Implementation of Autoregressive Diffusion in Pytorch
-
Updated
Sep 2, 2026 - Python
Implementation of Autoregressive Diffusion in Pytorch
Ultra-minimal autoregressive diffusion model for image generation
Official code, locked protocols, and audit artifacts for "Jev-Routed Temporal Granularity with Recovery and Hysteresis for Causal Video Generation": per-segment fine/coarse/hold routing for Causal-rCM (Wan2.1-1.3B) via the Jev oracle, with two-GPU (T4/A100) feasibility audits.
JevGAG + DDAG: a two-GPU study of adaptive temporal granularity for causal video generation and video world models - the JevGAG report (preconditions) and the DDAG method (regime map, intrinsic probe, seam repair), with a boundary analysis.
To associate your repository with the autoregressive-diffusion topic, visit your repo's landing page and select "manage topics."