arXiv Machine Learning September 17, 2026 By Frantzeska Lavda, Maciej Falkiewicz, Van Khoa Nguyen, Alexandros Kalousis

Spatially Adaptive Noise Injection

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

diffusion

arXiv Computer Vision

Sep 2

ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory Hardware

arXiv:2609.00955v1 Announce Type: new Abstract: Diffusion models achieve strong image generation quality but incur high iterative denoising costs. Analog compute-in-memory (CIM) can accelerate matrix...

By Yuannuo Feng, Yizhe Chen, Wenshuai Yao, Yuxin Xie, Ngai Wong, Wenyong Zhou, Wang Kang

diffusion safety

arXiv AI

Aug 11

SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing

arXiv:2601. 19180v2 Announce Type: replace-cross Abstract: Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines.

By Lifan Jiang, Boxi Wu, Yuhang Pei, Tianrun Wu, Yongyuan Chen, Yan Zhao, Shiyu Yu, Deng Cai

computer-vision multimodal

arXiv Machine Learning

Sep 17

Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows

The paper introduces Contrastive Noise Alignment (CNA), a training-time method for generative flow models that dynamically aligns Gaussian noise with data samples using a cross-modal InfoNCE objective. By modeling noise as an interacting particle system and regularizing with angular entropy and radial norm penalties, CNA reduces arbitrary data-noise couplings and flow curvature. Empirical results show that CNA improves generation quality, lowering FID by over 50% for few-step pixel-space generation compared to standard rectified flow and outperforming optimal transport baselines by at least 24%.

By Lennart Wittke, Vinicius Azevedo

diffusion multimodal safety

arXiv Computer Vision

Sep 3

Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image Restoration

The paper introduces LEADer, a framework that uses local epistemic uncertainty to guide active sampling in diffusion-based image restoration. By adjusting prior strength per pixel and pruning sampling trajectories based on uncertainty traces, LEADer balances detail preservation with artifact suppression and accelerates convergence. The method is plug‑and‑play, theoretically guarantees data consistency and stable convergence, and improves performance across multiple state‑of‑the‑art diffusion models with minimal memory overhead.

By Jiaqi Zhang, Zheng Pang, Rongrong Gao, Qiyuan Zhang, Yang Yang

diffusion efficiency benchmarks

arXiv Machine Learning

Jun 10

Blind denoising diffusion models and the blessings of dimensionality

arXiv:2602. 09639v2 Announce Type: replace Abstract: Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline remain poorly understood.

By Zahra Kadkhodaie, Aram-Alexandre Pooladian, Sinho Chewi, Eero Simoncelli

rag diffusion benchmarks

arXiv AI

Jun 16

Region-Adaptive Sampling for Diffusion Transformers

arXiv:2502. 10389v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains.

By Ziming Liu, Yifan Yang, Chengruidong Zhang, Yiqi Zhang, Lili Qiu, Yang You, Yuqing Yang

llms diffusion