Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency

• URL: http://arxiv.org/abs/2607.11836v1
• Date: Mon, 13 Jul 2026 17:27:13 GMT
• Title: Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency
• Abstract summary: Cycle-World is a framework designed for stable and temporally consistent long-video generation.<n>Our approach tackles error drift by enforcing strict temporal reversibility across both the training and inference phases.<n>Experiments on the VBench benchmark demonstrate that Cycle-World's dual-phase synergy significantly mitigates error drift.
• Score: 123.12549538776109
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive diffusion models have enabled high-quality video generation, yet their sequential nature inherently suffers from error accumulation. In long-horizon video synthesis, minor prediction deviations compound over time, inevitably leading to unconstrained generative drift, structural collapse, and severe visual degradation. To address this, we propose Cycle-World, a novel framework designed for stable and temporally consistent long-video generation. Our approach tackles error drift by enforcing strict temporal reversibility across both the training and inference phases. Theoretically, we demonstrate that forward generative drift can be strictly bottlenecked by a cycle-consistency objective. During training, we integrate an efficient reverse-prediction model to implicitly embed causal constraints into the forward generator, compelling it to produce reversible sequences that tightly adhere to the natural video manifold. At inference time, we repurpose this frozen reverse model as a runtime corrector. Through gradient-based cycle guidance, it iteratively refines the generated latent representations, actively suppressing accumulated errors before they are committed to the historical context. Extensive experiments on the VBench benchmark demonstrate that Cycle-World's dual-phase synergy significantly mitigates error drift, achieving state-of-the-art overall generation quality and long-horizon temporal consistency in 60-second synthesis.

Related papers

• FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching [68.01498128172214]
  We propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training.<n>Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via emphTweedie matching to enforce both textbfmanifold constraint and temporal consistency across overlap regions.<n>Our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any
  arXiv  Detail & Related papers  (2026-05-20T08:55:37Z)
• Can Video Diffusion Models Predict Past Frames? Bidirectional Cycle Consistency for Reversible Interpolation [25.677744104220853]
  Video frame aims to synthesize realistic intermediate frames between given endpoints while adhering to specific motion semantics.<n>We propose a novel bidirectional framework that enforces symmetry between forward and backward generation trajectories.<n>Our method achieves state-of-the-art performance in imaging quality, motion smoothness, and dynamic control on both 37-frame and 73-frame tasks.
  arXiv  Detail & Related papers  (2026-04-02T06:58:46Z)
• Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation [43.89162138967428]
  We propose a novel distillation framework tailored specifically for video diffusion models.<n>Its core innovations include: (1) an adaptive regression loss that dynamically adjusts spatial supervision weights to prevent artifacts arising from excessive distribution shifts; (2) a temporal regularization loss that promotes smooth and physically plausible sampling trajectories; and (3) an inference-time frame strategy that reduces sampling overhead while preserving perceptual quality.<n>Experiments and ablation studies on the VBench and VBench2 benchmarks demonstrate that our method achieves stable few-step video synthesis, significantly enhancing perceptual fidelity and motion realism.
  arXiv  Detail & Related papers  (2026-03-23T11:54:33Z)
• HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising [52.237486207964245]
  HiAR is a hierarchical denoising framework that reverses the conventional generation order.<n>It performs causal generation across all blocks at every denoising step, so that each block is always conditioned on context at the same noise level.<n>On VBench (20s generation), HiAR achieves the best overall score and the lowest temporal drift among all compared methods.
  arXiv  Detail & Related papers  (2026-03-09T17:58:16Z)
• TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation [45.36298679288268]
  Auto-regressive video generation enables long video synthesis by iteratively conditioning each new batch of frames on previously generated content.<n>Recent work has shown that such pipelines suffer from severe temporal drift, where errors accumulate and amplify over long horizons.<n>We propose a simple, inference-time method that mitigates temporal drift by identifying and removing unstable latent tokens before they are reused for conditioning.
  arXiv  Detail & Related papers  (2026-01-30T19:44:16Z)
• LoL: Longer than Longer, Scaling Video Generation to Hour [50.945885467651216]
  This work achieves the first demonstration of real-time, streaming, and infinite-length video generation with little quality decay.<n>As an illustration, we generate continuous videos up to 12 hours in length, which, to our knowledge, is among the longest publicly demonstrated results in streaming video generation.
  arXiv  Detail & Related papers  (2026-01-23T17:21:35Z)
• End-to-End Training for Autoregressive Video Diffusion via Self-Resampling [63.84672807009907]
  Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch.<n>We introduce Resampling Forcing, a teacher-free framework that enables training autoregressive video models from scratch and at scale.
  arXiv  Detail & Related papers  (2025-12-17T18:53:29Z)
• BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models [50.986189632485285]
  We introduce Backwards Aggregation (BAgger), a self-supervised scheme that constructs corrective trajectories from the model's own rollouts.<n>Unlike prior approaches that rely on few-step distillation and distribution-matching losses, BAgger trains with standard score or flow matching objectives.<n>We instantiate BAgger on causal diffusion transformers and evaluate on text-to-video, video extension, and multi-prompt generation.
  arXiv  Detail & Related papers  (2025-12-12T23:02:02Z)
• AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion [19.98565541640125]
  We introduce Auto-Regressive Diffusion (AR-Diffusion), a novel model that combines the strengths of auto-regressive and diffusion models for flexible video generation.<n>Inspired by auto-regressive generation, we incorporate a non-decreasing constraint on the corruption timesteps of individual frames.<n>This setup, together with temporal causal attention, enables flexible generation of videos with varying lengths while preserving temporal coherence.
  arXiv  Detail & Related papers  (2025-03-10T15:05:59Z)
• Intrinsic Temporal Regularization for High-resolution Human Video Synthesis [59.54483950973432]
  temporal consistency is crucial for extending image processing pipelines to the video domain. We propose an effective intrinsic temporal regularization scheme, where an intrinsic confidence map is estimated via the frame generator to regulate motion estimation. We apply our intrinsic temporal regulation to single-image generator, leading to a powerful " INTERnet" capable of generating $512times512$ resolution human action videos.
  arXiv  Detail & Related papers  (2020-12-11T05:29:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.