FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring

• URL: http://arxiv.org/abs/2607.27110v2
• Date: Mon, 03 Aug 2026 12:29:16 GMT
• Title: FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring
• Abstract summary: We propose FreqForcing, a training-free framework that addresses error accumulation in long-video generation via Spectral Self-Anchoring (SSA)<n>Our FreqForcing extends Self-Forcing pretrained on 5s clips to two-minute generation, achieving 24x extrapolation.
• Score: 38.650762310010734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive video diffusion models enable real-time streaming video generation. However, errors introduced during self-rollout accumulate over long horizons, manifesting as color drift, motion stagnation, and eventual visual collapse. In this paper, we characterize this phenomenon from a frequency-domain perspective: error accumulation appears as a pronounced energy drift in the low-frequency bands. We further investigate the effectiveness of attention sink in the frequency domain, and find that it improves the video quality by alleviating the spectral energy drift to some extent, but cannot fully resolve it. Motivated by the above analysis, we propose FreqForcing, a training-free framework that addresses error accumulation in long-video generation via Spectral Self-Anchoring (SSA). The proposed SSA leverages the low-frequency components of anchor attention to maintain long-horizon visual stability, while preserving dynamic motion through the high-frequency components of local attention. Our FreqForcing extends Self-Forcing pretrained on 5s clips to two-minute generation, achieving 24x extrapolation. Extensive experiments show that FreqForcing outperforms existing training-free methods quantitatively and qualitatively while remaining competitive with representative training-based approaches.

Related papers

• SAGA: Stable Acceleration Guidance for Autoregressive Video Generation [17.967260849031593]
  We propose SAGA, a training-free textbftextitstable textbftextitautoregressive video generation approach.<n>SAGA integrates an acceleration domain spectral guidance objective based on finite-window Slepian projections.<n>Experiments show that SAGA consistently improves temporal quality across multiple autoregressive diffusion models.
  arXiv  Detail & Related papers  (2026-07-09T00:55:10Z)
• SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition [49.508770157706486]
  We propose SRENet to learn both global context and fine-grained temporal dynamics of motion from a frequency perspective for action recognition.<n>SRENet achieves state-of-the-art performance, validating the effectiveness of frequency modeling in point cloud-based action understanding.
  arXiv  Detail & Related papers  (2026-06-02T05:11:47Z)
• 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)
• FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction [28.81130393371554]
  Video diffusion models perform well in short-video synthesis, but suffer from content drift, temporal inconsistency, and over-smoothed dynamics.<n>We propose FreeSpec, a training-free spectral reconstruction framework for long-video generation.<n>Experiments on Wan2.1 and LTX-Video demonstrate that FreeSpec improves long-video generation, especially for temporal dynamics.
  arXiv  Detail & Related papers  (2026-05-07T16:21:34Z)
• Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation [15.110494847628212]
  FLEX is a training-free inference-time framework that bridges the gap between short-term training and long-term inference.<n>It significantly outperforms state-of-the-art models at 6x extrapolation (30s duration) and matches the performance of long-video fine-tuned baselines at 12x scale (60s duration)<n>As a plug-and-play augmentation, FLEX seamlessly integrates into existing inference pipelines for horizon extension.
  arXiv  Detail & Related papers  (2026-02-15T07:14:47Z)
• 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)
• Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression [36.99018442740971]
  We find that naively applying StreamingLLM-style attention sinks to video diffusion leads to fidelity degradation and motion stagnation.<n>We introduce Deep Forcing, which consists of two training-free mechanisms that address this without any fine-tuning.<n>Our results demonstrate that training-free KV-cache management can match or exceed training-based approaches for autoregressively streaming long-video generation.
  arXiv  Detail & Related papers  (2025-12-04T18:46:44Z)
• DiTVR: Zero-Shot Diffusion Transformer for Video Restoration [48.97196894658511]
  DiTVR is a zero shot video restoration framework that couples a diffusion transformer with trajectory aware attention and a flow consistent sampler.<n>Our attention mechanism aligns tokens along optical flow trajectories, with particular emphasis on vital layers that exhibit the highest sensitivity to temporal dynamics.<n>The flow guided sampler injects data consistency only into low-frequency bands, preserving high frequency priors while accelerating cache.
  arXiv  Detail & Related papers  (2025-08-11T09:54:45Z)
• FANeRV: Frequency Separation and Augmentation based Neural Representation for Video [32.35716293561769]
  We present a Frequency Separation and Augmentation based Neural Representation for video (FANeRV)<n>FANeRV explicitly separates input frames into high and low-frequency components using discrete wavelet transform.<n>A specially designed gated network effectively fuses these frequency components for optimal reconstruction.
  arXiv  Detail & Related papers  (2025-04-09T10:19:35Z)
• FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention [57.651429116402554]
  This paper investigates a straightforward and training-free approach to extend an existing short video diffusion model for consistent long video generation. We find that directly applying the short video diffusion model to generate long videos can lead to severe video quality degradation. Motivated by this, we propose a novel solution named FreeLong to balance the frequency distribution of long video features during the denoising process.
  arXiv  Detail & Related papers  (2024-07-29T11:52:07Z)

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.