Pith. sign in

REVIEW 20 cited by

Scaling Autoregressive Video Models

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 1906.02634 v3 pith:LEJ2YQDK submitted 2019-06-06 cs.CV cs.AIcs.LG

Scaling Autoregressive Video Models

classification cs.CV cs.AIcs.LG
keywords videomodelshighcomplexcontinuationsoftenresultsautoregressive
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 20 Pith papers

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

  1. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

    cs.CV 2026-02 conditional novelty 7.0

    Causal Forcing distills few-step autoregressive video generators from an autoregressive diffusion teacher rather than a bidirectional one, avoiding conditional-expectation blur and beating Self Forcing on motion and q...

  2. Learning Interactive Real-World Simulators

    cs.AI 2023-10 conditional novelty 7.0

    UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.

  3. Scaling Laws for Autoregressive Generative Modeling

    cs.LG 2020-10 accept novelty 7.0

    Autoregressive transformers follow power-law scaling laws for cross-entropy loss with nearly universal exponents relating optimal model size to compute budget across four domains.

  4. OmniGen-AR: AutoRegressive Any-to-Image Generation

    cs.CV 2026-06 unverdicted novelty 6.0

    OmniGen-AR is a unified autoregressive framework for any-to-image generation that tokenizes text and visual conditions together and uses disentangled causal attention to support tasks like text-to-image, depth-to-imag...

  5. Streaming Video Generation with Streaming Force Control

    cs.CV 2026-06 unverdicted novelty 6.0

    StreamForce presents a unified causal model for force-controllable streaming video generation using a new force representation and distillation pipeline, claiming SOTA force adherence and 16.6 FPS performance.

  6. Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity

    cs.CV 2026-05 unverdicted novelty 6.0

    Head Forcing assigns tailored KV cache strategies to local, anchor, and memory attention heads plus head-wise RoPE re-encoding to extend autoregressive video generation from seconds to minutes without training.

  7. Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

    cs.CV 2026-02 unverdicted novelty 6.0

    Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.

  8. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

    cs.CV 2026-02 conditional novelty 6.0

    Causal Forcing initializes autoregressive diffusion students from AR teachers to recover flow maps that bidirectional teachers cannot provide, delivering 19%+ gains over Self Forcing on dynamic degree and related metrics.

  9. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

    cs.CV 2026-02 conditional novelty 6.0

    Causal Forcing uses an autoregressive teacher for ODE initialization in diffusion distillation to close the causal attention gap and deliver better real-time video generation than Self Forcing.

  10. Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

    cs.CV 2025-09 unverdicted novelty 6.0

    Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.

  11. Unified Video Action Model

    cs.RO 2025-02 unverdicted novelty 6.0

    UVA learns a joint video-action latent representation with decoupled diffusion decoding heads, enabling a single model to perform accurate fast policy learning, forward/inverse dynamics, and video generation without p...

  12. Latent Video Diffusion Models for High-Fidelity Long Video Generation

    cs.CV 2022-11 unverdicted novelty 6.0

    Latent-space hierarchical diffusion models with targeted error-correction techniques generate realistic videos exceeding 1000 frames while using less compute than prior pixel-space approaches.

  13. Language Models (Mostly) Know What They Know

    cs.CL 2022-07 unverdicted novelty 6.0

    Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.

  14. A General Language Assistant as a Laboratory for Alignment

    cs.CL 2021-12 conditional novelty 6.0

    Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.

  15. VideoGPT: Video Generation using VQ-VAE and Transformers

    cs.CV 2021-04 accept novelty 6.0

    VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.

  16. Scaling Laws for Transfer

    cs.LG 2021-02 unverdicted novelty 6.0

    Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.

  17. RoboNet: Large-Scale Multi-Robot Learning

    cs.RO 2019-10 conditional novelty 6.0

    RoboNet is a multi-robot video dataset that enables pre-training of vision-based manipulation models which, after fine-tuning on a new robot, outperform robot-specific training that uses 4-20 times more data.

  18. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

    cs.CV 2026-05 unverdicted novelty 5.0

    Causal Forcing++ applies causal consistency distillation to enable scalable frame-wise 1-2 step autoregressive video generation, outperforming prior 4-step chunk-wise methods on quality metrics while halving first-fra...

  19. VRAG: Learning World Models for Interactive Video Generation

    cs.CV 2025-05 unverdicted novelty 5.0

    The work introduces video retrieval augmented generation (VRAG) with explicit global state conditioning to reduce compounding errors and improve spatiotemporal consistency in interactive video world models.

  20. CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

    cs.CV 2022-05 unverdicted novelty 5.0

    CogVideo is a large-scale transformer pretrained for text-to-video generation that outperforms public models in evaluations.