Diffusion Models

Follow this topic Ask about this topic

Diffusion models learn a data distribution by gradually corrupting examples with noise and training a denoiser to reverse that process. Major approaches include DDPMs and score-based SDEs, latent diffusion and diffusion Transformers, flow and consistency methods, and discrete masked or continuous-time Markov diffusion; conditioning and guidance adapt them to specific tasks. They are used for images, video, audio, language, molecules, and scientific forecasting, with evaluations ranging from ImageNet FID to language perplexity and domain-specific measures of accuracy and uncertainty. A central tension is how to make sampling faster and generation more controllable without sacrificing quality, calibration, or diversity, while theory and ongoing audits address generalization, memorization, and privacy.

Latest papers

1,192 papers152 papers in the last four weeks, up 77% on the four weeks before. 0.9% of all new papers.

Apr 12, 2026

Rethinking the Diffusion Model from a Langevin Perspective

Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically demanding mathematics that can be difficult for beginners to grasp. One classic question is: how does the reverse process invert the forward process to generate data from pure noise? This article systematically organizes the diffusion model from a fresh Langevin perspective, offering a simpler, clearer, and more intuitive answer. We also address the following questions: how can ODE-based and SDE-based diffusion models be unified under a single framework? Why are diffusion models theoretically superior to ordinary VAEs? Why is flow matching not fundamentally simpler than denoising or score matching, but equivalent under maximum-likelihood? We demonstrate that the Langevin perspective offers clear and straightforward answers to these questions, bridging existing interpretations of diffusion models, showing how different formulations can be converted into one another within a common framework, and offering pedagogical value for both learners and experienced researchers seeking deeper intuition.

Candi Zheng, Yuan Lan

Department of Mathematics, The Hong Kong University of Science and Technology

Diffusion Models

Apr 11, 2026

Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs

Transformer-based diffusion models have demonstrated remarkable performance at generating high-quality samples. However, our theoretical understanding of the reasons for this success remains limited. For instance, existing models are typically trained by minimizing a denoising objective, which is equivalent to fitting the score function of the training data. However, we do not know why transformer-based models can match the score function for denoising, or why gradient-based methods converge to the optimal denoising model despite the non-convex loss landscape. To the best of our knowledge, this paper provides the first convergence analysis for training transformer-based diffusion models. More specifically, we consider the population Denoising Diffusion Probabilistic Model (DDPM) objective for denoising data that follow a multi-token Gaussian mixture distribution. We theoretically quantify the required number of tokens per data point and training iterations for the global convergence towards the Bayes optimal risk of the denoising objective, thereby achieving a desired score matching error. A deeper investigation reveals that the self-attention module of the trained transformer implements a mean denoising mechanism that enables the trained model to approximate the oracle Minimum Mean Squared Error (MMSE) estimator of the injected noise in the diffusion steps. Numerical experiments validate these findings.

Hongkang Li, Hancheng Min, Rene Vidal

Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA · Institute of Natural Sciences & School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China

Diffusion Models Diffusion-Based Denoising Diffusion Transformer Score Matching

Apr 11, 2026

FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer

With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrained weights enables low-cost customized generation. However, most existing model merging methods are designed for classification or text generation, and when applied to image generation, they suffer from content drift due to error accumulation across multiple diffusion steps. For image-oriented methods, training-based approaches are computationally expensive and unsuitable for edge deployment, while training-free ones use uniform fusion strategies that ignore inter-adapter differences, leading to detail degradation. We find that since different adapters are specialized for generating different types of content, the contribution of each diffusion step carries different significance for each adapter. Accordingly, we propose a frequency-domain importance-driven dynamic LoRA switch method. Furthermore, we observe that maintaining semantic consistency across adapters effectively mitigates detail loss; thus, we design an automatic Generation Alignment mechanism to align generation intents at the semantic level. Experiments demonstrate that our FREE-Switch (Frequency-based Efficient and Dynamic LoRA Switch) framework efficiently combines adapters for different objects and styles, substantially reducing the training cost of high-quality customized generation.

Shenghe Zheng, Minyu Zhang, Tianhao Liu +1

Harbin Institute of Technology

Diffusion-Based Image Generation Diffusion Models Image Style Transfer Low-Rank Adaptation

Apr 10, 2026

Diffusion Denoiser Achievable Analysis for Finite Blocklength Unsourced Random Access

Polyanskiy proposed a framework for the unsourced multiple access channel (MAC) problem where users employ a common codebook in the finite blocklength regime. However, existing approaches handle channel noise before the joint decoder. In this work, we introduce a decoder compatible diffusion denoiser as a lightweight analysis within joint decoding. The score network is trained on samples drawn from the channel output distribution, making the method easy to integrate with existing code designs. In our theoretical analysis, we derive a diffusion-denoiser random-coding achievable bound that is strictly tighter. Simulations on existing decoders, including FASURA, MSUG-MRA and pilot-based method, show consistent performance gains with at least a

0.5

\mathrm{dB}

improvement in required

\mathrm{E_b/N_0}

at a fixed error target.

Yuming Han, Yuxin Long

Texas A&M University, Department of ECE, College Station, TX 77843, USA · University of Leeds, Institute for Transport Studies, Leeds, LS2 9JT, UK

Diffusion-Based Denoising Diffusion Models

Apr 10, 2026

SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images

Diffusion models trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address this, we propose SCoRe (Spectral Cutoff Regeneration), a training-free, generation-time spectral regeneration method for clean image generation from diffusion models trained on noisy images. Leveraging the spectral bias of diffusion models, which infer high-frequency details from low-frequency cues, SCoRe suppresses corrupted high-frequency components of a generated image via a frequency cutoff and regenerates them via SDEdit. Crucially, we derive a theoretical mapping between the cutoff frequency and the SDEdit initialization timestep based on Radially Averaged Power Spectral Density (RAPSD), which prevents excessive noise injection during regeneration. Experiments on synthetic (CIFAR-10) and real-world (SIDD) noisy datasets demonstrate that SCoRe substantially outperforms post-processing and noise-robust baselines, restoring samples closer to clean image distributions without any retraining or fine-tuning.

Yuta Matsuzaki, Seiichi Uchida, Shumpei Takezaki

Kyushu University, Fukuoka, Japan

Diffusion-Based Image Generation Diffusion Models Diffusion Model Sampling

Apr 10, 2026

Detecting Diffusion-generated Images via Dynamic Assembly Forests

Diffusion models are known for generating high-quality images, causing serious security concerns. To combat this, most efforts rely on deep neural networks (e.g., CNNs and Transformers), while largely overlooking the potential of traditional machine learning models. In this paper, we freshly investigate such alternatives and proposes a novel Dynamic Assembly Forest model (DAF) to detect diffusion-generated images. Built upon the deep forest paradigm, DAF addresses the inherent limitations in feature learning and scalable training, making it an effective diffusion-generated image detector. Compared to existing DNN-based methods, DAF has significantly fewer parameters, much lower computational cost, and can be deployed without GPUs, while achieving competitive performance under standard evaluation protocols. These results highlight the strong potential of the proposed method as a practical substitute for heavyweight DNN models in resource-constrained scenarios. Our code and models are available at https://github.com/OUC-VAS/DAF.

Mengxin Fu, Yuezun Li

School of Computer Science and Technology, Ocean University of China

AI-Generated Image Detection Diffusion Models

Apr 10, 2026

Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios

Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks, limiting the performance and practicality of existing methods. End to end neural network based approaches are generally simple to design and highly efficient in inference, but their black-box nature leads to limited interpretability. Diffusion based methods alleviate this to some extent by providing powerful generative priors and a more structured inference process. However, they are trained to learn a single domain target distribution, whereas fusion lacks natural fused data and relies on modeling complementary information from multiple sources, making diffusion hard to apply directly in practice. To address these challenges, this paper proposes an efficient degradation aware diffusion framework for image fusion under arbitrary degradation scenarios. Specifically, instead of explicitly predicting noise as in conventional diffusion models, our method performs implicit denoising by directly regressing the fused image, enabling flexible adaptation to diverse fusion tasks under complex degradations with limited steps. Moreover, we design a joint observation model correction mechanism that simultaneously imposes degradation and fusion constraints during sampling to ensure high reconstruction accuracy. Experiments on diverse fusion tasks and degradation configurations demonstrate the superiority of the proposed method under complex degradation scenarios.

Yu Shi, Yu Liu, Zhong-Cheng Wu +3

Department of Biomedical Engineering, Hefei University of Technology · Faculty of Information Engineering and Automation, Kunming University of Science and Technology · School of Information Science and Technology, University of Science and Technology of China

Multi-Source Image Fusion Diffusion Models

Apr 9, 2026

What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment Reconstruction

Virtual Try-On (VTON) has seen rapid advancements, providing a strong foundation for generative fashion tasks. However, the inverse problem, Virtual Try-Off (VTOFF)-aimed at reconstructing the canonical garment from a draped-on image-remains a less understood domain, distinct from the heavily researched field of VTON. In this work, we seek to establish a robust architectural foundation for VTOFF by studying and adapting various diffusion-based strategies from VTON and general Latent Diffusion Models (LDMs). We focus our investigation on the Dual-UNet Diffusion Model architecture and analyze three axes of design: (i) Generation Backbone: comparing Stable Diffusion variants; (ii) Conditioning: ablating different mask designs, masked/unmasked inputs for image conditioning, and the utility of high-level semantic features; and (iii) Losses and Training Strategies: evaluating the impact of the auxiliary attention-based loss, perceptual objectives and multi-stage curriculum schedules. Extensive experiments reveal trade-offs across various configuration options. Evaluated on VITON-HD and DressCode datasets, our framework achieves state-of-the-art performance with a drop of 9.5% on the primary metric DISTS and competitive performance on LPIPS, FID, KID, and SSIM, providing both stronger baselines and insights to guide future Virtual Try-Off research.

Loc-Phat Truong, Meysam Madadi, Sergio Escalera

Computer Vision Center, Spain · Universitat de Barcelona, Spain

Diffusion Models Diffusion-Based Image Generation

Apr 9, 2026

Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training

Conditional Diffusion Models are powerful surrogates for emulating complex spatiotemporal dynamics, yet they often fail to match the accuracy of deterministic neural emulators for high-precision tasks. In this work, we address two critical limitations of autoregressive PDE diffusion models: their sub-optimal single-step accuracy and the prohibitive computational cost of unrolled training. First, we characterize the relationship between the noise schedule, the reconstruction error reduction rate and the diffusion exposure bias, demonstrating that standard schedules lead to suboptimal reconstruction error. Leveraging this insight, we propose an Adaptive Noise Schedule framework that minimizes inference reconstruction error by dynamically constraining the model's exposure bias. We further show that this optimized schedule enables a fast Proxy Unrolled Training method to stabilize long-term rollouts without the cost of full Markov Chain sampling. Both proposed methods enable significant improvements in short-term accuracy and long-term stability over diffusion and deterministic baselines on diverse benchmarks, including forced Navier-Stokes, Kuramoto-Sivashinsky and Transonic Flow.

Constantin Le Cleï, Nils Thuerey, Xiaoxiang Zhu

Technical University of Munich, Munich, Germany.

Diffusion Models Autoregressive Diffusion PDE Surrogate Modeling Diffusion Timestep Scheduling Conditional Diffusion Models Diffusion Model Acceleration

Apr 9, 2026

PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation

Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major privacy concerns. The problem is more acute for personalized talking-head generation, where identity-specific data are highly sensitive and often cannot be pooled across users or devices. PrivFedTalk is presented as a privacy-aware federated framework for personalized talking-head generation that combines conditional latent diffusion with parameter-efficient identity adaptation. A shared diffusion backbone is trained across clients, while each client learns lightweight LoRA identity adapters from local private audio-visual data, avoiding raw data sharing and reducing communication cost. To address heterogeneous client distributions, Identity-Stable Federated Aggregation (ISFA) weights client updates using privacy-safe scalar reliability signals computed from on-device identity consistency and temporal stability estimates. Temporal-Denoising Consistency (TDC) regularization is introduced to reduce inter-frame drift, flicker, and identity drift during federated denoising. To limit update-side privacy risk, secure aggregation and client-level differential privacy are applied to adapter updates. The implementation supports both low-memory GPU execution and multi-GPU client-parallel training on heterogeneous shared hardware. Comparative experiments on the present setup across multiple training and aggregation conditions with PrivFedTalk, FedAvg, and FedProx show stable federated optimization and successful end-to-end training and evaluation under constrained resources. The results support the feasibility of privacy-aware personalized talking-head training in federated environments, while suggesting that stronger component-wise, privacy-utility, and qualitative claims need further standardized evaluation.

Soumya Mazumdar, Vineet Kumar Rakesh, Tapas Samanta

Department of Computer Science and Business Systems Gargi Memorial Institute of Technology Affiliated to Maulana Abul Kalam Azad University of Technology Balarampur, Mouza Beralia, Baruipur, Kolkata 700144, West Bengal, India · Engineering Sciences, Homi Bhabha National Institute Anushaktinagar, Mumbai, Maharashtra 400094, India · Computer and Informatics Group / Radioactive Ion Beam Facilities Group Variable Energy Cyclotron Centre 1/AF, Bidhannagar, Kolkata 700064, West Bengal, India

Talking Head Generation Federated Learning Federated Fine-Tuning Diffusion Models

Apr 9, 2026

Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code

Autoregressive (AR) language models have driven significant progress in automated software engineering, enabling powerful code generation and assistance systems. However, the next-token prediction paradigm introduces structural limitations for code reasoning, including restricted global planning, challenges in maintaining long-range dependencies, and limited grounding in program execution semantics. Noting the heavy skewness of existing literature towards AR models, we discuss emerging paradigms that could potentially overcome the logic and scaling bottlenecks of next-token prediction by unlocking next-generation architectural capabilities for code intelligence. Specifically, we discuss the potential of Diffusion Models, which generate code via holistic denoising that captures long-range syntactic constraints often missed by AR models. We also discuss Code World Models (CWMs), which simulate execution states to support reasoning, and State Space Models (SSMs), which provide linear-time efficiency for massive contexts. By connecting these developments with findings from cognitive neuroscience, we outline directions for developing "System 2" code generation agents.

Kishan Maharaj, Ashita Saxena, Srikanth Tamilselvam

IBM

Code World Models LLM Code Generation Diffusion Models World Models State Space Models

Apr 9, 2026

FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding

Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content. Existing NSFW detection methods mainly operate either before or after image generation. Pre-generation methods rely on text prompts and struggle with the gap between prompt safety and image safety. Post-generation methods apply classifiers to final outputs, but they are poorly suited to intermediate noisy images. To address this, we introduce FlowGuard, a cross-model in-generation detection framework that inspects intermediate denoising steps. This is particularly challenging in latent diffusion, where early-stage noise obscures visual signals. FlowGuard employs a novel linear approximation for latent decoding and leverages a curriculum learning approach to stabilize training. By detecting unsafe content early, FlowGuard reduces unnecessary diffusion steps to cut computational costs. Our cross-model benchmark spanning nine diffusion-based backbones shows the effectiveness of FlowGuard for in-generation NSFW detection in both in-distribution and out-of-distribution settings, outperforming existing methods by over 30% in F1 score while delivering transformative efficiency gains, including slashing peak GPU memory demand by over 97% and projection time from 8.1 seconds to 0.2 seconds compared to standard VAE decoding.

Jinghan Yang, Yihe Fan, Xudong Pan +1

Fudan University, Shanghai, China · Fudan University, Shanghai Innovation Institute, Shanghai, China

Diffusion Models Latent Diffusion Models

Apr 9, 2026

Monocular Depth Estimation From the Perspective of Feature Restoration: A Diffusion Enhanced Depth Restoration Approach

Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods employ an encoder-decoder architecture with multi-level/scale feature processing. However, the limitations of the current architecture and the effects of different-level features on the prediction accuracy are not evaluated. In this paper, we first investigate the above problem and show that there is still substantial potential in the current framework if encoder features can be improved. Therefore, we propose to formulate the depth estimation problem from the feature restoration perspective, by treating pretrained encoder features as degraded features of an assumed ground truth feature that yields the ground truth depth map. Then an Invertible Transform-enhanced Indirect Diffusion (InvT-IndDiffusion) module is developed for feature restoration. Due to the absence of direct supervision on feature, only indirect supervision from the final sparse depth map is used. During the iterative procedure of diffusion, this results in feature deviations among steps. The proposed InvT-IndDiffusion solves this problem by using an invertible transform-based decoder under the bi-Lipschitz condition. Finally, a plug-and-play Auxiliary Viewpoint-based Low-level Feature Enhancement module (AV-LFE) is developed to enhance local details with auxiliary viewpoint when available. Experiments demonstrate that the proposed method achieves better performance than the state-of-the-art methods on various datasets. Specifically on the KITTI benchmark, compared with the baseline, the performance is improved by 4.09% and 37.77% under different training settings in terms of RMSE. Code is available at https://github.com/whitehb1/IID-RDepth.

Huibin Bai, Shuai Li, Hanxiao Zhai +6

School of Software, Shandong University, Jinan 250100, China · Shandong University-WeiHai Research Institute of Industrial Technology, Weihai 264209, China · School of Control Science and Engineering, Shandong University, Jinan, China +4

Depth Estimation Monocular Depth Estimation Diffusion Models

Apr 8, 2026

Score Shocks: The Burgers Equation Structure of Diffusion Generative Models

We analyze the score field of a diffusion generative model through a Burgers-type evolution law. For VE diffusion, the heat-evolved data density implies that the score obeys viscous Burgers in one dimension and the corresponding irrotational vector Burgers system in

\R^d

, giving a PDE view of speciation transitions as the sharpening of inter-mode interfaces. For any binary decomposition of the noised density into two positive heat solutions, the score separates into a smooth background and a universal

\tanh

interfacial term determined by the component log-ratio; near a regular binary mode boundary this yields a normal criterion for speciation. In symmetric binary Gaussian mixtures, the criterion recovers the critical diffusion time detected by the midpoint derivative of the score and agrees with the spectral criterion of Biroli, Bonnaire, de~Bortoli, and Mézard (2024). After subtracting the background drift, the inter-mode layer has a local Burgers

\tanh

profile, which becomes global in the symmetric Gaussian case with width

σ_τ^2/a

. We also quantify exponential amplification of score errors across this layer, show that Burgers dynamics preserves irrotationality, and use a change of variables to reduce the VP-SDE to the VE case, yielding a closed-form VP speciation time. Gaussian-mixture formulas are verified to machine precision, and the local theorem is checked numerically on a quartic double-well.

Krisanu Sarkar

Indian Institute of Technology Bombay, Mumbai, India

Diffusion Models Score-Based Generative Modeling Stochastic Differential Equations

Apr 8, 2026

A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression

With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in the diffusion learning, they usually produce reconstructions with deviation from the original images, leading to suboptimal compression results. To address this problem, in this paper, we propose a Noise Constrained Diffusion (NC-Diffusion) framework for high fidelity image compression. Unlike existing diffusion-based compression methods that add random Gaussian noise and direct the noise into the image space, the proposed NC-Diffusion formulates the quantization noise originally added in the learned image compression as the noise in the forward process of diffusion. Then a noise constrained diffusion process is constructed from the ground-truth image to the initial compression result generated with quantization noise. The NC-Diffusion overcomes the problem of noise mismatch between compression and diffusion, significantly improving the inference efficiency. In addition, an adaptive frequency-domain filtering module is developed to enhance the skip connections in the U-Net based diffusion architecture, in order to enhance high-frequency details. Moreover, a zero-shot sample-guided enhancement method is designed to further improve the fidelity of the image. Experiments on multiple benchmark datasets demonstrate that our method can achieve the best performance compared with existing methods.

Zhenyu Du, Yanbo Gao, Shuai Li +3

Shandong University, Jinan, China · University of Electronic Science and Technology of China, Sichuan, China

Learned Image Compression Generative Image Compression Diffusion Model Compression Diffusion Models

Apr 8, 2026

Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles

Autonomous vehicles in interactive traffic environments are often limited by the scarcity of safety-critical tail events in static datasets, which biases learned policies toward average-case behaviors and reduces robustness. Existing evaluation methods attempt to address this through adversarial stress testing, but are predominantly open-loop and post-hoc, making it difficult to incorporate discovered failures back into the training process. We introduce Evaluation as Evolution (

E^2

), a closed-loop framework that transforms adversarial generation from a static validation step into an adaptive evolutionary curriculum. Specifically,

E^2

formulates adversarial scenario synthesis as transport-regularized sparse control over a learned reverse-time SDE prior. To make this high-dimensional generation tractable, we utilize topology-driven support selection to identify critical interacting agents, and introduce Topological Anchoring to stabilize the process. This approach enables the targeted discovery of failure cases while strictly constraining deviations from realistic data distributions. Empirically,

E^2

improves collision failure discovery by 9.01% on the nuScenes dataset and up to 21.43% on the nuPlan dataset over the strongest baselines, while maintaining low invalidity and high realism. It further yields substantial robustness gains when the resulting boundary cases are recycled for closed-loop policy fine-tuning.

Yicheng Guo, Jiaqi Liu, Chengkai Xu +2

College of Transportation, Tongji University, Shanghai 201804, China · Department of Computer Science, University of North Carolina at Chapel Hill, United States

Autonomous Driving Safety Evaluation Adversarial Scenario Generation Diffusion Models

Apr 7, 2026

Improving Controllable Generation: Faster Training and Better Performance via $x_0$ -Supervision

Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language alone cannot reliably express. Controllable generation methods augment the initial T2I model with additional conditions that more easily describe the scene. Prior works straightforwardly train the augmented network with the same loss as the initial network. Although natural at first glance, this can lead to very long training times in some cases before convergence. In this work, we revisit the training objective of controllable diffusion models through a detailed analysis of their denoising dynamics. We show that direct supervision on the clean target image, dubbed

x_0

-supervision, or an equivalent re-weighting of the diffusion loss, yields faster convergence. Experiments on multiple control settings demonstrate that our formulation accelerates convergence by up to 2

\times

according to our novel metric (mean Area Under the Convergence Curve - mAUCC), while also improving both visual quality and conditioning accuracy. Our code is available at https://github.com/CEA-LIST/x0-supervision

Amadou S. Sangare, Adrien Maglo, Mohamed Chaouch +1

Université Paris-Saclay, CEA, List, F-91120, Palaiseau, France

Controllable Image Generation Conditional Diffusion Models T2I Diffusion Models Diffusion Models

Apr 7, 2026

Cross-Resolution Diffusion Models via Network Pruning

Diffusion models have demonstrated impressive image synthesis performance, yet many UNet-based models are trained at certain fixed resolutions. Their quality tends to degrade when generating images at out-of-training resolutions. We trace this issue to resolution-dependent parameter behaviors, where weights that function well at the default resolution can become adverse when spatial scales shift, weakening semantic alignment and causing structural instability in the UNet architecture. Based on this analysis, this paper introduces CR-Diff, a novel method that improves the cross-resolution visual consistency by pruning some parameters of the diffusion model. Specifically, CR-Diff has two stages. It first performs block-wise pruning to selectively eliminate adverse weights. Then, a pruned output amplification is conducted to further purify the pruned predictions. Empirically, extensive experiments suggest that CR-Diff can improve perceptual fidelity and semantic coherence across various diffusion backbones and unseen resolutions, while largely preserving the performance at default resolutions. Additionally, CR-Diff supports prompt-specific refinement, enabling quality enhancement on demand.

Jiaxuan Ren, Junhan Zhu, Huan Wang

University of Electronic Science and Technology of China · Westlake University

Diffusion Model Pruning Image Generation Diffusion-Based Image Generation Diffusion Models

Apr 7, 2026

Human Interaction-Aware 3D Reconstruction from a Single Image

Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition of individual reconstructions often leads to artifacts such as unrealistic overlaps, missing geometry in occluded regions, and distorted interactions. These limitations highlight the need for approaches that incorporate group-level context and interaction priors. We introduce a holistic method that explicitly models both group- and instance-level information. To mitigate perspective-induced geometric distortions, we first transform the input into a canonical orthographic space. Our primary component, Human Group-Instance Multi-View Diffusion (HUG-MVD), then generates complete multi-view normals and images by jointly modeling individuals and group context to resolve occlusions and proximity. Subsequently, the Human Group-Instance Geometric Reconstruction (HUG-GR) module optimizes the geometry by leveraging explicit, physics-based interaction priors to enforce physical plausibility and accurately model inter-human contact. Finally, the multi-view images are fused into a high-fidelity texture. Together, these components form our complete framework, HUG3D. Extensive experiments show that HUG3D significantly outperforms both single-human and existing multi-human methods, producing physically plausible, high-fidelity 3D reconstructions of interacting people from a single image. Project page: https://jongheean11.github.io/HUG3D_project

Gwanghyun Kim, Junghun James Kim, Suh Yoon Jeon +2

Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea · IPAI, Seoul National University, Republic of Korea · INMC, Seoul National University, Republic of Korea

3D Human Reconstruction Single-View 3D Reconstruction Diffusion Models

Apr 6, 2026

Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation

Diffusion models are increasingly being utilised to create synthetic tabular and time series data for privacy-preserving augmentation. Tabular Denoising Diffusion Probabilistic Models (TabDDPM) generate high-quality synthetic data from heterogeneous tabular datasets but assume independence between samples, limiting their applicability to time-series domains where temporal dependencies are critical. To address this, we propose a temporal extension of TabDDPM, introducing sequence awareness through the use of lightweight temporal adapters and context-aware embedding modules. By reformulating sensor data into windowed sequences and explicitly modeling temporal context via timestep embeddings, conditional activity labels, and observed/missing masks, our approach enables the generation of temporally coherent synthetic sequences. Compared to baseline and interpolation techniques, validation using bigram transition matrices and autocorrelation analysis shows enhanced temporal realism, diversity, and coherence. On the WISDM accelerometer dataset, the suggested system produces synthetic time-series that closely resemble real world sensor patterns and achieves comparable classification performance (macro F1-score 0.64, accuracy 0.71). This is especially advantageous for minority class representation and preserving statistical alignment with real distributions. These developments demonstrate that diffusion based models provide effective and adaptable solutions for sequential data synthesis when they are equipped for temporal reasoning. Future work will explore scaling to longer sequences and integrating stronger temporal architectures.

Umang Dobhal, Christina Garcia, Sozo Inoue

Time Series Generation Tabular Diffusion Models Diffusion Models Synthetic Data Augmentation

Apr 6, 2026

OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models

In a rapidly growing field of model training there is a constant practical interest in parameter-efficient fine-tuning and various techniques that use a small amount of training data to adapt the model to a narrow task. However, there is an open question: how to combine several adapters tuned for different tasks into one which is able to yield adequate results on both tasks? Specifically, merging subject and style adapters for generative models remains unresolved. In this paper we seek to show that in the case of orthogonal fine-tuning (OFT), we can use structured orthogonal parametrization and its geometric properties to get the formulas for training-free adapter merging. In particular, we derive the structure of the manifold formed by the recently proposed Group-and-Shuffle (

\mathcal{GS}

) orthogonal matrices, and obtain efficient formulas for the geodesics approximation between two points. Additionally, we propose a

\text{spectra restoration}

transform that restores spectral properties of the merged adapter for higher-quality fusion. We conduct experiments in subject-driven generation tasks showing that our technique to merge two

\mathcal{GS}

orthogonal matrices is capable of uniting concept and style features of different adapters. To the best of our knowledge, this is the first training-free method for merging multiplicative orthogonal adapters. Code is available via the link.

Ali Aliev, Kamil Garifullin, Nikolay Yudin +5

HSE University · FusionBrain Lab · AXXX

Model Merging Diffusion Model Adaptation Diffusion Model Fine-Tuning Diffusion Models Fine-Tuning Orthogonal Representation Learning

Apr 6, 2026

Graph Signal Diffusion Models for Wireless Resource Allocation

We consider constrained ergodic resource optimization in wireless networks with graph-structured interference. We train a diffusion model policy to match expert conditional distributions over resource allocations. By leveraging a primal-dual (expert) algorithm, we generate primal iterates that serve as draws from the corresponding expert conditionals for each training network instance. We view the allocations as stochastic graph signals supported on known channel state graphs. We implement the diffusion model architecture as a U-Net hierarchy of graph neural network (GNN) blocks, conditioned on the channel states and additional node states. At inference, the learned generative model amortizes the iterative expert policy by directly sampling allocation vectors from the near-optimal conditional distributions. In a power-control case study, we show that time-sharing the generated power allocations achieves near-optimal ergodic sum-rate utility and near-feasible ergodic minimum-rates, with strong generalization and transferability across network states.

Yigit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti +1

Dept. of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA

Wireless Resource Allocation Diffusion Policy Diffusion Models Conditional Diffusion Models

Apr 6, 2026

Simultaneous Dual-View Mammogram Synthesis Using Denoising Diffusion Probabilistic Models

Breast cancer screening relies heavily on mammography, where the craniocaudal (CC) and mediolateral oblique (MLO) views provide complementary information for diagnosis. However, many datasets lack complete paired views, limiting the development of algorithms that depend on cross-view consistency. To address this gap, we propose a three-channel denoising diffusion probabilistic model capable of simultaneously generating CC and MLO views of a single breast. In this configuration, the two mammographic views are stored in separate channels, while a third channel encodes their absolute difference to guide the model toward learning coherent anatomical relationships between projections. A pretrained DDPM from Hugging Face was fine-tuned on a private screening dataset and used to synthesize dual-view pairs. Evaluation included geometric consistency via automated breast mask segmentation and distributional comparison with real images, along with qualitative inspection of cross-view alignment. The results show that the difference-based encoding helps preserve the global breast structure across views, producing synthetic CC-MLO pairs that resemble real acquisitions. This work demonstrates the feasibility of simultaneous dual-view mammogram synthesis using a difference-guided DDPM, highlighting its potential for dataset augmentation and future cross-view-aware AI applications in breast imaging.

Jorge Alberto Garza-Abdala, Gerardo A. Fumagal-González, Eduardo de Avila-Armenta +5

Tecnologico de Monterrey, School of Engineering and Sciences, Monterrey, Mexico · School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile · Tecnologico de Monterrey, School of Medicine and Health Sciences, Monterrey, Mexico

Multi-View Image Synthesis Medical Image Synthesis Mammography Synthetic Data Augmentation Diffusion Models

Apr 5, 2026

Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics

Generating molecular dynamics (MD) trajectories using deep generative models has attracted increasing attention, yet remains inherently challenging due to the limited availability of MD data and the complexities involved in modeling high-dimensional MD distributions. To overcome these challenges, we propose a novel framework that leverages structure pretraining for MD trajectory generation. Specifically, we first train a diffusion-based structure generation model on a large-scale conformer dataset, on top of which we introduce an interpolator module trained on MD trajectory data, designed to enforce temporal consistency among generated structures. Our approach effectively harnesses abundant structural data to mitigate the scarcity of MD trajectory data and effectively decomposes the intricate MD modeling task into two manageable subproblems: structural generation and temporal alignment. We comprehensively evaluate our method on the QM9 and DRUGS small-molecule datasets across unconditional generation, forward simulation, and interpolation tasks, and further extend our framework and analysis to tetrapeptide and protein monomer systems. Experimental results confirm that our approach excels in generating chemically realistic MD trajectories, as evidenced by remarkable improvements of accuracy in geometric, dynamical, and energetic measurements.

Aniketh Iyengar, Jiaqi Han, Pengwei Sun +3

Stanford University · Lambda, Inc

Molecular Dynamics Simulation 3D Molecular Generation Diffusion Models

Apr 4, 2026

ML-based approach to classification and generation of structured light propagation in turbulent media

We study the classification task of structured-light beams after propagation through a random turbulent medium. The received speckle patterns are generated by numerical simulation of a stochastic paraxial propagation model, and the classification task is formulated over a finite alphabet of 15 OAM source classes. We benchmark intensity and autocorrelation inputs using SimpleCNN and ResNet-18 as classifiers. We also quantify the effect of training-set size and receiver-window misalignment. Since additional propagated samples may be costly to obtain, we develop a class-conditioned diffusion model for generative augmentation of turbulence-degraded intensity images. The main contribution is a spectrum-aware diffusion objective: a pixel-domain loss combined with a Fourier-domain Bregman regularizer designed to preserve high-frequency speckle statistics. We prove that this hybrid objective is consistent with the posterior-mean regression target of the diffusion model and show that generated samples substantially improve low-data classification.

Aokun Wang, Anjali Nair, Zhongjian Wang +1

Division of Mathematical Sciences, Nanyang Technological University, 21 Nanyang Link, 637371 Singapore · Committee on Computational and Applied Mathematics, University of Chicago, Chicago, IL 60637 USA · Departments of Statistics and Mathematics, University of Chicago, Chicago, IL 60637 USA

Synthetic Data Augmentation Conditional Diffusion Models Diffusion Models

Apr 4, 2026

CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Data

Diffusion models have excelled at generative tasks for both continuous and token-based domains, but their application to discrete ordinal data remains underdeveloped. We present CountsDiff, a diffusion framework designed to model distributions on the natural numbers. CountsDiff extends the Blackout diffusion framework by simplifying its formulation through a direct parameterization in terms of a survival probability schedule and an explicit loss weighting. This introduces flexibility through design parameters with direct analogues in existing diffusion modeling frameworks. Beyond this reparameterization, CountsDiff introduces features from modern diffusion models, previously absent in counts-based domains, including continuous-time training, classifier-free guidance, and churn/remasking reverse dynamics that allow non-monotone reverse trajectories. We propose an initial instantiation of CountsDiff and validate it on natural image datasets (CIFAR-10, CelebA), exploring the effects of the introduced design parameters in a complex, well-studied, and interpretable data domain. We then highlight biological count assays as a natural use case, evaluating CountsDiff on single-cell RNA-seq imputation in fetal and heart cell atlases. Remarkably, we find that even this simple instantiation matches or surpasses the performance of a state-of-the-art discrete generative model and leading scRNA-seq imputation methods, while leaving substantial headroom for further gains through optimized design choices in future work.

Renzo G. Soatto, Anders Hoel, Greycen Ren +5

Massachusetts Institute of Technology (MIT), Cambridge, MA, USA · Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA · Eric and Wendy Schmidt Center, Broad Institute, Cambridge, MA, USA +1

Diffusion Models Synthetic Data Generation Incomplete Data Imputation

Apr 4, 2026

StrADiff: A Structured Source-Wise Adaptive Diffusion Framework for Linear and Nonlinear Blind Source Separation

This paper presents StrADiff, a Structured Source-Wise Adaptive Diffusion Framework for unsupervised blind source separation under linear and nonlinear mixing. The framework treats each latent dimension as a source branch and assigns to it an individual adaptive reverse diffusion mechanism, so that latent sources are recovered directly from observed mixtures through a single end-to-end objective, without supervised source labels or separate post-processing. Source-wise generation, structural regularization, and observation-space reconstruction are optimized jointly during training. In this instantiation, a Gaussian process (GP) prior is used as one example of a source-wise structured prior to impose temporal organization on each recovered trajectory; the framework itself is not restricted to GP priors and can in principle incorporate other structured priors. Theoretical components clarify the induced pushforward source law, the sample-level role of the structured prior, the coupling between source recovery and prior adaptation, and a conditional weak recovery statement in an idealized linear low-noise regime. Experiments on linear and nonlinear mixtures show that StrADiff can recover meaningful latent source trajectories in an unsupervised manner, with particularly stable performance in the linear case and moderate degradation under nonlinear mixing. Beyond classical signal separation, a source branch may also be interpreted as an independent, disentangled, or otherwise interpretable explanatory factor under suitable structural assumptions, suggesting a broader route toward structured latent modeling and future identifiable nonlinear representation learning.

Yuan-Hao Wei

Diffusion Models

Apr 4, 2026

DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to reduce computational cost. However, these methods fail to achieve superior acceleration performance in few-step diffusion transformer models due to inefficient feature caching strategies, manually designed sparsity allocation, and the practice of retaining complete forward computations in several steps in these token cache methods. To tackle these challenges, we propose a differentiable layer-wise sparsity optimization framework for diffusion transformer models, leveraging token caching to reduce token computation costs and enhance acceleration. Our method optimizes layer-wise sparsity allocation in an end-to-end manner through a learnable network combined with a dynamic programming solver. Additionally, our proposed two-stage training strategy eliminates the need for full-step processing in existing methods, further improving efficiency. We conducted extensive experiments on a range of diffusion-transformer models, including DiT-XL/2, PixArt-

α

, FLUX, and Wan2.1. Across these architectures, our method consistently improves efficiency without degrading sample quality. For example, on PixArt-

α

with 20 sampling steps, we reduce computational cost by

54\%

while achieving generation metrics that surpass those of the original model, substantially outperforming prior approaches. These results demonstrate that our method delivers large efficiency gains while often improving generation quality.

Haowei Zhu, Ji Liu, Ziqiong Liu +4

Advanced Micro Devices, Inc. · Tsinghua University · BNRist

Diffusion Model Inference Acceleration Diffusion Models Diffusion Transformer Diffusion Model Caching

Apr 3, 2026

NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning

While neural lossless image compression has advanced significantly with learned entropy models, lossless video compression remains largely unexplored in the neural setting. We present NeuralLVC, a neural lossless video codec that combines masked diffusion with an I/P-frame architecture for exploiting temporal redundancy. Our I-frame model compresses individual frames using bijective linear tokenization that guarantees exact pixel reconstruction. The P-frame model compresses temporal differences between consecutive frames, conditioned on the previous decoded frame via a lightweight reference embedding that adds only 1.3% trainable parameters. Group-wise decoding enables controllable speed-compression trade-offs. Our codec is lossless in the input domain: for video, it reconstructs YUV420 planes exactly; for image evaluation, RGB channels are reconstructed exactly. Experiments on 9 Xiph CIF sequences and on 24 HD sequences at 720p and 1080p (Xiph, UVG, and the modern BVI-AOM benchmark) show that NeuralLVC outperforms H.264 and H.265 lossless by a significant margin at every resolution tested. We verify exact reconstruction through end-to-end encode-decode testing with arithmetic coding. These results suggest that masked diffusion with temporal conditioning is a promising direction for neural lossless video compression.

Tiberio Uricchio, Marco Bertini

University of Pisa · Pisa, Italy · Università degli Studi di Firenze +1

Masked Diffusion Models Neural Video Compression Video Compression Diffusion Models Lossless Data Compression

Apr 3, 2026

Understanding Latent Diffusability via Fisher Geometry

Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood. We quantify latent-space diffusability via the rate of change of the Minimum Mean Squared Error (MMSE) along the diffusion trajectory. Our framework decomposes this MMSE rate into contributions from Fisher Information (FI) and Fisher Information Rate (FIR). We show that isometric embeddings preserve intrinsic FI and establish quantitative intrinsic-FI bounds for a broader class of bi-Lipschitz encoders with controlled weak volume distortion, whereas FIR is governed by the interplay between encoder and data geometries. Our analysis separates four geometric contributions in local stability bounds for Gaussian-smoothed FIR: dimensional compression, tangential distortion, high-frequency encoder curvature, and curvature of data manifold. Experiments across diverse autoencoding architectures provide qualitative support for the geometric mechanisms identified by the theory and show that empirical FI and FIR track several measures of generation quality and latent-space geometry in the settings tested. We establish FI and FIR as a comprehensive analytical framework for understanding latent diffusability.

Jing Gu, Morteza Mardani, Wonjun Lee +2

School of Mathematics, University of Minnesota · NVIDIA · Department of Mathematics, The Ohio State University +1

Information Geometry Neural Representation Geometry Latent Diffusion Models Diffusion Models Latent Space Geometry