Search: diffusion models

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

• Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

  Shuchen Xue, Chongjian Ge, Shilong Zhang, Yichen Li, Zhi-Ming Ma · 2 September 2026 · Game Theory and Voting Systems

  Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where both pre-training and RL post-training stages are grounded in the same log-likelihood formulation. In contrast, recent RL approaches for diffusion models, most notably Denoising Diffusion …

• Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture

  Shuchen Xue, Tianyu Xie, Tianyang Hu, Zijin Feng, Jiacheng Sun, Kenji Kawaguchi, Zhenguo Li, Zhi-Ming Ma · 2 September 2026 · Stochastic processes and financial applications

  Efficiently scaling Large Language Models (LLMs) necessitates exploring alternatives to dominant autoregressive (AR) methods, with Masked Diffusion Models (MDMs) emerging as candidates. However, comparing AR (typically decoder-only) and MDM (often encoder-only) paradigms is confounded by differing a…

• Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training

  Luca Ciampi, Gabriele Lagani, Giuseppe Amato, Fabrizio Falchi · 2 September 2026 · Medical Image Segmentation Techniques

  Supervised deep learning achieves strong performance in biomedical image segmentation but relies on costly pixel-wise annotations, motivating semi-supervised approaches that exploit unlabeled data. We introduce a diffusion-based teacher--student framework in which segmentation predictions are used t…

• P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image Enhancement

  Ruoyu Guo, Haonan Zhong, Maurice Pagnucco, Yang Song · 2 September 2026 · Image Enhancement Techniques

  Recent advancements in low-light image enhancement have leveraged diffusion models for their strong ability to generate perceptually realistic, detailed images. Patch diffusion models further offer a promising solution to size-agnostic image restoration while improving efficiency. However, existing …

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

  Yuannuo Feng, Yizhe Chen, Wenshuai Yao, Yuxin Xie, Ngai Wong, Wenyong Zhou, Wang Kang · 2 September 2026 · Advanced Mathematical Modeling in Engineering

  Diffusion models achieve strong image generation quality but incur high iterative denoising costs. Analog compute-in-memory (CIM) can accelerate matrix-vector multiplications, yet spatial memory variations perturb weights and accumulate during sampling. Unlike conventional neural networks, diffusion…

• Training-Free Inpainting Across Domains with a Frozen Text-to-Image Diffusion Model

  Zhenhuan Wang, Fengyi Yuan · 2 September 2026 · Generative Adversarial Networks and Image Synthesis

  We show that a frozen generic text-to-image diffusion model can perform conditional inpainting across three evaluated natural-image domains with one fixed controller configuration, without inpainting-specific weight training, dataset-specific weight adaptation, or learned inpainting-specific conditi…

• Advanced Pixel Diffusion Model with Guided Sparse Global Refinement

  Weiyi You, Jinhua Zhang, Xingyu Zhou, Wei Long, Junyu Lou, Shuhang Gu · 2 September 2026 · Advanced Image Processing Techniques

  Pixel-space diffusion has recently emerged as a promising direction for high-fidelity image generation by modeling images directly in the original pixel domain. However, pixel-space diffusion is computationally demanding due to the extremely high dimensionality of natural images. For efficiency, exi…

• EarthLD: Towards Unified Open-World Landslide Understanding via Vision-Language Guided Diffusion Models

  Yuanchao Su, Lianru Gao, Mengying Jiang, Jiangyi Chen, Jiaxin Cheng, Yicong Zhou · 2 September 2026 · Landslides and related hazards

  Landslides are widespread geological hazards, yet their automated detection and mapping in remote sensing imagery remain challenging because of their irregular morphology, ambiguous spectral signatures, and substantial domain shifts across imaging platforms. To overcome these challenges, we propose …

• TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models

  Chao Zhou, Yiling Chen, Qi Chu, Tao Gong, Nenghai Yu, Tianyi We · 2 September 2026 · Speech and Audio Processing

  Although pretrained joint audio-visual diffusion models offer rich control over \emph{what} to generate, they provide no explicit control over \emph{when} an utterance should occur. To address this, we study \emph{inference-time speech scheduling}, a novel task that places coupled speech and visual …

• Conditional Diffusion Models for Energy-Efficient Driving

  Hemanth Neelgund Ramesh, Andr\'e Snoeck, Chyi-Fu Hong, Shijing Sun · 31 August 2026 · Electric Vehicles and Infrastructure

  Electrification of commercial delivery fleets is shifting fleet routing from distance- and time-based optimization toward energy-aware decision-making. Existing sequence models primarily provide deterministic point estimates or limited uncertainty summaries, which do not capture the range of plausib…

• Amortizing intractable inference in diffusion models for vision, language, and control

  Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Esmeralda S. Whitammer · 31 August 2026 · Neural Networks and Applications

  Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data, $\mathbf{x}\sim p^{\rm p…

• Diffusion models as plug-and-play priors

  Alexandros Graikos, Esmeralda S. Whitammer, Nebojsa Jojic, Dimitris Samaras · 31 August 2026 · Bayesian Methods and Mixture Models

  We consider the problem of inferring high-dimensional data $\mathbf{x}$ in a model that consists of a prior $p(\mathbf{x})$ and an auxiliary differentiable constraint $c(\mathbf{x},\mathbf{y})$ on $x$ given some additional information $\mathbf{y}$. In this paper, the prior is an independently traine…

• Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models

  Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, Yaliang Li · 31 August 2026 · Text and Document Classification Technologies

  Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the generation of not-safe-for-work (NSFW) content, posing significant …

• How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models

  Victor Besnier, Anh-Quan Cao, Elias Ramzi, Spyros Gidaris, Tuan-Hung Vu, Andrei Bursuc, Eloi Zablocki, Matthieu Cord · 31 August 2026 · Generative Adversarial Networks and Image Synthesis

  Video generation for autonomous driving cannot follow the web-scale route: driving data is expensive to collect, bound by privacy requirements, and cannot be scraped at will, so models must make the most of a fixed corpus. We present a systematic scaling-law study of video diffusion models trained f…

• Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution

  Ren Wang, Yung-Yu Chuang · 27 August 2026 · Advanced Image Processing Techniques

  The perception-distortion trade-off poses a fundamental challenge in single-image super-resolution (SR). Although diffusion-based SR methods excel at generating perceptually realistic images, achieving high fidelity remains a key limitation. Recent advances in diffusion-based SR have shown promise i…

• DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models

  Minhae Oh, Nakyung Lee, Jungwoo Lee · 27 August 2026 · Large Language Models

  Correcting flawed reasoning traces remains a significant challenge for Large Language Models (LLMs), whose autoregressive generation can propagate early mistakes into subsequent reasoning. We introduce DCGC, a Masked Diffusion Model (MDM) framework for global correction that uses an imperfect soluti…

• Generalization, memorization, and overfitting for diffusion models trained in the lazy high-dimensional regime

  Hugo Latourelle-Vigeant, Sinho Chewi, Aram-Alexandre Pooladian, John Sous, Theodor Misiakiewicz · 26 August 2026 · Numerical methods in inverse problems

  Modern score-based generative models have achieved remarkable empirical success in high-dimensional tasks such as image, audio, and video synthesis. These models reduce distribution learning to a sequence of regression problems that, if solved exactly on finite data, would ultimately reproduce the t…

• A Theory of Speciation in Generative Diffusion Models on Compact Riemannian Manifolds

  Alessio Marta, Paola Causin · 26 August 2026 · Theoretical and Computational Physics

  Speciation in generative diffusion models denotes the emergence of distinct stable branches during denoising, through which initially undifferentiated trajectories progressively commit to different data classes. In this work we develop an intrinsic theory of speciation for diffusion models supported…

• Controllable blind deblurring with diffusion models

  Imane Si Salah, Emile Cribelier, Thomas Veit, Wolf Hauser, Arthur Leclaire · 26 August 2026 · Advanced Image Processing Techniques

  Image acquisition with a camera involves several degradations due to the optical system, sensor, or low-level processing steps. We address blind deblurring in professional photography: we aim to invert unknown isotropic blur without knowledge of the degradation kernel. For such inverse problems,wher…

• On-Policy Self-Distillation in Diffusion Models

  Wei Zhou, Xiongwei Zhu, Lingdong Kong, Bo Chen, Lei Zhang, Yongyuan Liang, Xiaoxia Hou, Ye Tian, Xian Sun, Yingshuo Wang, Linfeng Li, Shengqiong Wu, Leigang Qu, Feng Li, Wei Liu, Julian McAuley, Tat-Seng Chua · 26 August 2026 · Reinforcement Learning in Robotics

  Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward g…

• Scaling Reinforcement Learning for Diffusion Models via Velocity Matching

  Jaemoo Choi, Wei Guo, Yuchen Zhu, Arash Vahdat, Molei Tao, Julius Berner, Yongxin Chen · 26 August 2026 · Generative Adversarial Networks and Image Synthesis

  Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing methods largely inherit policy-gradient machinery from large language models. Unlike autoregressive models, diffusion models do not provide tractable likelih…

• Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion Model

  Jie Chen, Hongling Chen, Jinghuai Gao, Chuangji Meng, Tao Yang, XinXin Liang · 25 August 2026 · Seismic Imaging and Inversion Techniques

  Seismic acoustic impedance plays a crucial role in lithological identification and subsurface structure interpretation. However, due to the inherently ill-posed nature of the inversion problem, directly estimating impedance from post-stack seismic data remains highly challenging. Recently, diffusion…

• DreamHand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery

  Yufei Liu, Xixi Wang, Hao Li, Ganlong Zhao, Kaitong Cai, Chengkai Jin, Chunxiao Liu, Jianbo Liu, Siyuan Huang, Xingang Pan, Hongsheng Li · 21 August 2026 · Human Pose and Action Recognition

  Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusion and frequent out-of-sight gaps. Existing single-frame and windowed temporal regressors fail when hand shortly leaves the frame, while rece…

• A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

  Libo Chen, Souvik Ghosh, Teo Deveney, Chris Budd, Vinay P. Namboodiri · 21 August 2026 · Advanced Mathematical Modeling in Engineering

  We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at inference via a plug-in correction term. The plug-in term separates the conditioning c…

• Diffusion Models for High-Dimensional Clustered Data: Intrinsic-Dimension Adaptivity via Bayesian Classification

  Yuga Iguchi, Paul Fearnhead · 20 August 2026 · Advanced Mathematical Modeling in Engineering

  The empirical success of diffusion models in generative modelling has motivated theoretical work, including quantitative error bounds and qualitative analyses that characterise the different phases of denoising. We bring these two areas together by studying the adaptivity of diffusion models to the …