remains a grand challenge in deep neural networks across all application domains. We propose an operator learning method to solve time-dependent partial differential equations (PDEs) continuously and with extrapolation in time without any temporal discretization. The proposed method, named Diffusion-inspired Temporal Transformer Operator (DiTTO), is inspired by latent diffusion models and their conditioning mechanism, which we use to incorporate the temporal evolution of the PDE, in combination with elements from the transformer architecture to improve its capabilities. Upon training, DiTTO can make inferences in real-time. We demonstrate its extrapolation capability on a climate problem by estimating the temperature around the globe for several years, and also in modeling hypersonic flows around a double-cone. We propose different training strategies involving temporal-bundling and sub-sampling and demonstrate performance improvements for several benchmarks, performing extrapolation for long time intervals as well as zero-shot super-resolution in time.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bridging Sequential Deep Operator Network and Video Diffusion: Residual Refinement of Spatio-Temporal PDE Solutions

    cs.CE 2025-07 conditional novelty 5.0 of 10

    Feeding an S-DeepONet coarse prediction into a video diffusion model trained on the residual reduces PDE solution errors by 82% on cavity flow and 34% on plastic deformation, beating either single-stage model.

  2. Enhanced accuracy through ensembling of randomly initialized auto-regressive models for time-dependent PDEs

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Deep ensembles of randomly initialized autoregressive models reduce long-horizon prediction error compared to any single model across three PDE-driven dynamical systems.

  3. Learning Mappings in Mesh-based Simulations

    cs.LG 2025-06 conditional novelty 3.0 of 10

    A bilinear scatter encoding plus a masked UNet yields competitive surrogate accuracy and data efficiency on several mesh-based simulation benchmarks, though the encoding is a standard technique.

Pith tools