Search: diffusion models

More than 1,000 papers match: here are the 1,000 most recent, ranked by relevance.

• Target Parameterization in Diffusion Models for Nonlinear Spatiotemporal System Identification

  Achraf El Messaoudi, Noureddine Khaous, Karim Cherifi · 21 April 2026 · Model Reduction and Neural Networks

  Machine learning is becoming increasingly important for nonlinear system identification, including dynamical systems with spatially distributed outputs. However, classical identification and forecasting approaches become markedly less reliable in turbulent-flow regimes, where the dynamics are high-d…

• Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

  Kijung Jeon, Michael Muehlebach, Molei Tao · 21 April 2026 · Markov Chains and Monte Carlo Methods

  Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.g., molecular generation, robotics). We present a unified framework for constrained diffusion models on generic nonconvex feasible sets $\Sigm…

• Grokking of Diffusion Models: Case Study on Modular Addition

  Joon Hyeok Kim, Yong-Hyun Park, Mattis Dals{\ae}tra {\O}stby, Jiatao Gu · 21 April 2026 · Generative Adversarial Networks and Image Synthesis

  Despite their empirical success, how diffusion models generalize remains poorly understood from a mechanistic perspective. We demonstrate that diffusion models trained with flow-matching objectives exhibit grokking--delayed generalization after overfitting--on modular addition, enabling controlled a…

• Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

  Jeongjae Lee, Jinho Chang, Jeongsol Kim, Jong Chul Ye · 21 April 2026 · Generative Adversarial Networks and Image Synthesis

  Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are motivated by different perspectives such as Soft RL, GFlowNets, etc., we show that many can be writte…

• Interpolating Discrete Diffusion Models with Controllable Resampling

  Marcel Kollovieh, Sirine Ayadi, Stephan G\"unnemann · 21 April 2026 · Machine Learning in Materials Science

  Discrete diffusion models form a powerful class of generative models across diverse domains, including text and graphs. However, existing approaches face fundamental limitations. Masked diffusion models suffer from irreversible errors due to early unmasking, while uniform diffusion models, despite e…

• Motion-Adapter: A Diffusion Model Adapter for Text-to-Motion Generation of Compound Actions

  Yue Jiang, Mingyu Yang, Liuyuxin Yang, Yang Xu, Bingxin Yun, Yuhe Zhang · 20 April 2026 · Human Motion and Animation

  Recent advances in generative motion synthesis have enabled the production of realistic human motions from diverse input modalities. However, synthesizing compound actions from texts, which integrate multiple concurrent actions into coherent full-body sequences, remains a major challenge. We identif…

• Efficient Video Diffusion Models: Advancements and Challenges

  Shitong Shao, Lichen Bai, Pengfei Wan, James Kwok, Zeke Xie · 20 April 2026 · Image and Video Quality Assessment

  Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis compounds computation across spatial-temporal token growth and …

• CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder

  Duy-Phuong Dao, Muhammad Taqiyuddin, Jahae Kim, Sang-Heon Lee, Hye-Won Jung, Jaehoo Choi, Hyung-Jeong Yang · 20 April 2026 · Generative Adversarial Networks and Image Synthesis

  Latent diffusion models have emerged as powerful generative models in medical imaging, enabling the synthesis of high quality brain magnetic resonance imaging scans. In particular, predicting the evolution of a patients brain can aid in early intervention, prognosis, and treatment planning. In this …

• Exploring the flavor structure of leptons via diffusion models

  Satsuki Nishimura, Hajime Otsuka, Haruki Uchiyama · 17 April 2026 · Neutrino Physics Research

  We propose a method to explore the flavor structure of leptons using diffusion models, which are known as one of generative artificial intelligence (generative AI). We consider a simple extension of the Standard Model with the type I seesaw mechanism and train a neural network to generate the neutri…

• An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation

  Onno Niemann, Gonzalo Mart\'inez Mu\~noz, Alberto Su\'arez Gonzalez · 17 April 2026 · Advanced Neuroimaging Techniques and Applications

  Recent work has shown that diffusion models trained with the denoising score matching (DSM) objective often violate the Fokker--Planck (FP) equation that governs the evolution of the true data density. Directly penalizing these deviations in the objective function reduces their magnitude but introdu…

• Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value

  Yixian Xu, Shengjie Luo, Liwei Wang, Di He, Chang Liu · 17 April 2026 · Forecasting Techniques and Applications

  Diffusion models have achieved remarkable success in generative modeling. Despite more stable training, the loss of diffusion models is not indicative of absolute data-fitting quality, since its optimal value is typically not zero but unknown, leading to confusion between large optimal loss and insu…

• Edge-preserving noise for diffusion models

  Jente Vandersanden, Sascha Holl, Xingchang Huang, Gurprit Singh · 17 April 2026 · Image and Signal Denoising Methods

  Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information important for high-quality generation. We introduce an edge-preserving diffusion process that generalizes isotropic models via a hybrid noise scheme with an ed…

• Diffusion Crossover: Defining Evolutionary Recombination in Diffusion Models via Noise Sequence Interpolation

  Chisatao Kumada, Satoru Hiwa, Tomoyuki Hiroyasu · 17 April 2026 · Generative Adversarial Networks and Image Synthesis

  Interactive Evolutionary Computation (IEC) provides a powerful framework for optimizing subjective criteria such as human preferences and aesthetics, yet it suffers from a fundamental limitation: in high-dimensional generative representations, defining crossover in a semantically consistent manner i…

• Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model

  Shuyun Wang, Hu Zhang, Xin Shen, Dadong Wang, Xin Yu · 16 April 2026 · Generative Adversarial Networks and Image Synthesis

  Bitstream-corrupted video recovery aims to restore realistic content degraded during video storage or transmission. Existing methods typically assume that predefined masks of corrupted regions are available, but manually annotating these masks is labor-intensive and impractical in real-world scenari…

• Monthly Diffusion v0.9: A Latent Diffusion Model for the First AI-MIP

  Kyle J. C. Hall, Maria J. Molina · 16 April 2026 · Meteorological Phenomena and Simulations

  Here, we describe Monthly Diffusion at 1.5-degree grid spacing (MD-1.5 version 0.9), a climate emulator that leverages a spherical Fourier neural operator (SFNO)-inspired Conditional Variational Auto-Encoder (CVAE) architecture to model the evolution of low-frequency internal atmospheric variability…

• Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation

  Auguste de Lambilly, Vladimir Baturin, David Portehault, Guillaume Lambard, Nataliya Sokolovska, Florence d'Alch\'e-Buc, Jean-Claude Crivello · 16 April 2026 · Machine Learning in Materials Science

  The discovery of inorganic crystal structures with targeted properties is a significant challenge in materials science. Generative models, especially state-of-the-art diffusion models, offer the promise of modeling complex data distributions and proposing novel, realistic samples. However, current g…

• OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner

  Haoyang Jiang, Zekun Wang, Mingyang Yi, Xiuyu Li, Lanqing Hu, Junxian Cai, Qingbin Liu, Xi Chen, Ju Fan · 15 April 2026 · Generative Adversarial Networks and Image Synthesis

  The Diffusion Probabilistic Model (DPM) achieves remarkable performance in image generation, while its increasing parameter size and computational overhead hinder its deployment in practical applications. To improve this, the existing literature focuses on obtaining a smaller model with a fixed arch…

• StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation

  Yinxi He, Kang Liao, Chunyu Lin, Tianyi Wei, Yao Zhao · 15 April 2026 · Generative Adversarial Networks and Image Synthesis

  This paper introduces StructDiff, a generative framework based on a single-scale diffusion model for single-image generation. Single-image generation aims to synthesize diverse samples with similar visual content to the source image by capturing its internal statistics, without relying on external d…

• Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling

  Zida Li, Jun Li, Yuzhe Sha, Ziqiang Li, Lizhi Xiong, Zhangjie Fu · 15 April 2026 · Adversarial Robustness in Machine Learning

  Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks. Existing defenses, particularly input-level methods, are more practical for deployment but often rely on ob…

• NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models

  Nir Goren, Oren Katzir, Abhinav Nakarmi, Eyal Ronen, Mahmood Sharif, Or Patashnik · 15 April 2026 · Privacy-Preserving Technologies in Data

  With the rapid adoption of diffusion models for visual content generation, proving authorship and protecting copyright have become critical. This challenge is particularly important when model owners keep their models private and may be unwilling or unable to handle authorship issues, making third-p…

• Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data

  Farbod Alinezhad, Jianfei Cao, Gary J. Young, Brady Post · 15 April 2026 · Advanced Causal Inference Techniques

  Predicting counterfactual outcomes in longitudinal data, where sequential treatment decisions heavily depend on evolving patient states, is critical yet notoriously challenging due to complex time-dependent confounding and inadequate uncertainty quantification in existing methods. We introduce the C…

• StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback

  Jiho Park, Sieun Choi, Jaeyoon Seo, Jihie Kim · 15 April 2026 · Multimodal Machine Learning Applications

  Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizing pixel-based human-drawn sketches, a representative example of abstract expression. To combat these challenges, we propose StableSketcher, a novel framework …

• Characterizing higher-order representations through generative diffusion models explains human decoded neurofeedback performance

  Hojjat Azimi Asrari, Megan A. K. Peters · 15 April 2026 · Neural Networks and Applications

  Brains construct not only "first-order" representations of the environment but also "higher-order" representations about those representations -- including higher-order uncertainty estimates that guide learning and adaptive behavior. Higher-order expectations about representational uncertainty -- i.…

• SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models

  You Qin, Linqing Wang, Hao Fei, Roger Zimmermann, Liefeng Bo, Qinglin Lu, Chunyu Wang · 15 April 2026 · Generative Adversarial Networks and Image Synthesis

  The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on ground-truth states sampled from the forward noising process…

• Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models

  Jinhui Hou, Zhiyu Zhu, Junhui Hou · 14 April 2026 · Advanced Image Processing Techniques

  Diffusion bridge models have shown great promise in image restoration by explicitly connecting clean and degraded image distributions. However, they often rely on complex and high-cost trajectories, which limit both sampling efficiency and final restoration quality. To address this, we propose an En…