Cover Image

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Zhuguanyu, Gong, Ruihao, Yong, Yang, Huang, Yushi, Fan, Xiangyu, Yang, Lei, Lin, Dahua, Liu, Xianglong
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals
by: Fan, Xiangyu, et al.
Published: (2025)

Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models
by: Du, Jinyang, et al.
Published: (2026)

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

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

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
by: Liu, Tao, et al.
Published: (2026)

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

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
by: Huang, Yushi, et al.
Published: (2023)

MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis
by: Shao, Shitong, et al.
Published: (2025)

Temporal Feature Matters: A Framework for Diffusion Model Quantization
by: Huang, Yushi, et al.
Published: (2024)

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
by: Zhao, Min, et al.
Published: (2026)

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
by: Lv, Chengtao, et al.
Published: (2026)

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
by: Ding, Zihan, et al.
Published: (2024)

Adversarial Concept Distillation for One-Step Diffusion Personalization
by: Yang, Yixiong, et al.
Published: (2025)

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
by: Zhou, Mingyuan, et al.
Published: (2024)

Few-Step Distillation for Text-to-Image Generation: A Practical Guide
by: Pu, Yifan, et al.
Published: (2025)

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
by: Jiang, Dengyang, et al.
Published: (2026)

Cross-Resolution Distribution Matching for Diffusion Distillation
by: Chen, Feiyang, et al.
Published: (2026)

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

LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation
by: Huang, Yushi, et al.
Published: (2025)

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
by: Huang, Yushi, et al.
Published: (2024)

DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
by: Zhao, Tong, et al.
Published: (2026)

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

DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching
by: Yang, Meng, et al.
Published: (2025)

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
by: Lu, Yanzuo, et al.
Published: (2025)

TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
by: Liu, Xiangyu, et al.
Published: (2026)

TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution
by: Dong, Linwei, et al.
Published: (2024)

RealisticDreamer: Guidance Score Distillation for Few-shot Gaussian Splatting
by: Wu, Ruocheng, et al.
Published: (2025)

Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
by: You, Yuyang, et al.
Published: (2026)

SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation
by: Nguyen, Thuan Hoang, et al.
Published: (2023)

Stable Score Distillation
by: Zhu, Haiming, et al.
Published: (2025)

Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations
by: Zhang, Yuan, et al.
Published: (2026)

Indirect Gradient Matching for Adversarial Robust Distillation
by: Lee, Hongsin, et al.
Published: (2023)

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

Distribution Matching Distillation without Fake Score Network
by: Kim, Youngjoong, et al.
Published: (2026)

Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images
by: Yang, Jinghe, et al.
Published: (2025)

Training-Free Video Editing via Optical Flow-Enhanced Score Distillation
by: Zhu, Lianghan, et al.
Published: (2024)

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
by: Zhou, Mingyuan, et al.
Published: (2024)

Robust Dataset Distillation by Matching Adversarial Trajectories
by: Lai, Wei, et al.
Published: (2025)

VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
by: Wang, Hanyang, et al.
Published: (2025)

Target-Balanced Score Distillation
by: Xu, Zhou, et al.
Published: (2025)