Pith. sign in

REVIEW 4 cited by

Flexible Diffusion Modeling of Long Videos

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2205.11495 v3 pith:N6B6DBPV submitted 2022-05-23 cs.CV cs.LG

William Harvey , Saeid Naderiparizi , Vaden Masrani , Christian Weilbach , Frank Wood This is my paper · ORCID
classification cs.CVcs.LG
keywords videomodelingframesvideosdiffusionlongsamplesampled
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a framework for video modeling based on denoising diffusion probabilistic models that produces long-duration video completions in a variety of realistic environments. We introduce a generative model that can at test-time sample any arbitrary subset of video frames conditioned on any other subset and present an architecture adapted for this purpose. Doing so allows us to efficiently compare and optimize a variety of schedules for the order in which frames in a long video are sampled and use selective sparse and long-range conditioning on previously sampled frames. We demonstrate improved video modeling over prior work on a number of datasets and sample temporally coherent videos over 25 minutes in length. We additionally release a new video modeling dataset and semantically meaningful metrics based on videos generated in the CARLA autonomous driving simulator.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 102 citations worldwide. Full citation record

  1. Mitigating Compounding Error via Video Representation Regularization

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Compounding error in autoregressive video diffusion tracks effective-rank collapse of DiT hidden states, and representation regularization (SigReg/Unif) stabilizes long rollouts where data scaling does not.

  2. Information-Guided Diffusion Sampling for Dataset Distillation

    cs.LG 2025-07 conditional novelty 5.0 of 10

    IGDS improves diffusion-based dataset distillation by guiding sampling with an IPC-dependent balance between prototype and contextual information.

  3. VRAG: Learning World Models for Interactive Video Generation

    cs.CV 2025-05 unverdicted novelty 5.0 of 10

    VRAG improves long-horizon interactive video generation by conditioning autoregressive diffusion on retrieved historical frames and explicit global state, outperforming long-context baselines on the tested Minecraft a...

  4. Reinforcement Learning: From Algorithms To Foundation Models

    cs.AI 2026-07 conditional novelty 3.0 of 10

    A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.

Pith tools