Cover Image

MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shao, Shitong, Yi, Hongwei, Guo, Hanzhong, Ye, Tian, Zhou, Daquan, Lingelbach, Michael, Xu, Zhiqiang, Xie, Zeke
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
by: Yi, Hongwei, et al.
Published: (2025)

Real-time One-Step Diffusion-based Expressive Portrait Videos Generation
by: Guo, Hanzhong, et al.
Published: (2024)

Magic 1-For-1: Generating One Minute Video Clips within One Minute
by: Yi, Hongwei, et al.
Published: (2025)

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

FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
by: Shao, Shitong, et al.
Published: (2026)

Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
by: Shao, Shitong, et al.
Published: (2024)

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
by: Shao, Shitong, et al.
Published: (2024)

Self-supervised Dataset Distillation: A Good Compression Is All You Need
by: Zhou, Muxin, et al.
Published: (2024)

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

DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation
by: Shen, Zhiqiang, et al.
Published: (2024)

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

Weak-to-Strong Diffusion with Reflection
by: Bai, Lichen, et al.
Published: (2025)

Efficient Video Diffusion Models: Advancements and Challenges
by: Shao, Shitong, et al.
Published: (2026)

OD3: Optimization-free Dataset Distillation for Object Detection
by: Khatib, Salwa K. Al, et al.
Published: (2025)

CoRe^2: Collect, Reflect and Refine to Generate Better and Faster
by: Shao, Shitong, et al.
Published: (2025)

Rethinking Centered Kernel Alignment in Knowledge Distillation
by: Zhou, Zikai, et al.
Published: (2024)

Golden Noise for Diffusion Models: A Learning Framework
by: Zhou, Zikai, et al.
Published: (2024)

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection
by: Bai, Lichen, et al.
Published: (2024)

Infinite Mask Diffusion for Few-Step Distillation
by: Yoo, Jaehoon, et al.
Published: (2026)

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

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

LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
by: Shao, Shitong, et al.
Published: (2026)

Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
by: Shao, Shitong, et al.
Published: (2023)

MagicPool: Dealing with Magic State Distillation Failures on Large-Scale Fault-Tolerant Quantum Computer
by: Hirano, Yutaka, et al.
Published: (2024)

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
by: Ildiz, M. Emrullah, et al.
Published: (2024)

Efficient Magic State Distillation by Zero-Level Distillation
by: Itogawa, Tomohiro, et al.
Published: (2024)

Dataset Distillation via Curriculum Data Synthesis in Large Data Era
by: Yin, Zeyuan, et al.
Published: (2023)

Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspective
by: Huang, Rui, et al.
Published: (2025)

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

HumanNet: Scaling Human-centric Video Learning to One Million Hours
by: Deng, Yufan, et al.
Published: (2026)

Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
by: Li, Baiang, et al.
Published: (2026)

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
by: Zhao, Ji, et al.
Published: (2026)

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

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

Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
by: Ding, Yongqi, et al.
Published: (2025)

CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think
by: Sun, Zening, et al.
Published: (2026)

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
by: Zhou, Zanwei, 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)

Distilling Magic States in the Bicycle Architecture
by: Xu, Shifan, et al.
Published: (2026)

Constant-Overhead Magic State Distillation
by: Wills, Adam, et al.
Published: (2024)