Search: diffusion models

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

• Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

  Joan Serr\`a, Dipam Goswami, Fabio Morreale, Wei-Hsiang Liao, Yuki Mitsufuji · 19 May 2026 · Generative Adversarial Networks and Image Synthesis

  Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliability and robustness, preventing their adoption in real-world setups. In this paper, we take a decisive step towards more r…

• DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data

  Masahiro Suzuki, Bohui Xia, Hiroto Yamamoto, Masanori Miyahara · 19 May 2026 · Forecasting Techniques and Applications

  Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitation in generating meaningful data. To address this limitation, we propose DAD4TS, a diffusion-model-based data augmentation method with reinforcement…

• Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization

  Yuan Xue, Daniel Kudenko, Megha Khosla · 19 May 2026 · Computational Drug Discovery Methods

  Structure-based drug design has been accelerated by pocket-aware 3D generative models, yet most methods primarily fit the training distribution and may fall short of satisfying multiple properties required in real-world therapeutic drug discovery. Recently, increasing attention has focused on struct…

• Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space

  Kelvin Kan, Xingjian Li, Benjamin J. Zhang, Tuhin Sahai, Stanley Osher, Markos A. Katsoulakis · 19 May 2026 · Language Development and Disorders

  Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology. Existing convergence theory, however, exhibits fundamental limitations. KL-based analyses diverge under singular priors such as the masked distribution, while bo…

• Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra

  Yoichi Ochiai · 19 May 2026 · Cell Image Analysis Techniques

  While real-time image generation using diffusion models has advanced rapidly on NVIDIA GPUs, systematic optimization research on non-CUDA platforms such as Apple Silicon remains extremely limited. In this study, we conducted comprehensive optimization experiments across 10 phases targeting the Apple…

• Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?

  Renye Yan, Jikang Cheng, Shikun Sun, Yi Sun, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Junliang Xing, Yimao Cai · 18 May 2026 · Generative Adversarial Networks and Image Synthesis

  Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignment through explicit rewards. However, most studies apply RL to the full denoising trajectory, making it computationally costly and weakening prefere…

• Autoguided Online Data Curation for Diffusion Model Training

  Valeria Pais, Luis Oala, Daniele Faccio, Marco Aversa · 18 May 2026 · Generative Adversarial Networks and Image Synthesis

  The costs of generative model compute rekindled promises and hopes for efficient data curation. In this work, we investigate whether recently developed autoguidance and online data selection methods can improve the time and sample efficiency of training generative diffusion models. We integrate join…

• Uncertainty Quantification for Large Language Diffusion Models

  Artem Vazhentsev, Vladislav Smirnov, David Li, Maxim Panov, Timothy Baldwin, Artem Shelmanov · 15 May 2026 · Generative Adversarial Networks and Image Synthesis

  Large Language Diffusion Models (LLDMs) are emerging as an alternative to autoregressive models, offering faster inference through higher parallelism. Similar to autoregressive LLMs, they remain prone to hallucinations, making reliable uncertainty quantification (UQ) crucial for safe deployment. How…

• ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models

  Ledun Zhang, Yatu Ji, Xufei Zhuang, Xinying Yao · 15 May 2026 · Generative Adversarial Networks and Image Synthesis

  Existing object removal tools often rely on manual masks or text prompts, making precise removal difficult for non-expert users in complex scenes and often leading to incomplete removal or unnatural background completion. To address this issue, we present ClickRemoval, an open-source interactive obj…

• IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model

  Yifan Chen, Fei Yin, Chunle Guo, Chongyi Li, Yujiu Yang · 15 May 2026 · Image Enhancement Techniques

  In nighttime circumstances, it is challenging for individuals and machines to perceive their surroundings. While prevailing image restoration methods adeptly handle singular forms of degradation, they falter when confronted with intricate nocturnal scenes, such as the concurrent presence of weather …

• Image Restoration via Diffusion Models with Dynamic Resolution

  Yang Zheng, Wen Li, Zhaoqiang Liu · 15 May 2026 · Advanced Image Processing Techniques

  Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods based on latent DMs seek to alleviate this issue by utilizing …

• Covariance-aware sampling for Diffusion Models

  Andrea Schioppa, Tim Salimans · 15 May 2026 · Generative Adversarial Networks and Image Synthesis

  We present a covariance-aware sampler that improves the quality of pixel-space Diffusion Model (DM) sampling in the few-step regime. We hypothesize that in the few-step regime samplers fail because they rely solely on the predicted mean of the reverse distribution, while our solution explicitly mode…

• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

  Quanhao Li, Junqiu Yu, Kaixun Jiang, Yujie Wei, Zhen Xing, Pandeng Li, Ruihang Chu, Shiwei Zhang, Yu Liu, Zuxuan Wu · 15 May 2026 · Domain Adaptation and Few-Shot Learning

  Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while …

• Learning to Optimize Radiotherapy Plans via Fluence Maps Diffusion Model Generation and LSTM-based Optimization

  Isabella Poles, Simon Arberet, Riqiang Gao, Martin Kraus, Marco D. Santambrogio, Florin C. Ghesu, Ali Kamen, Dorin Comaniciu · 14 May 2026 · Advanced Radiotherapy Techniques

  Volumetric Modulated Arc Therapy (VMAT) is a cornerstone of modern radiation therapy, enabling highly conformal tumor irradiation and healthy-tissue sparing. Yet, its planning solves inverse and nested optimization for multi-leaf collimators, monitor units and dose parameters, while enforcing their …

• Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold

  Ye He, Yitong Qiu, Molei Tao · 14 May 2026 · Generative Adversarial Networks and Image Synthesis

  We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated samples go relative to the geometry induced by the data? To answer this, we introduce a time-dependent family of log-density ridge manifolds constructed from th…

• On the Limits of Latent Reuse in Diffusion Models

  Yifeng Yu, Lu Yu · 14 May 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models are often trained in low-dimensional latent spaces, which are then reused for related but shifted datasets. In this work, we study when such latent reuse remains reliable under distribution shift. We consider a source-target setting in which both datasets are approximately low-dimen…

• DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense

  Ziyang You, Liling Zheng, Xiaoke Yang, Xuxing Lu · 14 May 2026 · Chaos-based Image/Signal Encryption

  Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor attack that hijacks the PRNG to deterministically control generated images. A malicious PRNG, injected via compromised packages, forces pixel-perfect repr…

• Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms

  Heehwan Wang, Joonwoo Kwon, Sooyoung Kim, Jungwoo Seo, Shinjae Yoo, Yuewei Lin, Jiook Cha · 14 May 2026 · Music and Audio Processing

  Music style transfer blends source structure with reference style to enable personalized music creation. However, existing zero-shot methods often struggle to capture fine-grained audio nuances, relying on coarse text descriptions or requiring expensive task-specific training. We propose Stylus, a t…

• AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

  Yuchao Gu, Guian Fang, Yuxin Jiang, Weijia Mao, Song Han, Han Cai, Mike Zheng Shou · 14 May 2026 · Domain Adaptation and Few-Shot Learning

  Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness for any-step video diffusion. This limitation arises because …

• Amortized Guidance for Image Inpainting with Pretrained Diffusion Models

  Yilie Huang, Xun Yu Zhou · 14 May 2026 · Generative Adversarial Networks and Image Synthesis

  We study image inpainting with generative diffusion models. Existing methods typically either train dedicated task-specific models, or adapt a pretrained diffusion model separately for each masked image at deployment. We introduce a middle-ground model, termed Amortized Inpainting with Diffusion (AI…

• The critical slowing down in diffusion models

  Luca Maria Del Bono, Giulio Biroli, Patrick Charbonneau, Marylou Gabri\'e · 14 May 2026 · Quantum many-body systems

  Computational sampling has been central to the sciences since the mid-20th century. While machine-learning-based approaches have recently enabled major advances, their behavior remains poorly understood, with limited theoretical control over when and why they succeed. Here we provide such insight fo…

• Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation

  Aniketh Iyengar, Jiaqi Han, Boris Ruf, Vincent Grari, Marcin Detyniecki, Stefano Ermon · 14 May 2026 · Green IT and Sustainability

  The rapidly growing computational demands of diffusion models for image generation have raised significant concerns about energy consumption and environmental impact. While existing approaches to energy optimization focus on architectural improvements or hardware acceleration, there is a lack of pri…

• Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks

  Daniil Dushenev, Nazariy Karpov, Daniil Zinovjev, Alexander Gorin, Konstantin Kulikov · 13 May 2026 · Domain Adaptation and Few-Shot Learning

  Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a lightweight synthetic data augmentation pipeline that fine-tunes a LoRA adapter on as…

• STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models

  Ankit Yadav, Arpit Garg, Ta Duc Huy, Lingqiao Liu · 13 May 2026 · Generative Adversarial Networks and Image Synthesis

  Distilled one-step (T=1) or few-step (T$\leq$4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to their multi-step counterparts. In multi-step diffusion, diversity can be introduced through schedules, trajectories, or iterative optimization; ho…

• ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models

  Hai Jiang, Zhen Liu, Yinjie Lei, Songchen Han, Bing Zeng, Shuaicheng Liu · 13 May 2026 · Image Enhancement Techniques

  In this paper, we propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination degradation image restoration, which decouples the restoration process into adaptive illumination correction and diffusion-based reconstruction while being trained solely on low-quality degraded im…