pith. sign in

arxiv: 2504.19353 · v1 · pith:2QPDSNZGnew · submitted 2025-04-27 · 💻 cs.LG · cs.AI

Flow Along the K-Amplitude for Generative Modeling

classification 💻 cs.LG cs.AI
keywords k-flowgenerationamplitudeimageparameterscalingalongcoefficients
0
0 comments X
read the original abstract

In this work, we propose a novel generative learning paradigm, K-Flow, an algorithm that flows along the $K$-amplitude. Here, $k$ is a scaling parameter that organizes frequency bands (or projected coefficients), and amplitude describes the norm of such projected coefficients. By incorporating the $K$-amplitude decomposition, K-Flow enables flow matching across the scaling parameter as time. We discuss three venues and six properties of K-Flow, from theoretical foundations, energy and temporal dynamics, and practical applications, respectively. Specifically, from the practical usage perspective, K-Flow allows steerable generation by controlling the information at different scales. To demonstrate the effectiveness of K-Flow, we conduct experiments on unconditional image generation, class-conditional image generation, and molecule assembly generation. Additionally, we conduct three ablation studies to demonstrate how K-Flow steers scaling parameter to effectively control the resolution of image generation.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 4 Pith papers

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

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

    cs.LG 2026-04 unverdicted novelty 7.0

    Frequency-Forcing guides pixel flow-matching with a data-derived low-frequency auxiliary stream to softly enforce scale-ordered generation, improving FID on ImageNet-256 over baselines.

  2. A Minimal Model of Representation Collapse: Frustration, Stop-Gradient, and Dynamics

    cond-mat.dis-nn 2026-04 unverdicted novelty 7.0

    A minimal embedding model shows representation collapse arises from frustrated samples through slow dynamics and is prevented by stop-gradient.

  3. Spectral Progressive Diffusion for Efficient Image and Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    Spectral Progressive Diffusion accelerates image and video generation in pretrained diffusion models by progressively growing resolution along the denoising trajectory using spectral noise expansion and a power spectr...

  4. Spectral Progressive Diffusion for Efficient Image and Video Generation

    cs.CV 2026-05 unverdicted novelty 5.0

    Spectral Progressive Diffusion progressively grows resolution during denoising of pretrained diffusion models via spectral noise expansion and a power-spectrum-derived schedule, enabling training-free speedups and a f...