Pith. sign in

REVIEW 3 cited by

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.20280 v1 pith:SDGNTVAN submitted 2024-10-26 cs.CV cs.AI

classification cs.CVcs.AI
keywords videogenerationmodeldiffusionframesmardinimaskedplanning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial generation in an asymmetric network design: i) a MAR-based planning model containing most of the parameters generates planning signals for each masked frame using low-resolution input; ii) a lightweight generation model uses these signals to produce high-resolution frames via diffusion de-noising. MarDini's MAR enables video generation conditioned on any number of masked frames at any frame positions: a single model can handle video interpolation (e.g., masking middle frames), image-to-video generation (e.g., masking from the second frame onward), and video expansion (e.g., masking half the frames). The efficient design allocates most of the computational resources to the low-resolution planning model, making computationally expensive but important spatio-temporal attention feasible at scale. MarDini sets a new state-of-the-art for video interpolation; meanwhile, within few inference steps, it efficiently generates videos on par with those of much more expensive advanced image-to-video models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Resampling Forcing trains autoregressive video diffusion models on self-resampled degraded histories with a causal mask, achieving stable long-horizon generation without a teacher or discriminator.

  2. Controllable Coupled Image Generation via Diffusion Models

    cs.CV 2025-06 reject novelty 6.0 of 10

    A cross-attention control method that couples backgrounds across multiple generated images by blending LLM-extracted background and entity prompts with a time-varying weight optimized for background similarity and tex...

  3. Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression

    cs.RO 2025-02 conditional novelty 6.0 of 10

    HMA is a masked autoregressive transformer that predicts future video and actions across many robot embodiments, running up to 15x faster than prior diffusion-based video simulators while matching or improving visual ...

Pith tools