Copertina

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Xiao, Zhang, Zekai, Li, Xiang, Chen, Siyi, Zhu, Zhihui, Wang, Peng, Qu, Qing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

Generalization of Diffusion Models Arises with a Balanced Representation Space
di: Zhang, Zekai, et al.
Pubblicazione: (2025)

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

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

Analyzing and Mitigating Model Collapse in Rectified Flow Models
di: Zhu, Huminhao, et al.
Pubblicazione: (2024)

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

Understanding and Improving Transfer Learning of Deep Models via Neural Collapse
di: Li, Xiao, et al.
Pubblicazione: (2022)

Revisiting Diffusion Model Predictions Through Dimensionality
di: Jin, Qing, et al.
Pubblicazione: (2026)

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

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
di: Yaras, Can, et al.
Pubblicazione: (2024)

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

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

AlphaFlow: Understanding and Improving MeanFlow Models
di: Zhang, Huijie, et al.
Pubblicazione: (2025)

Improving Adversarial Energy-Based Model via Diffusion Process
di: Geng, Cong, et al.
Pubblicazione: (2024)

Understanding Diffusion Models via Code Execution
di: Yu, Cheng
Pubblicazione: (2025)

Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models
di: Guo, Xingzhuo, et al.
Pubblicazione: (2025)

Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
di: Xie, Tianyu, et al.
Pubblicazione: (2025)

Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
di: Yi, Mingyang, et al.
Pubblicazione: (2024)

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
di: Li, Muyang, et al.
Pubblicazione: (2024)

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

Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
di: Jiang, Jiachen, et al.
Pubblicazione: (2025)

Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models
di: Bao, Fan, et al.
Pubblicazione: (2024)

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

Safe and Reliable Diffusion Models via Subspace Projection
di: Chen, Huiqiang, et al.
Pubblicazione: (2025)

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
di: Hu, Zijing, et al.
Pubblicazione: (2025)

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
di: Liu, Xuewen, et al.
Pubblicazione: (2024)

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

The Dual Power of Interpretable Token Embeddings: Jailbreaking Attacks and Defenses for Diffusion Model Unlearning
di: Chen, Siyi, et al.
Pubblicazione: (2025)

Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
di: Peng, Xinyu, et al.
Pubblicazione: (2024)

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

Score-based Membership Inference on Diffusion Models
di: Rao, Mingxing, et al.
Pubblicazione: (2025)

GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning
di: Xu, Yanchen, et al.
Pubblicazione: (2025)

Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning
di: Chen, Ping, et al.
Pubblicazione: (2026)

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

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

Robust Classification via a Single Diffusion Model
di: Chen, Huanran, et al.
Pubblicazione: (2023)

Residual Denoising Diffusion Models
di: Liu, Jiawei, et al.
Pubblicazione: (2023)

Improving Fine-Grained Control via Aggregation of Multiple Diffusion Models
di: Yue, Conghan, et al.
Pubblicazione: (2024)