Papers › Scaling Autoregressive Video Models
Scaling Autoregressive Video Models
Dirk Weissenborn, Oscar Täckström, Jakob Uszkoreit
Due to the statistical complexity of video, the high degree of inherent stochasticity, and the sheer amount of data, generating natural video remains a challenging task. State-of-the-art video generation models often attempt to address these issues by combining sometimes complex, usually video-specific neural network architectures, latent variable models, adversarial training and a range of other methods. Despite their often high complexity, these approaches still fall short of generating high quality video continuations outside of narrow domains and often struggle with fidelity. In contrast, we show that conceptually simple autoregressive video generation models based on a three-dimensional self-attention mechanism achieve competitive results across multiple metrics on popular benchmark datasets, for which they produce continuations of high fidelity and realism. We also present results from training our models on Kinetics, a large scale action recognition dataset comprised of YouTube videos exhibiting phenomena such as camera movement, complex object interactions and diverse human movement. While modeling these phenomena consistently remains elusive, we hope that our results, which include occasional realistic continuations encourage further research on comparatively complex, large scale datasets such as Kinetics.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="1906.02634", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1906.02634")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Generation | BAIR Robot Pushing | Video Transformer | Cond | 1 | #7 of 31 | Archive leaderboard | report |
| Video Generation | BAIR Robot Pushing | Video Transformer | FVD score | 94± 2 | #7 of 31 | Archive leaderboard | report |
| Video Generation | BAIR Robot Pushing | Video Transformer | Notes | FVD on only leftmost samples is 94, FVD on unrolled (all subsequences) is 96 | #7 of 31 | Archive leaderboard | report |
| Video Generation | BAIR Robot Pushing | Video Transformer | Pred | 15 | #7 of 31 | Archive leaderboard | report |
| Video Generation | BAIR Robot Pushing | Video Transformer | Train | 15 | #7 of 31 | Archive leaderboard | report |
| Video Prediction | Kinetics-600 12 frames, 64x64 | Video Transformer | Cond | 5 | #15 of 16 | Archive leaderboard | report |
| Video Prediction | Kinetics-600 12 frames, 64x64 | Video Transformer | FVD | 170±5 | #15 of 16 | Archive leaderboard | report |
| Video Prediction | Kinetics-600 12 frames, 64x64 | Video Transformer | Pred | 11 | #15 of 16 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections