ViRDM models and training assets
This repository contains the trained causal four-step ViRDM generators and the compact frozen artifacts required to reproduce training.
checkpoints/virdm_causal4_dynamic_step20.pt: the primary 20-update model with dynamics regularization (5e-4).checkpoints/virdm_causal4_nodynamic_step20.pt: the matched model without dynamics regularization.prompt_data/data.mdb: 6,505 captions in the original orderedzhuhz22/Causal-Forcing-datatraining split; no video or latent payloads.references/reference_M4096.pt: the fixed 4,096-landmark joint video-text reference used by ViRDM. Its publication metadata contains stable upstream identifiers rather than machine-local paths.references/siglip2_text_fp32.npy: frozen SigLIP2 features aligned row for row with the reference and prompt table.asset_receipt.json: row contract, filenames, and SHA-256 checksums.
Project page: https://neu-vi.github.io/ViRDM/