Pith. sign in

REVIEW 6 cited by

Owl-1: Omni World Model for Consistent Long Video Generation

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 2412.09600 v1 pith:2CD3UBNP submitted 2024-12-12 cs.CV cs.AIcs.LG

Owl-1: Omni World Model for Consistent Long Video Generation

classification cs.CV cs.AIcs.LG
keywords videogenerationlongobservationsvideosworldmodelowl-1
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Video generation models (VGMs) have received extensive attention recently and serve as promising candidates for general-purpose large vision models. While they can only generate short videos each time, existing methods achieve long video generation by iteratively calling the VGMs, using the last-frame output as the condition for the next-round generation. However, the last frame only contains short-term fine-grained information about the scene, resulting in inconsistency in the long horizon. To address this, we propose an Omni World modeL (Owl-1) to produce long-term coherent and comprehensive conditions for consistent long video generation. As videos are observations of the underlying evolving world, we propose to model the long-term developments in a latent space and use VGMs to film them into videos. Specifically, we represent the world with a latent state variable which can be decoded into explicit video observations. These observations serve as a basis for anticipating temporal dynamics which in turn update the state variable. The interaction between evolving dynamics and persistent state enhances the diversity and consistency of the long videos. Extensive experiments show that Owl-1 achieves comparable performance with SOTA methods on VBench-I2V and VBench-Long, validating its ability to generate high-quality video observations. Code: https://github.com/huang-yh/Owl.

discussion (0)

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

Forward citations

Cited by 6 Pith papers

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

  1. GenHSI: Controllable Generation of Human-Scene Interaction Videos

    cs.CV 2025-06 unverdicted novelty 7.0

    GenHSI is a training-free three-stage pipeline that turns a scene image, character image, and complex HSI prompt into long videos with plausible chained interactions by generating atomic actions, 3D keyframes via 2D i...

  2. TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization

    cs.CV 2026-06 unverdicted novelty 6.0

    TivTok factorizes video clips into reusable time-invariant tokens and frame-specific time-variant tokens via Scope-Induced Factorization and Invariant Broadcasting, achieving 2.91x better compression for 128-frame vid...

  3. World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks

    cs.CV 2026-05 unverdicted novelty 6.0

    Proposes World-Ego Modeling with WEM using CP-MoE diffusion and a new HTEWorld benchmark, claiming SOTA on hybrid navigation-manipulation tasks.

  4. Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation

    cs.CV 2026-04 unverdicted novelty 6.0

    Long-CODE isolates long-context video evaluation with a new benchmark dataset and shot-dynamics metric that correlates better with human judgments on narrative richness and global consistency than short-video metrics.

  5. A Comprehensive Survey on World Models for Embodied AI

    cs.CV 2025-10 conditional novelty 6.0

    A unified three-axis taxonomy — functionality, temporal modeling, spatial representation — organizes the world-model literature for embodied AI.

  6. BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation

    cs.CV 2025-11 conditional novelty 5.0

    BlockVid generates minute-long videos with a semantic sparse KV cache, Block Forcing training, and chunk-level noise scheduling, reporting large gains on its own LV-Bench and on VBench.