PFD-BDCM is a diffusion-based structural causal model that represents dynamic spatio-temporal confounders via conditional autoregressive processes and functional data via basis expansions, with theoretical preservation of causal effects and empirical outperformance on synthetic and air-pollution dat
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Category theory proves prompt-based learning on perfect foundation models works only for representable tasks, fine-tuning solves tasks in the pretext category, and models can represent unseen target-category objects using source-category structure.
citing papers explorer
-
Partially Functional Dynamic Backdoor Diffusion-based Causal Model
PFD-BDCM is a diffusion-based structural causal model that represents dynamic spatio-temporal confounders via conditional autoregressive processes and functional data via basis expansions, with theoretical preservation of causal effects and empirical outperformance on synthetic and air-pollution dat
-
On the Power of Foundation Models
Category theory proves prompt-based learning on perfect foundation models works only for representable tasks, fine-tuning solves tasks in the pretext category, and models can represent unseen target-category objects using source-category structure.