Latest Diffusion Models Research Papers

The newest Diffusion Models papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Diffusion Models so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Application of a Fusion Model Combining MRI-VASARI Features and ADC in Predicting the Molecular Subtypes of Adult-type Diffuse Gliomas
  Kai XIAO, Xiaoran LI, Xiaohong LIANG, Fengqi LI et al. · DOAJ (DOAJ: Directory of Op... · Nov 1, 2026

  Objective: To develop a machine learning model integrating MRI visually accessible Rembrandt images (VASARI) features and apparent diffusion coefficient (ADC) parameters for the preoperative classification of the three subtypes of adult-typ…

• SonoWorld4D: From One Video to a 4D Audio-Visual Scene via Diffusion Synchronization
  Derong Jin, Xiyi Chen, Ming C. Lin, Ruohan Gao · arXiv · Oct 29, 2026

  Recent progress in visual scene generation has extended beyond static 3D scenes toward the more challenging problem of generating dynamic 4D scenes from minimal input. However, sound, despite being intrinsically coupled with dynamic objects…

• Difficulty Calibration Across Time for Membership Inference in Diffusion Models
  Michael Joseph, Yedid Hoshen · arXiv · Oct 29, 2026

  Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a given image was in a model's training set. The standard approach…

• Accurate MRI-free PET Quantification and Reliability Assessment via CT-to-MRI Synthesis and Conformal Prediction
  Jungwoo Seo, Seung Yun Choi, Kun Ho Lee, Seun Jeon et al. · arXiv · Oct 29, 2026

  Standardized uptake value ratio (SUVR) quantification of amyloid PET commonly relies on a subject-specific T1-weighted MRI, yet a usable MRI is not always available. We therefore combined CT-to-MRI synthesis with conformal prediction for MR…

• Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
  Siyoon Jin, Dahyun Chung, Honggyu An, Sangbeom Lim et al. · arXiv · Oct 27, 2026

  Cross-view object correspondence identifies the same object across views. However, existing methods often rely on frame-wise matching or sequential tracking, which can propagate correspondence errors under appearance changes or occlusions. …

• Know, then Draw: A New Learning Paradigm for Visual Generation
  Yucheng Mao, Chongjian Ge, Zhuowen Tu, Hao Tan et al. · arXiv · Oct 27, 2026

  Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning paradigm that assigns these roles to autoregressive pretraining for knowledge acquisition and diffusion post-training for hi…

• The Noise Plane: A Diffusion Bridge Across Exponent and Dispersion
  Xuran Hu, Yuru Jia, Tengxi Wang, Miloš Daković et al. · arXiv · Oct 27, 2026

  Diffusion-based denoising commonly uses Gaussian perturbations, whereas sensor noise follows diverse signal-dependent statistical laws. In this paper, we propose $p$-Bridge, a unified measurement-indexed diffusion framework for Tweedie nois…

• GroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis
  Akshay Krishnan, Matias Turkulainen, Jamie Wynn, Zawar Qureshi et al. · arXiv · Oct 27, 2026

  Multi-view or video diffusion models have recently emerged as state-of-the-art approaches for novel-view synthesis from sparse image collections. While they can produce high quality images, they tend to hallucinate unrealistic spatial layou…

• ALADDIN: Adversarial Latent Diffusion Distillation for One-Step Identity Swapping
  Ivan Shchekotov, Timofei Gritsaev, Viacheslav Pirogov, Dmitry Vetrov · arXiv · Oct 27, 2026

  Face swapping transfers a source identity onto a target image while preserving the target's pose, expression, hair, and lighting. The most realistic current methods are diffusion-based, but they need many network evaluations per image. GAN-…

• Taming Noise Initialization for Zero-shot Video Restoration with Image Diffusion Priors
  Chong Wang, Zixuan Fu, Hao Cheng, Siyuan Yang et al. · arXiv · Oct 27, 2026

  Recent advances in diffusion models have achieved remarkable success in restoring high-quality images in a zero-shot manner. Unfortunately, extending this success to video restoration is challenging due to the substantial computational reso…

• VibeVideoBench:Evaluating Multimodal Agents on Code-Driven Video Generation
  Muxi Diao, Wenbin Xu, Lele Yang, Xuyang Ma et al. · arXiv · Oct 26, 2026

  Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a ruleconsistent game or narration synchronized to on-screen events. A different route is emerging: multimodal agents that wri…

• VidEdit3D: Flexible 3D Gaussian Editing with Video Diffusion
  Yanming Yang, Chenxi Song, Tong Zhao, Juntao Xu et al. · arXiv · Oct 26, 2026

  Recent advancements in text-guided 3D editing, particularly with 3D Gaussian Splatting (3DGS), have shown promise but still lag behind the flexibility of 2D editing tools. Existing methods face a critical trade-off between preserving multi-…

• Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers
  Yeonjae Kim, Omin Kwon, Seong Hoon Seo, Jae W. Lee · arXiv · Oct 26, 2026

  Attention over tens of thousands of visual tokens dominates the inference of video diffusion transformers (DiTs). Existing methods reduce this cost through sparsity, low precision, or both, but use a single precision for all kept tiles. We …

• VPR-Space: A Benchmark for Visual Place Recognition in Space Analog Domains
  Richard Fechner, Peer Neubert · arXiv · Oct 26, 2026

  Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-of-the-art VPR and SLAM approaches excel in urban and feature-rich natural environments, the…

• Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation
  Junyi Chen, Haiyu Zhang, Zhoujie Fu, Tengfei Wang et al. · arXiv · Oct 26, 2026

  Few-step distillation is essential for deploying modern video diffusion models. Among existing approaches, Distribution Matching Distillation (DMD) has emerged as a highly promising paradigm by achieving strong output-space fidelity without…

• Copying As Defense: Protecting Images from Editing By Eliciting Model Copying
  Salma Abdel Magid, Sanghyuk Chun, Eric Slyman, Kushal Kafle et al. · arXiv · Oct 26, 2026

  Image editors built on diffusion transformers (DiTs), such as Flux Kontext, make it possible to turn a single photograph into a convincing manipulated image, including harmful and non-consensual edits. Proactive defenses aim to prevent such…

• Generative Structure from Motion with Native 3D Diffusion
  Haobin Duan, Binbin Huang, Mochu Xiang, Yiqun Zhao et al. · arXiv · Oct 26, 2026

  Recovering an object's 3D structure and camera motion from a few uncalibrated views is a fundamental problem in computer vision. Classical structure from motion methods recover 3D geometry consistent with the input images but cannot recover…

• HiFiPix: Bringing High-Fidelity Real-World Super-Resolution Back to Pixel Space
  Wenjie Li, Du Chen, Hui Wang, Linlong Fan et al. · arXiv · Oct 26, 2026

  Diffusion-based real-world image super-resolution suffers from limited reconstruction fidelity due to information loss in VAE-based latent representations. Recently, pixel-space diffusion models offer a promising high-faithfulness alternati…

• Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models
  Dianye Huang, Jiamei Guo, Yue Zhou, Mingde Li et al. · arXiv · Oct 23, 2026

  Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measurement targets and discrete token-based numerical prediction. Methods: This…

• CompMVR: Compression-Aware Multi-View Restoration Using Diffusion Models for Geometrically Consistent 3D Reconstruction
  Dong-hwi Kim, Chaewon Moon, Hojun Song, Dongbeom Kim et al. · arXiv · Oct 23, 2026

  Real-world 3D reconstruction pipelines often rely on multi-view images degraded by lossy compression. While compression artifacts have been extensively studied in single-image or video restoration, their impact on multi-view geometry remain…

• SCDM-HTD: Spectral-Wise Conditional Diffusion Model for Hyperspectral Target Detection
  Dunbin Shen, Wenfeng Kong, Jianjun Liu, Xiaorui Ma et al. · arXiv · Oct 23, 2026

  Hyperspectral target detection (HTD) aims to locate and recognize objects at a fine-grained scale, playing a pivotal role in remote sensing. Despite significant progress, current HTD methods primarily focus on feature comparison while negle…

• WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models
  Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li et al. · arXiv · Oct 22, 2026

  Video diffusion models have learned rich 3D/4D priors, making them promising for scene generation and video re-rendering. However, their use in spatial tasks is limited by imprecise camera control, spatial and temporal inconsistencies, and …

• Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems
  Merve Kocabas, Benjamin A. Burns, Andreas Geiger, Kent Gauen et al. · arXiv · Oct 22, 2026

  Diffusion models have become strong priors for solving inverse problems. However, nonlinear inverse problems such as phase retrieval remain challenging when multiple measurement-consistent solutions are distinguishable only by the prior; we…

• Diffusion-Based Synthesis of Complete 3D Biparametric Prostate MRI
  Claudia Giardina, Montse Pardàs, Verónica Vilaplana · arXiv · Oct 22, 2026

  Synthetic biparametric MRI (bpMRI) may help alleviate the limited availability of large and representative prostate MRI datasets for deep learning applications. In this work, we present a conditional 3D diffusion framework for anatomy-condi…

• GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching
  Ariel Lapid, Yuval Haitman, Reuven Peretz, Arnon Netzer et al. · arXiv · Oct 22, 2026

  Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achieve strong perceptual quality by leveraging powerful image p…

• Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
  Ruopeng Gao, Yukun Huang, Jiarui Hu, Shuai Wang et al. · arXiv · Oct 21, 2026

  Autoregressive video diffusion models generate videos chunk by chunk, yet producing plausible continuations does not guarantee that they capture how scenes evolve. Under teacher forcing, strong temporal redundancy may allow local visual con…

• CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion
  Kai Zhu, Yintianrun Zhang, Shuwei Jiang, Ruolin Zuo et al. · arXiv · Oct 21, 2026

  Diffusion-based video generation models (VGMs) can produce visually plausible videos, yet their camera ego-motion often drifts over long horizons. Camera ego-motion determines how the viewpoint changes between frames and is essential for ma…

• How Do DiTs Denoise? An Aggregator-Predictor View of Attention and MLPs
  Gyeonghun Kang, William Xingxu Chen, Xiang Cheng · arXiv · Oct 21, 2026

  How do diffusion transformers (DiTs) represent image content and learn rules for reusing it to generalize? We develop an aggregator--predictor view of DiTs as input-adaptive local denoisers, in which context aggregation and patch prediction…

• Compositionality with Primitives: A Unified View from Euclidean to Hyperbolic Vision-Language Models
  Puru Vaish, Meelad Dashti, Christoph Brune, Pascal Mettes et al. · arXiv · Oct 21, 2026

  Compositional zero-shot learning (CZSL) aims to recognize novel combinations of previously observed objects and attributes. Prior work showed that large-scale vision-language models encode decomposable semantic structures that can be recomp…

• JointLight: Human-Centric Video Relighting with Asynchronous RGB-Irradiance Joint Modeling
  Henglei Lv, Bailin Deng, Xiaoqiang Liu, Yichen Wang et al. · arXiv · Oct 21, 2026

  Understanding and modeling light transport in human-centric scenes is a longstanding challenge. While recent progress in diffusion models has boosted research in relighting, precise illumination control still lags, primarily due to the scar…