Cover Image

Not All Tokens Need 40 Steps: Heterogeneous Step Allocation in Diffusion Transformers for Efficient Video Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chu, Ernie, Patel, Vishal M.
Format:	Preprint
Published:	2026
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

Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling
by: Chu, Ernie, et al.
Published: (2026)

StepAL: Step-aware Active Learning for Cataract Surgical Videos
by: Shah, Nisarg A., et al.
Published: (2025)

SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
by: Vallaeys, Théophane, et al.
Published: (2025)

Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
by: Pu, Yifan, et al.
Published: (2024)

Clockwork Diffusion: Efficient Generation With Model-Step Distillation
by: Habibian, Amirhossein, et al.
Published: (2023)

Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
by: Qiao, Bingtian, et al.
Published: (2026)

Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers
by: Nair, Nithin Gopalakrishnan, et al.
Published: (2024)

Step Saver: Predicting Minimum Denoising Steps for Diffusion Model Image Generation
by: Yu, Jean, et al.
Published: (2024)

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

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
by: He, Xiaoxuan, et al.
Published: (2026)

VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement
by: Zhang, Shulian, et al.
Published: (2025)

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
by: Chen, Zheng, et al.
Published: (2025)

Aligning Step-by-Step Instructional Diagrams to Video Demonstrations
by: Zhang, Jiahao, et al.
Published: (2023)

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

Frame by Familiar Frame: Understanding Replication in Video Diffusion Models
by: Rahman, Aimon, et al.
Published: (2024)

Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
by: Kumar, Amandeep, et al.
Published: (2026)

Dreamguider: Improved Training free Diffusion-based Conditional Generation
by: Nair, Nithin Gopalakrishnan, et al.
Published: (2024)

Low-rank Adaptation-based All-Weather Removal for Autonomous Navigation
by: Rajagopalan, Sudarshan, et al.
Published: (2024)

Diffusion Models Are Innate One-Step Generators
by: Zheng, Bowen, et al.
Published: (2024)

Phased One-Step Adversarial Equilibrium for Video Diffusion Models
by: Cheng, Jiaxiang, et al.
Published: (2025)

AWRaCLe: All-Weather Image Restoration using Visual In-Context Learning
by: Rajagopalan, Sudarshan, et al.
Published: (2024)

Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion
by: Gregorek, Jakub, et al.
Published: (2026)

Think Before You Diffuse: Infusing Physical Rules into Video Diffusion
by: Zhang, Ke, et al.
Published: (2025)

Step Differences in Instructional Video
by: Nagarajan, Tushar, et al.
Published: (2024)

EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
by: Tan, Xiaofeng, et al.
Published: (2026)

UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space
by: Liu, Yong, et al.
Published: (2025)

Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
by: Liu, Hao, et al.
Published: (2026)

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
by: NextStep Team, et al.
Published: (2025)

GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration
by: Rajagopalan, Sudarshan, et al.
Published: (2024)

Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
by: A, Pranav, et al.
Published: (2026)

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

RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration
by: Rajagopalan, Sudarshan, et al.
Published: (2025)

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
by: Fei, Hao, et al.
Published: (2024)

Step by Step Network
by: Han, Dongchen, et al.
Published: (2025)

Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution
by: Tai, Yu-Shan, et al.
Published: (2026)

One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution
by: Fang, Yushun, et al.
Published: (2025)

Diffusion Adversarial Post-Training for One-Step Video Generation
by: Lin, Shanchuan, et al.
Published: (2025)

Denoising Diffusion Step-aware Models
by: Yang, Shuai, et al.
Published: (2023)

EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow
by: Park, Dogyun, et al.
Published: (2026)

You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
by: Noroozi, Mehdi, et al.
Published: (2024)