Image de couverture de livre

Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Yixian, Luo, Shengjie, Wang, Liwei, He, Di, Liu, Chang
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Diffusion Model with Perceptual Loss
par: Lin, Shanchuan, et autres
Publié: (2023)

Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning
par: Moser, Brian B., et autres
Publié: (2024)

Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise
par: Zhang, Zhenkai, et autres
Publié: (2023)

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

Stitched Value Model for Diffusion Alignment
par: Go, Hyojun, et autres
Publié: (2026)

Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts
par: Chang, Jinho, et autres
Publié: (2024)

Bridging Geometric States via Geometric Diffusion Bridge
par: Luo, Shengjie, et autres
Publié: (2024)

Improved Diffusion-based Generative Model with Better Adversarial Robustness
par: Wang, Zekun, et autres
Publié: (2025)

Quotient-Space Diffusion Models
par: Xu, Yixian, et autres
Publié: (2026)

RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
par: Zhang, Xinchen, et autres
Publié: (2024)

On the Design Fundamentals of Diffusion Models: A Survey
par: Chang, Ziyi, et autres
Publié: (2023)

Improving Interpretation Faithfulness for Vision Transformers
par: Hu, Lijie, et autres
Publié: (2023)

Occlusion-Aware Diffusion Model for Pedestrian Intention Prediction
par: Liu, Yu, et autres
Publié: (2025)

Text-Aware Diffusion for Policy Learning
par: Luo, Calvin, et autres
Publié: (2024)

Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
par: Cai, Rui, et autres
Publié: (2025)

Improving the Diffusability of Autoencoders
par: Skorokhodov, Ivan, et autres
Publié: (2025)

FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models
par: Hu, Rui, et autres
Publié: (2024)

Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models
par: Li, Wenhao, et autres
Publié: (2023)

Improving Compositional Generation with Diffusion Models Using Lift Scores
par: Yu, Chenning, et autres
Publié: (2025)

Improving Diffusion Models for Inverse Problems using Manifold Constraints
par: Chung, Hyungjin, et autres
Publié: (2022)

Conjugate-Gradient-like Based Adaptive Moment Estimation Optimization Algorithm for Deep Learning
par: Tian, Jiawu, et autres
Publié: (2024)

DMin: Scalable Training Data Influence Estimation for Diffusion Models
par: Lin, Huawei, et autres
Publié: (2024)

GARDO: Reinforcing Diffusion Models without Reward Hacking
par: He, Haoran, et autres
Publié: (2025)

Pixel-Space Post-Training of Latent Diffusion Models
par: Zhang, Christina, et autres
Publié: (2024)

From Text to Pose to Image: Improving Diffusion Model Control and Quality
par: Bonnet, Clément, et autres
Publié: (2024)

Reconstruction Alignment Improves Unified Multimodal Models
par: Xie, Ji, et autres
Publié: (2025)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
par: Zou, Chang, et autres
Publié: (2024)

ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation
par: Patni, Suraj, et autres
Publié: (2024)

Input-Adaptive Generative Dynamics in Diffusion Models
par: Xing, Yucheng, et autres
Publié: (2024)

Improving Diffusion-Based Image Synthesis with Context Prediction
par: Yang, Ling, et autres
Publié: (2024)

Diagnosing Shoulder Disorders Using Multimodal Large Language Models and Consumer-Grade Cameras
par: Hong, Jindong, et autres
Publié: (2025)

FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
par: Liu, Jiacheng, et autres
Publié: (2025)

Diffuse and Disperse: Image Generation with Representation Regularization
par: Wang, Runqian, et autres
Publié: (2025)

Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection
par: Zhou, Meilun, et autres
Publié: (2025)

Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
par: Jun, Youngjun, et autres
Publié: (2024)

ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models
par: Sepehri, Mohammad Shahab, et autres
Publié: (2026)

Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models
par: Berry, Lucas, et autres
Publié: (2024)

AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models
par: Li, Yuming, et autres
Publié: (2026)

Accelerating Diffusion Transformers with Token-wise Feature Caching
par: Zou, Chang, et autres
Publié: (2024)

Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors
par: Tao, Linwei, et autres
Publié: (2024)