Image de couverture de livre

Training-Free Adaptation of Diffusion Models via Doob's $h$-Transform

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhu, Qijie, Ye, Zeqi, Liu, Han, Wang, Zhaoran, Chen, Minshuo
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Provable Separations between Memorization and Generalization in Diffusion Models
par: Ye, Zeqi, et autres
Publié: (2025)

Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
par: Ye, Zeqi, et autres
Publié: (2025)

Provable Statistical Rates for Consistency Diffusion Models
par: Dou, Zehao, et autres
Publié: (2024)

Infinite-dimensional generative diffusions via Doob's h-transform
par: Pieper-Sethmacher, Thorben, et autres
Publié: (2026)

DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models
par: Bu, Dake, et autres
Publié: (2026)

Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?
par: Yin, Yutong, et autres
Publié: (2025)

Gradient Guidance for Diffusion Models: An Optimization Perspective
par: Guo, Yingqing, et autres
Publié: (2024)

An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
par: Chen, Minshuo, et autres
Publié: (2024)

Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
par: Fu, Hengyu, et autres
Publié: (2024)

Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
par: Zhang, Zixuan, et autres
Publié: (2026)

Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
par: Fu, Hengyu, et autres
Publié: (2024)

Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
par: Wu, Yuchen, et autres
Publié: (2024)

Diffusion Model for Data-Driven Black-Box Optimization
par: Li, Zihao, et autres
Publié: (2024)

Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching
par: Chang, Jinyuan, et autres
Publié: (2026)

Counterfactual Generative Models for Time-Varying Treatments
par: Wu, Shenghao, et autres
Publié: (2023)

Diffusion Factor Models: Generating High-Dimensional Returns with Factor Structure
par: Chen, Minshuo, et autres
Publié: (2025)

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality
par: Hu, Jerry Yao-Chieh, et autres
Publié: (2024)

TFG: Unified Training-Free Guidance for Diffusion Models
par: Ye, Haotian, et autres
Publié: (2024)

Martingale Neural Operators: Learning Stochastic Marginals via Doob-Meyer Factorization
par: Hidajat, Kai
Publié: (2026)

An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models
par: Zhang, Yufeng, et autres
Publié: (2022)

Training-Free Looped Transformers
par: Chen, Lizhang, et autres
Publié: (2026)

Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks
par: Li, Zihao, et autres
Publié: (2023)

Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance
par: Sani, Matina Mahdizadeh, et autres
Publié: (2026)

Parameter-Efficient Subspace Optimization for LLM Fine-Tuning
par: Lou, Yuchen, et autres
Publié: (2025)

Training-Free Self-Correction for Multimodal Masked Diffusion Models
par: Ouyang, Yidong, et autres
Publié: (2026)

Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds
par: Xu, Zhenghao, et autres
Publié: (2023)

Training-Free Constrained Generation With Stable Diffusion Models
par: Zampini, Stefano, et autres
Publié: (2025)

A Training-Free Conditional Diffusion Model for Learning Stochastic Dynamical Systems
par: Liu, Yanfang, et autres
Publié: (2024)

Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting
par: Pan, Licheng, et autres
Publié: (2025)

Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs
par: Zhong, Han, et autres
Publié: (2021)

Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo
par: Pei, Jiangbo, et autres
Publié: (2024)

Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
par: Zhang, Zhen, et autres
Publié: (2024)

A Theoretical Perspective for Speculative Decoding Algorithm
par: Yin, Ming, et autres
Publié: (2024)

Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration
par: Shen, Jucheng, et autres
Publié: (2025)

GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models
par: Zhang, Yiming, et autres
Publié: (2026)

Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings
par: Peetathawatchai, Pura, et autres
Publié: (2024)

Cutting the Skip: Training Residual-Free Transformers
par: Ji, Yiping, et autres
Publié: (2025)

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
par: Zhu, Haowei, et autres
Publié: (2026)

A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization
par: Zhu, Yuchen, et autres
Publié: (2024)

Stitch: Training-Free Position Control in Multimodal Diffusion Transformers
par: Bader, Jessica, et autres
Publié: (2025)