The paper proposes an energy‑adaptive noise scheduling and whitening strategy for transform‑domain diffusion models. By aligning the forward diffusion process with the spectral energy distribution of natural images, the method jointly modulates injected noise based on individual transform coefficient energy and an image‑dependent energy path over diffusion time. Experiments on CIFAR‑10 show that this approach reduces the Fréchet Inception Distance from 142.48 to 100.45 for a compact DCT‑diff U‑Net variant.
arXiv:2606. 03393v1 Announce Type: new Abstract: We propose a novel diffusion model, Flicker-DDPM, which incorporates flicker (1/f) noise inspired by self-organized criticality (SOC), a widely observed phenomenon in natural systems.
The paper introduces a total‑variance/signal‑to‑noise‑ratio (TV/SNR) framework that allows independent control of TV and SNR in diffusion models. By replacing exponentially exploding TV schedules with constant TV while keeping the SNR schedule, the authors achieve consistent improvements in generation efficiency. The approach generalizes the SNR schedule from optimal transport flow matching and works across various reverse diffusion solvers, reducing the search space to two interpretable parameters for robust sampling in scientific applications such as molecular structure generation.
arXiv:2502. 10389v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains.
arXiv:2607. 03517v1 Announce Type: new Abstract: Brownian Bridge Diffusion Models (BBDM) offer an appealing framework for image restoration and inverse problems by constructing a stochastic bridge from the clean signal directly to the degraded observation, rather than to pure noise.
arXiv:2606. 27696v1 Announce Type: cross Abstract: In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within diffusion models.
arXiv:2608.29227v1 Announce Type: new Abstract: In this work we propose a novel non-linear diffusion filtering approach for images based on their channel representation. To derive the diffusion updat...
The paper introduces an adaptive step schedule controller for text‑to‑image diffusion models, allowing the number of denoising steps to vary based on the complexity of the input prompt. By mixing step schedules of different sizes and monitoring error discrepancies at each timestep, the method switches schedules to maintain image quality while reducing inference time. Experiments on COCO and DiffusionDB demonstrate that this approach achieves faster generation without sacrificing visual fidelity.
arXiv:2605.21907v2 Announce Type: replace Abstract: Test-Time Scaling (TTS) paradigm offers a promising perspective for enhancing the generation performance of diffusion models. However, current solu...
Spatially Adaptive Noise Injection (SANI) is a new diffusion sampling framework that adjusts the amount of noise added at each pixel during reverse diffusion. Unlike traditional samplers that apply a uniform noise variance across the image, SANI uses a probabilistic gating mechanism to inject noise only where the denoiser is uncertain, such as edges and textures, while preserving smooth regions. Experiments show that SANI consistently improves Fréchet Inception Distance over vanilla DDPM and DDIM samplers across various timesteps, and remains competitive with variance‑learning baselines.
The paper introduces adaptive second‑order solvers for diffusion models, employing a proportional‑integral (PI) step‑size controller based on a diffusion noise‑normalised error estimator. Unlike existing adaptive methods that react only to the current error, the PI solver incorporates past error information, producing smoother step adaptations. The authors also demonstrate that per‑sample trajectories share structure, allowing aggregation into a fixed schedule that largely preserves adaptive benefits. Experiments on natural‑image and language datasets show that the fixed schedule outperforms the commonly used EDM schedule for image sampling with the stochastic Heun sampler, and that the PI adaptive solver achieves lower FID than most baselines, though it does not surpass the EDM‑churn sampler at low neural‑network‑evaluation counts. In language diffusion, the PI solver improves perplexity over EDM and entropy schedules at low‑to‑medium NFE, albeit with reduced token entropy. The study concludes that per‑sample adaptivity is highly beneficial for simple 1D toy problems but only marginally useful for image and language data, where an average schedule can sometimes outperform the PI‑adaptive approach.
arXiv:2605.08392v2 Announce Type: replace Abstract: Practical diffusion sampling requires simulating a reverse-time ODE or SDE with a limited number of denoising steps, making the choice of sampling...
arXiv:2608.29997v1 Announce Type: new Abstract: We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete dif...