Imagen de Portada

Generalization of Diffusion Models Arises with a Balanced Representation Space

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Zekai, Li, Xiao, Li, Xiang, Shi, Lianghe, Wu, Meng, Tao, Molei, Qu, Qing
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
por: Li, Xiao, et al.
Publicado: (2025)

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
por: Shi, Lianghe, et al.
Publicado: (2025)

Mirror Diffusion Models for Constrained and Watermarked Generation
por: Liu, Guan-Horng, et al.
Publicado: (2023)

Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering
por: Wang, Peng, et al.
Publicado: (2024)

Understanding Generalization in Diffusion Distillation via Probability Flow Distance
por: Zhang, Huijie, et al.
Publicado: (2025)

Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
por: Rojas, Kevin, et al.
Publicado: (2025)

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
por: Li, Wenda, et al.
Publicado: (2024)

Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images
por: Zhu, Sichen, et al.
Publicado: (2025)

LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling
por: Li, Xin, et al.
Publicado: (2024)

CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
por: Wu, Chengfeng, et al.
Publicado: (2026)

Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
por: Li, Xiang, et al.
Publicado: (2024)

Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
por: Zhang, Xinxi, et al.
Publicado: (2024)

DFU: scale-robust diffusion model for zero-shot super-resolution image generation
por: Havrilla, Alex, et al.
Publicado: (2023)

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
por: Hahm, Jaehoon, et al.
Publicado: (2024)

The Emergence of Reproducibility and Generalizability in Diffusion Models
por: Zhang, Huijie, et al.
Publicado: (2023)

Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing
por: Chen, Siyi, et al.
Publicado: (2024)

Latent Diffusion Inversion Requires Understanding the Latent Space
por: Rao, Mingxing, et al.
Publicado: (2025)

Boundary-Constrained Diffusion Models for Floorplan Generation: Balancing Realism and Diversity
por: Stoppani, Leonardo, et al.
Publicado: (2026)

Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
por: Jin, Xin, et al.
Publicado: (2024)

MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
por: Li, Xiang, et al.
Publicado: (2026)

Federated Balanced Learning
por: Li, Jiaze, et al.
Publicado: (2026)

RCDM: Enabling Robustness for Conditional Diffusion Model
por: Xu, Weifeng, et al.
Publicado: (2024)

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
por: Dai, Zeyu, et al.
Publicado: (2025)

Representation-Conditioned Diffusion Models for Guided Training Data Generation
por: Karthikeyan, Nithesh Chandher, et al.
Publicado: (2026)

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
por: Shi, Qingyu, et al.
Publicado: (2025)

Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
por: Qiu, Xingyu, et al.
Publicado: (2025)

Canonical Latent Representations in Conditional Diffusion Models
por: Xu, Yitao, et al.
Publicado: (2025)

Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
por: Zhang, Ziyi, et al.
Publicado: (2024)

Towards Controllable Image Generation through Representation-Conditioned Diffusion Models
por: Karthikeyan, Nithesh Chandher, et al.
Publicado: (2026)

MARBLE: Multi-Aspect Reward Balance for Diffusion RL
por: Zhao, Canyu, et al.
Publicado: (2026)

Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum
por: Haque, Nashrah, et al.
Publicado: (2024)

Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
por: Baade, Alan, et al.
Publicado: (2026)

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
por: Wang, Peng, et al.
Publicado: (2023)

Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction
por: Li, Xiao, et al.
Publicado: (2025)

Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification
por: Li, Bohan, et al.
Publicado: (2023)

Draw Like an Artist: Complex Scene Generation with Diffusion Model via Composition, Painting, and Retouching
por: Liu, Minghao, et al.
Publicado: (2024)

Enhancing Counterfactual Image Generation Using Mahalanobis Distance with Distribution Preferences in Feature Space
por: Zhang, Yukai, et al.
Publicado: (2024)

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models
por: Gandikota, Rohit, et al.
Publicado: (2025)

Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model
por: Zhu, Shen, et al.
Publicado: (2025)

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
por: Wu, Fang, et al.
Publicado: (2026)