Imagen de Portada

$R_\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fan, Linqian, Sun, Peiqin, Wen, Tiancheng, Lu, Shun, Song, Chengru
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
por: Wu, Zhuguanyu, et al.
Publicado: (2026)

Video RWKV:Video Action Recognition Based RWKV
por: Yin, Zhuowen, et al.
Publicado: (2024)

ReDiF: Reinforced Distillation for Few Step Diffusion
por: Tighkhorshid, Amirhossein, et al.
Publicado: (2025)

Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
por: Dong, Linwei, et al.
Publicado: (2026)

Diffusion Reinforcement Learning via Centered Reward Distillation
por: Zhu, Yuanzhi, et al.
Publicado: (2026)

Regularized Distribution Matching Distillation for One-step Unpaired Image-to-Image Translation
por: Rakitin, Denis, et al.
Publicado: (2024)

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
por: Lee, Jeongjae, et al.
Publicado: (2026)

Inverse Bridge Matching Distillation
por: Gushchin, Nikita, et al.
Publicado: (2025)

SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching
por: Li, Xinghui, et al.
Publicado: (2023)

Distilled Datamodel with Reverse Gradient Matching
por: Ye, Jingwen, et al.
Publicado: (2024)

ReDistill: Residual Encoded Distillation for Peak Memory Reduction of CNNs
por: Chen, Fang, et al.
Publicado: (2024)

One-Step Diffusion Distillation through Score Implicit Matching
por: Luo, Weijian, et al.
Publicado: (2024)

Knowledge Distillation Based on Transformed Teacher Matching
por: Zheng, Kaixiang, et al.
Publicado: (2024)

Score Distillation of Flow Matching Models
por: Zhou, Mingyuan, et al.
Publicado: (2025)

Diffusion Reward: Learning Rewards via Conditional Video Diffusion
por: Huang, Tao, et al.
Publicado: (2023)

Generative Distribution Distillation
por: Cui, Jiequan, et al.
Publicado: (2025)

Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
por: Zhang, Ziyi, et al.
Publicado: (2024)

Enhancing Vector Quantization with Distributional Matching: A Theoretical and Empirical Study
por: Fang, Xianghong, et al.
Publicado: (2025)

Optimizing Few-Step Generation with Adaptive Matching Distillation
por: Bai, Lichen, et al.
Publicado: (2026)

DataDAM: Efficient Dataset Distillation with Attention Matching
por: Sajedi, Ahmad, et al.
Publicado: (2023)

Exploring Diffusion and Flow Matching Under Generator Matching
por: Patel, Zeeshan, et al.
Publicado: (2024)

Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization
por: Fan, Jiajun, et al.
Publicado: (2025)

The Coupling Within: Flow Matching via Distilled Normalizing Flows
por: Berthelot, David, et al.
Publicado: (2026)

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
por: Cai, Xu, et al.
Publicado: (2025)

UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
por: Cheng, Yufeng, et al.
Publicado: (2025)

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
por: Lu, Yunhong, et al.
Publicado: (2025)

Directly Fine-Tuning Diffusion Models on Differentiable Rewards
por: Clark, Kevin, et al.
Publicado: (2023)

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

One-step Diffusion Models with $f$-Divergence Distribution Matching
por: Xu, Yilun, et al.
Publicado: (2025)

SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching
por: Lee, Yongmin, et al.
Publicado: (2024)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
por: Li, Quanhao, et al.
Publicado: (2026)

SFDDM: Single-fold Distillation for Diffusion models
por: Hong, Chi, et al.
Publicado: (2024)

Amortized Posterior Sampling with Diffusion Prior Distillation
por: Mammadov, Abbas, et al.
Publicado: (2024)

SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models
por: Lian, Jiesong, et al.
Publicado: (2025)

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
por: Bergmeister, Andreas, et al.
Publicado: (2026)

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder
por: Lee, Yongmin, et al.
Publicado: (2025)

Few-Step Diffusion via Score identity Distillation
por: Zhou, Mingyuan, et al.
Publicado: (2025)

Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
por: Meanti, Giacomo, et al.
Publicado: (2025)

Dataset Distillation via the Wasserstein Metric
por: Liu, Haoyang, et al.
Publicado: (2023)

Multistep Distillation of Diffusion Models via Moment Matching
por: Salimans, Tim, et al.
Publicado: (2024)