Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance

• URL: http://arxiv.org/abs/2604.20902v1
• Date: Tue, 21 Apr 2026 17:00:16 GMT
• Title: Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance
• Abstract summary: We propose Frequency-Forcing, which realizes frequency ordering through an auxiliary low-frequency stream that matures earlier in time.<n>Unlike Latent Forcing, our frequency scratchpad is derived from the data itself via a lightweight learnable wavelet packet transform.<n>On ImageNet-256, Frequency-Forcing consistently improves FID over strong pixel- and latent-space baselines, and naturally composes with a semantic stream to yield further gains.
• Score: 5.433581405393181
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse, low-frequency structure before fine detail - has proven highly effective for synthesizing natural images. Two recent works offer distinct paradigms for this. K-Flow imposes a hard frequency constraint by reinterpreting a frequency scaling variable as flow time, running the trajectory inside a transformed amplitude space. Latent Forcing provides a soft ordering mechanism by coupling the pixel flow with an auxiliary semantic latent flow via asynchronous time schedules, leaving the pixel interpolation path itself untouched. Viewed from the angle of improving pixel generation, we observe that forcing - guiding generation with an earlier-maturing auxiliary stream - offers a highly compatible route to scale-ordered generation without rewriting the core flow coordinate. Building on this, we propose Frequency-Forcing, which realizes K-Flow's frequency ordering through Latent Forcing's soft mechanism: a standard pixel flow is guided by an auxiliary low-frequency stream that matures earlier in time. Unlike Latent Forcing, whose scratchpad relies on a heavy pretrained encoder (e.g., DINO), our frequency scratchpad is derived from the data itself via a lightweight learnable wavelet packet transform. We term this a self-forcing signal, which avoids external dependencies while learning a basis better adapted to data statistics than the fixed bases used in hard frequency flows. On ImageNet-256, Frequency-Forcing consistently improves FID over strong pixel- and latent-space baselines, and naturally composes with a semantic stream to yield further gains. This illustrates that forcing-based scale ordering is a versatile, path-preserving alternative to hard frequency flows.

Related papers

• Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion [46.51681899437508]
  We introduce Spectral Forcing, a parameter-free, time-conditional 2D-DCT low-pass operator applied to the noisy input before the patch embedder.<n>Its cutoff expands monotonically with the diffusion time and becomes the identity at the data endpoint.<n>On ImageNet-256 with JiT-700M/32, Spectral Forcing consistently improves both FID and Inception Score across different training epochs.
  arXiv  Detail & Related papers  (2026-06-13T10:29:11Z)
• RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling [51.279397568734424]
  Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis.<n>DiTs suffer from high inference latency and computational costs due to the quadratic complexity of 3D attention.<n>We introduce bftextRhymeFlow, a training-free framework that decouples the denoising trajectories of different frames.
  arXiv  Detail & Related papers  (2026-06-04T15:49:37Z)
• WPGRec: Wavelet Packet Guided Graph Enhanced Sequential Recommendation [9.195401107720498]
  Sequential recommendation aims to model users' evolving interests from noisy and non-stationary interaction streams.<n>We propose Wavelet Packet Guided Graph Enhanced Sequential Recommendation (WPGRec)<n>WPGRec applies a full-tree undecimated stationary wavelet packet transform to generate equal-length, shift-invariant subband sequences.<n>It then performs subband-wise interaction-graph propagation to inject high-order collaborative information.
  arXiv  Detail & Related papers  (2026-04-23T05:44:26Z)
• Frequency-Aware Flow Matching for High-Quality Image Generation [40.59308529513355]
  Flow matching models have emerged as a powerful framework for realistic image generation.<n>We propose Frequency-Aware Flow Matching, which explicitly incorporates frequency-aware conditioning into the flow matching framework.<n>Our method achieves state-of-the-art performance with an FID of 1.38, surpassing the prior diffusion model DiT and flow matching model SiT by 0.79 and 0.58 FID, respectively.
  arXiv  Detail & Related papers  (2026-04-16T21:00:41Z)
• KoopmanFlow: Spectrally Decoupled Generative Control Policy via Koopman Structural Bias [31.486395926173838]
  Generative Control Policies (GCPs) show immense promise in robotic manipulation but struggle to simultaneously model stable global motions and high-frequency local corrections.<n>We introduce KoopmanFlow, a parameter-efficient generative policy guided by a Koopman-inspired structural inductive bias.
  arXiv  Detail & Related papers  (2026-03-14T06:23:07Z)
• 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)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems [51.15230303652732]
  FLEX (F Low EXpert) is a backbone architecture for generative modeling of-temporal physical systems.<n>It reduces the variance of the velocity field in the diffusion model, which helps stabilize training.<n>It achieves accurate predictions for super-resolution and forecasting tasks using as few features as two reverse diffusion steps.
  arXiv  Detail & Related papers  (2025-05-23T00:07:59Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided Diffusion [2.3874115898130865]
  We will propose a new zero-shot low-light enhancement method to compensate for the lack of light and structural information in the diffusion sampling process. The inspiration comes from the similarity between the wavelet and Fourier frequency domains. Sufficient experiments show that the framework is robust and effective in various scenarios.
  arXiv  Detail & Related papers  (2024-11-21T09:16:51Z)
• StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation [52.56469577812338]
  We introduce StreamDiffusion, a real-time diffusion pipeline for interactive image generation.<n>Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction.<n>We present a novel approach that transforms the original sequential denoising into the denoising process.
  arXiv  Detail & Related papers  (2023-12-19T18:18:33Z)

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.