An offline-trained controller augments autoregressive diffusion models to perform fast, feed-forward data assimilation in chaotic spatiotemporal PDEs with order-of-magnitude speedups and improved accuracy over baselines.
Langwen Huang, Lukas Gianinazzi, Yuejiang Yu, Peter D Dueben, and Torsten Hoefler
2 Pith papers cite this work, alongside 120 external citations. Polarity classification is still indexing.
2
Pith papers citing it
120
external citations · OpenAlex
verdicts
UNVERDICTED 2representative citing papers
BioVid is a data-driven autoregressive model using 2D-encode/3D-decode tokenization and causal Transformer with EOS termination that reproduces real action duration distributions (W1 distance 1.24 frames) on NTU RGB+D drinking clips, outperforming fixed-length baselines.
citing papers explorer
-
Control-Augmented Autoregressive Diffusion for Data Assimilation
An offline-trained controller augments autoregressive diffusion models to perform fast, feed-forward data assimilation in chaotic spatiotemporal PDEs with order-of-magnitude speedups and improved accuracy over baselines.
-
BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension
BioVid is a data-driven autoregressive model using 2D-encode/3D-decode tokenization and causal Transformer with EOS termination that reproduces real action duration distributions (W1 distance 1.24 frames) on NTU RGB+D drinking clips, outperforming fixed-length baselines.