Conditional Diffusion Models

Follow this topic Ask about this topic

Conditional diffusion models learn to generate samples from a distribution specified by inputs such as images, labels, text, measurements, or physical parameters. Common approaches inject conditions into U-Nets or diffusion transformers through cross-attention, adaptive normalization, ControlNet branches, or inpainting, while classifier-free guidance adjusts conditional influence during sampling. They are used for image and video editing, medical reconstruction, time-series forecasting, scientific simulation, and molecular or engineering design, with evaluation spanning fidelity, condition accuracy, uncertainty, and physical validity. A central challenge is balancing faithful control with diversity and realism while keeping sampling efficient and ensuring models generalize to unseen conditions or domains.

Latest papers

279 papers32 papers in the last four weeks, up 23% on the four weeks before. 0.2% of all new papers.

Uncertainty-Guided Cross-Modal Alignment for Diffusion-Based IoT Intrusion Detection
Oct 29, 2026Mahdi Arab Loodaricheh, Anita Raja, Mohammad Hossein ManshaeiIoT Intrusion Detection Cross-Modal Alignment
Department of Computer Science, Hunter College and The Graduate Center, CUNY, New York, NY, USA
SCDM-HTD: Spectral-Wise Conditional Diffusion Model for Hyperspectral Target Detection
Oct 23, 2026Dunbin Shen, Wenfeng Kong, Jianjun Liu +2Hyperspectral Imaging Conditional Diffusion Models
School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, China · School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
Dancing Diffusion: Learning Continuous Programs for Image Generation and Editing
Oct 20, 2026Cui Enhe, Jinyue Yang, Bojian Yin +1Diffusion-Based Image Generation Diffusion-Based Image Editing
Renmin University of China · Institute of Automation, Chinese Academy of Sciences
Probabilistic Limit Order Book Forecasting with Conditional Diffusion Models
Oct 18, 2026Junyu Chen, Franklin Liu, Moshu Xu +1Limit Order Book Forecasting Limit Order Book Modeling
Department of Statistics and Data Science, Tsinghua University, Beijing, China
OrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting
Oct 15, 2026Jung Hun Phee, Tucker BalchLimit Order Book Forecasting Limit Order Book Modeling
Georgia Institute of Technology, Atlanta, Georgia, USA · Emory University, Atlanta, Georgia, USA
Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion
Oct 15, 2026Renxiang Huang, Yuchen Liang, Yingbin Liang +2Diffusion Models Diffusion Sampling
Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA, 95616, USA · Luddy School of Informatics, Computing, and Engineering, Indiana University Indianapolis, Indianapolis, IN, 46202, USA · Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, 43210, USA
Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting
Oct 14, 2026Shadi Omari, Bashar Khoury, Assaf SchusterProbabilistic Time Series Forecasting Diffusion Guidance
Department of Computer Science, Technion – Israel Institute of Technology
Representation Conditioning for Generation
Oct 14, 2026Saeed Razavi, Xingjian Leng, Liang ZhengDiffusion-Based Image Generation Diffusion Transformer
Australian National University
Decoupled Drift-Diffusion World Models for Consistent Future Frame Prediction
Oct 13, 2026Anton Arapin, Aditya Singh, Yixin Wang +2Aleatoric Uncertainty Action-Conditioned World Models
University of Michigan · NVIDIA
Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes
Oct 13, 2026Ethan Baron, Alan N. Amin, Andrew Gordon WilsonPhylogenetic Inference Generative Modeling
New York University
HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion
Oct 12, 2026Yating Wang, Kui Wu, Ran Yi +5Conditional Diffusion Models 3D Diffusion Models
Shanghai Jiao Tong University · LIGHTSPEED
MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation
Oct 12, 2026Protyay Dey, Ayush Roy, Hyuna Cho +2Functional Connectivity Neuroimaging
University at Buffalo, SUNY, USA · National Institutes of Health, USA · POSTECH, South Korea
Controllable Diverse Sampling through Pullback Directions
Oct 9, 2026Sylvain Dehayem Kenfouo, Aaron Zweig, Mingxuan Zhang +1Image Generation Diffusion Model Sampling
École Polytechnique, Institut Polytechnique de Paris · New York Genome Center · Irving Institute for Cancer Dynamics, Columbia University +4
Finite-Sample Guarantees for Fully Discrete Conditional Diffusion Models
Oct 9, 2026Qiuyun ZhuConditional Diffusion Models Diffusion Sampling
Department of Statistics and Actuarial Science University of Iowa
Opening the Black Box of Classifier-Free Guidance via Information Bottleneck
Oct 9, 2026Jiayang Gao, Tianyi Zheng, Jiayang Zou +5Classifier-Free Guidance Inference-Time Guidance
Shanghai Jiao Tong University, Shanghai, China · vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., China · Stanford University, California, USA +1
CoVA: Composing VAE Representations for Generative Learning
Oct 9, 2026Zhaowei Chen, Yikai Ge, Linze Li +2Diffusion-Based Image Generation Diffusion Transformer
Jiiov Technology · Nankai University
MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design
Oct 9, 2026Jixin Tang, Ji Guo, Jun ZhaoInverse Design Reward Design for RL
Fudan University
Diffusion Precipitation Generation with Medium-range Weather Forecasting
Oct 9, 2026Guowen Li, Yang Liu, Mengxuan Chen +11Precipitation Forecasting Weather Forecasting
Tsinghua University · The Chinese University of Hong Kong · The Hong Kong University of S & T +5
Memorization and Malign Generalization in Conditional Diffusion Models with Random Features
Oct 8, 2026Gwangho Kim, Sungyoon LeeRandom Feature Methods Conditional Diffusion Models
Department of Computer Science Hanyang University, Seoul
Position Forcing: Self-Conditioning 3D Generation
Oct 7, 2026Ziheng Ouyang, Zeqiang Lai, Jiarui Chen +73D Shape Generation 3D Diffusion Models
VCIP, Nankai University · Tencent Hunyuan · MMLab, CUHK +3
Noise Your Prompt: Noising Conditioning Tokens in Continuous Diffusion Language Models
Oct 6, 2026Justin JungDiffusion Language Model Training Continuous Diffusion Language Models
Lateral Intelligence
Learning Transition Kernels of Jump-Diffusion Processes with Conditional Diffusion Models
Oct 6, 2026Yuzhen Zhao, Yating Liu, Quentin GuibertStochastic Differential Equations Conditional Distribution Estimation
CEREMADE, CNRS, Universite Paris-Dauphine, PSL, 75016 Paris, France
SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation
Oct 6, 2026Jixing Zhou, Xinming HuangChannel Estimation Conditional Diffusion Models
Worcester Polytechnic Institute Worcester, MA, USA
Feature Information Dynamics in Diffusion
Oct 6, 2026Jia-Shu Pan, Tao Zhang, Yufei Huang +2Conditional Diffusion Models Diffusion Models
Department of Artificial Intelligence, School of Engineering, Westlake University · Zhejiang University · Research School of Astronomy and Astrophysics, Australian National University
SALD: Self-Referenced Advantage Learning for Diffusion Models
Oct 1, 2026Aryan Das, Surjo Dey, Koushik Biswas +4T2I Generation Conditional Diffusion Models
Indian Institute of Technology Kanpur, India · Rajiv Gandhi Institute of Petroleum Technology, India · IIIT Delhi, India +2
Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
Oct 1, 2026Sidney Bender, Benedikt Kunz, Ahmed Zeid +3Disentangled Representation Learning Counterfactual Explanations
Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Germany · Machine Learning Group, Technische Universität Berlin, Berlin, Germany
MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generation
Sep 30, 2026Pengfei Li, Mohammad KhalilCopula Models Synthetic Tabular Data Generation
Centre for the Science of Learning & Technology (SLATE), University of Bergen, Bergen, Norway
Proper Scoring Rule-based Diffusion for Probabilistic Weather Forecasting
Sep 29, 2026Joonhyeong Park, Giung Nam, Hyungi Lee +3Probabilistic Forecasting Proper Scoring Rules
KAIST · Kookmin University · New York University
ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation
Sep 29, 2026Fariza Rashid, Duc Van Le, Rahat Masood +3Time Series Imputation Conditional Diffusion Models
University of Sydney · University of New South Wales
Physics-Guided Conditional Diffusion Model for Rare Event Synthesis and Diagnosis for the Water-Gas Shift Reaction
Sep 28, 2026Md Abrar Rafid Siddique, Bibek Aryal, Qiugang LuPhysics-Informed Generative Modeling Synthetic Anomaly Generation
Department of Chemical Engineering, Texas Tech University, Lubbock, TX 79409, USA

Oct 29, 2026J/K move · Enter open · S save

Uncertainty-Guided Cross-Modal Alignment for Diffusion-Based IoT Intrusion Detection

Mahdi Arab Loodaricheh, Anita Raja, Mohammad Hossein Manshaei

Department of Computer Science, Hunter College and The Graduate Center, CUNY, New York, NY, USA

IoT Intrusion Detection Cross-Modal Alignment Multimodal Diffusion Models Diffusion-Based Data Augmentation Conditional Diffusion Models

Open paper AskPDF arXiv

Diffusion models evolve noisy states toward a learned data distribution, so their sampling behavior depends on the geometry of the representation in which denoising occurs. This dependence is especially important for multimodal data: independently trained encoders can map synchronized views to incompatible latent regions, while uniform alignment can let an uncertain view distort the shared geometry. To address this gap, we introduce a novel reliability-guided alignment rule that uses normalized VAE posterior variance to control directional cross-modal influence before diffusion training. We study this issue in minority-attack generation for imbalanced Internet-of-Things intrusion detection. Tabular flow attributes, a DeepInsight image, and a packet sequence are encoded by modality-specific variational autoencoders. Per-modality normalized VAE posterior variances provide bounded, sample-specific weighting signals in an asymmetric stop-gradient alignment objective. We use these quantities as heuristic encoder-derived reliability proxies rather than calibrated probabilistic uncertainties. The full modality-specific latent means obtained after alignment fine-tuning are standardized and modeled jointly by a class-conditional EDM; a second-order sampler then generates paired attack-conditioned latent blocks for the three decoders. In controlled experiments on TON-IoT, uncertainty-aware alignment obtains the highest mean precision, recall, density, and coverage among three diffusion variants. Augmenting only the training split yields ROC-AUC 0.9515, PR-AUC 0.8954, balanced accuracy 0.8395, and attack-class F1 0.7940 on an untouched real test set. Among the two variants with matched alignment fine-tuning, posterior-variance-based weighting improves both tabular generative fidelity and downstream detection relative to uniform weighting.