autoregressive-models
PDEBench: An Extensive Benchmark for Scientific Machine Learning
seq2cause: Turns any discrete sequence of events into a causal graph using autoregressive models (LLaMA, GPT, RNN, Mamba).
Stochastic processes insights from VAE. Code for the paper: Learning minimal representations of stochastic processes with variational autoencoders.
Ultra-minimal autoregressive diffusion model for image generation