Search: diffusion models

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

• Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling

  Zhen Ye, Xu Tan, Aoxiong Yin, Hongzhan Lin, Guangyan Zhang, Peiwen Sun, Yiming Li, Chi-Min Chan, Wei Ye, Shikun Zhang, Wei Xue · 28 April 2026 · Generative Adversarial Networks and Image Synthesis

  Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising via pervasive attention, treating high-level semantics and low-level details in a fully entangled man…

• $Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models

  Haosen Li, Wenshuo Chen, Shaofeng Liang, Lei Wang, Kaishen Yuan, Yutao Yue · 28 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models have achieved unprecedented success in text-aligned generation, largely driven by Classifier-Free Guidance (CFG). However, standard CFG operates strictly on instantaneous gradients, omitting the intrinsic curvature of the data manifold. Recent methods like Zigzag-sampling (Z-Samplin…

• VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation

  Nikoo Moradi, Gijs Luijten, Behrus Hinrichs-Puladi, Jens Kleesiek, Victor Alves, Jan Egger, Andr\'e Ferreira · 28 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models produce high-quality synthetic data but suffer from slow inference. We propose 3D Variable-Step Denoising Diffusion Probabilistic Model (VS-DDPM) a framework engineered to maintain generative quality while accelerating inference by several factors. We tested our approach on four tas…

• GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models

  Yiming Zhang, Sitong Liu, Ke Li, Zhihong Wu, Alex Cloninger, Melvin Leok · 28 April 2026 · Topological and Geometric Data Analysis

  Diffusion models are a leading paradigm for data generation, but training-free editing typically re-runs the full denoising trajectory for every edit strength, making iterative refinement expensive. To address this issue, we instead edit near the data manifold, where small local updates can replace …

• On the Memorization of Consistency Distillation for Diffusion Models

  Bingqing Jiang, Difan Zou · 28 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models are central to modern generative modeling, and understanding how they balance memorization and generalization is critical for reliable deployment. Recent work has shown that memorization in diffusion models is shaped by training dynamics, with generalization and memorization emergin…

• Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching

  Dong Liu, Haisheng Wang, Yanxuan Yu · 28 April 2026 · Functional Brain Connectivity Studies

  Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E$^2$-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching) to accelerate frequency domain diffusion models. Our method exploits two structural…

• Structure-Guided Diffusion Model for EEG-Based Visual Cognition Reconstruction

  Yongxiang Lian, Yueyang Cang, Pingge Hu, Yuchen He, Li Shi · 27 April 2026 · EEG and Brain-Computer Interfaces

  Objective: Decoding visual information from electroencephalography (EEG) is an important problem in neuroscience and brain-computer interface (BCI) research. Existing methods are largely restricted to natural images and categorical representations, with limited capacity to capture structural feature…

• Nuclear Diffusion Models for Low-Rank Background Suppression in Videos

  Tristan S. W. Stevens, Ois\'in Nolan, Jean-Luc Robert, Ruud J. G. van Sloun · 27 April 2026 · Image and Signal Denoising Methods

  Video sequences often contain structured noise and background artifacts that obscure dynamic content, posing challenges for accurate analysis and restoration. Robust principal component methods address this by decomposing data into low-rank and sparse components. Still, the sparsity assumption often…

• Score-based Membership Inference on Diffusion Models

  Mingxing Rao, Bowen Qu, Daniel Moyer · 27 April 2026 · Machine Learning in Healthcare

  Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing methods typically rely on measuring reconstruction error across multiple denoising steps as a test statistic, they often incur…

• Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks

  Aljalila Aladawi, Mohammed Talha Alam, Fakhri Karray · 24 April 2026 · Adversarial Robustness in Machine Learning

  Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods share a common weakness: erased concepts return when the model is fine-tuned on downstream data, even when that data is …

• The Feedback Hamiltonian is the Score Function: A Diffusion-Model Framework for Quantum Trajectory Reversal

  Sagar Dubey, Alan John · 24 April 2026 · Quantum many-body systems

  In continuously monitored quantum systems, the feedback protocol of Garc\'ia-Pintos, Liu, and Gorshkov reshapes the arrow of time: a Hamiltonian $H_{\mathrm{meas}} = r A / \tau$ applied with gain $X$ tilts the distribution of measurement trajectories, with $X < -2$ producing statistically time-rever…

• A Scale-Adaptive Framework for Joint Spatiotemporal Super-Resolution with Diffusion Models

  Max Defez, Filippo Quarenghi, Mathieu Vrac, Stephan Mandt, Tom Beucler · 24 April 2026 · Advanced Image Processing Techniques

  Deep-learning video super-resolution has progressed rapidly, but climate applications typically super-resolve (increase resolution) either space or time, and joint spatiotemporal models are often designed for a single pair of super-resolution (SR) factors (upscaling spatial and temporal ratio betwee…

• Quotient-Space Diffusion Models

  Yixian Xu, Yusong Wang, Shengjie Luo, Kaiyuan Gao, Tianyu He, Di He, Chang Liu · 24 April 2026 · Machine Learning in Materials Science

  Diffusion-based generative models have reformed generative AI, and have enabled new capabilities in the science domain, for example, generating 3D structures of molecules. Due to the intrinsic problem structure of certain tasks, there is often a symmetry in the system, which identifies objects that …

• Hallucination Early Detection in Diffusion Models

  Federico Betti, Lorenzo Baraldi, Lorenzo Baraldi, Rita Cucchiara, Nicu Sebe · 23 April 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-Image generation has seen significant advancements in output realism with the advent of diffusion models. However, diffusion models encounter difficulties when tasked with generating multiple objects, frequently resulting in hallucinations where certain entities are omitted. While existing s…

• Local Diffusion Models and Phases of Data Distributions

  Fangjun Hu, Guangkuo Liu, Yifan F. Zhang, Xun Gao · 23 April 2026 · Generative Adversarial Networks and Image Synthesis

  As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance in synthesizing complicated data distributions through a denoising process gradually guided by score functions. Real-life data, like images, is often spa…

• ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control

  Shelly Golan, Michael Finkelson, Ariel Bereslavsky, Yotam Nitzan, Or Patashnik · 23 April 2026 · Multimodal Machine Learning Applications

  Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scalar reward. When multiple criteria matter, the prevailing practice of ``early scalarization'' collapses rewards into a fixed weighted sum. Thi…

• Cold-Start Forecasting of New Product Life-Cycles via Conditional Diffusion Models

  Ruihan Zhou, Zishi Zhang, Jinhui Han, Yijie Peng, Xiaowei Zhang · 23 April 2026 · Forecasting Techniques and Applications

  Forecasting the life-cycle trajectory of a newly launched product is important for launch planning, resource allocation, and early risk assessment. This task is especially difficult in the pre-launch and early post-launch phases, when product-specific outcome history is limited or unavailable, creat…

• AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model

  Yutian Chen, Shi Guo, Renbiao Jin, Tianshuo Yang, Xin Cai, Yawen Luo, Mingxin Yang, Mulin Yu, Linning Xu, Tianfan Xue · 22 April 2026 · Advanced Vision and Imaging

  Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusion-based approaches mitigates this issues by synthesizing novel views, but they often condition on only one or two capture frames, which rest…

• Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval

  Hang Cheng, Fanhe Dong, Long Zeng · 22 April 2026 · 3D Shape Modeling and Analysis

  This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval methods struggle in zero-shot settings due to the absence of category supervision and the extreme sparsity of sketch inputs. O…

• Conditional Diffusion Modeling with Attention for Probabilistic Battery Capacity Prediction under Real-World Condition

  Chunlin Jiang, Hequn Li, Zhongwei Deng, Jie Shao, Zhansheng Ning · 22 April 2026 · Advanced Battery Technologies Research

  Accurate prediction of lithium-ion battery capacity and its associated uncertainty is essential for reliable battery management but remains challenging due to the stochastic nature of aging. This paper presents a new method, termed the Conditional Diffusion U-Net with Attention (CDUA), which integra…

• Class-specific diffusion models improve military object detection in a low-data domain

  Ella P. Fokkinga, Jan Erik van Woerden, Thijs A. Eker, Sebastiaan P. Snel, Elfi I. S. Hofmeijer, Klamer Schutte, Friso G. Heslinga · 21 April 2026 · Advanced Neural Network Applications

  Diffusion-based image synthesis has emerged as a promising source of synthetic training data for AI-based object detection and classification. In this work, we investigate whether images generated with diffusion can improve military vehicle detection under low-data conditions. We fine-tuned the text…

• StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets

  Anh-Quan Cao, Ivan Lopes, Raoul de Charette · 21 April 2026 · Large Language Models

  Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Leveraging the generalization power of diffusion models, we extend the partial learning setup to a zero-shot setting, training…

• On the Interpolation Effect of Score Smoothing in Diffusion Models

  Zhengdao Chen · 21 April 2026 · Model Reduction and Neural Networks

  Diffusion models have achieved remarkable progress in various domains with an intriguing ability to produce new data that do not exist in the training set. In this work, we study the hypothesis that such creativity arises from the neural network backbone learning a smoothed version of the empirical …

• Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization

  Yinbin Han, Meisam Razaviyayn, Renyuan Xu · 21 April 2026 · Model Reduction and Neural Networks

  Diffusion models have become a leading paradigm in generative AI, with score estimation via denoising score matching as a central component. While recent theory provides strong statistical guarantees, it typically relies on algorithm-agnostic assumptions and treats empirical risk minimization as if …

• UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

  Jiaqi Wang (Beijing University of Posts and Telecommunications, Beijing Academy of Artificial Intelligence), Haoge Deng (Beijing Academy of Artificial Intelligence), Ting Pan (Beijing Academy of Artificial Intelligence), Yang Liu (Beijing Academy of Artificial Intelligence), Chengyuan Wang (Beijing Academy of Artificial Intelligence), Fan Zhang (Beijing Academy of Artificial Intelligence), Yonggang Qi (Beijing University of Posts and Telecommunications), Xinlong Wang (Beijing Academy of Artificial Intelligence) · 21 April 2026 · Reinforcement Learning in Robotics

  Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that naively applying GRPO to UDM leads to training instability and marginal performance g…