Copertina

You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dou, Hongkun, Li, Zeyu, Jiang, Xingyu, Li, Hongjue, Yang, Lijun, Yao, Wen, Deng, Yue
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes
di: Dou, Hongkun, et al.
Pubblicazione: (2026)

Global Modeling Matters: A Fast, Lightweight and Effective Baseline for Efficient Image Restoration
di: Jiang, Xingyu, et al.
Pubblicazione: (2025)

You Only Look Omni Gradient Backpropagation for Moving Infrared Small Target Detection
di: Zhang, Guoyi, et al.
Pubblicazione: (2025)

Image Restoration via Multi-domain Learning
di: Jiang, Xingyu, et al.
Pubblicazione: (2025)

Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction
di: Liu, Shaohua, et al.
Pubblicazione: (2026)

Three Creates All: You Only Sample 3 Steps
di: Cai, Yuren, et al.
Pubblicazione: (2026)

One Step Diffusion via Shortcut Models
di: Frans, Kevin, et al.
Pubblicazione: (2024)

You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
di: Luo, Yihong, et al.
Pubblicazione: (2024)

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
di: Liu, Gongye, et al.
Pubblicazione: (2023)

High-Order Matching for One-Step Shortcut Diffusion Models
di: Chen, Bo, et al.
Pubblicazione: (2025)

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
di: Shao, Shitong, et al.
Pubblicazione: (2023)

You Only Need One Stage: Novel-View Synthesis From A Single Blind Face Image
di: Wang, Taoyue, et al.
Pubblicazione: (2026)

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

Physics-aligned Schrödinger bridge
di: Li, Zeyu, et al.
Pubblicazione: (2024)

Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation
di: Wang, Chuhan, et al.
Pubblicazione: (2026)

Accelerating Diffusion Sampling with Optimized Time Steps
di: Xue, Shuchen, et al.
Pubblicazione: (2024)

You Only Look Bottom-Up for Monocular 3D Object Detection
di: Xiong, Kaixin, et al.
Pubblicazione: (2024)

Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration
di: Sun, Xiaohui, et al.
Pubblicazione: (2026)

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

DPoser: Diffusion Model as Robust 3D Human Pose Prior
di: Lu, Junzhe, et al.
Pubblicazione: (2023)

You Only Look at Once for Real-time and Generic Multi-Task
di: Wang, Jiayuan, et al.
Pubblicazione: (2023)

You Only Speak Once to See
di: Yang, Wenhao, et al.
Pubblicazione: (2024)

On the Design of One-step Diffusion via Shortcutting Flow Paths
di: Lin, Haitao, et al.
Pubblicazione: (2025)

Asymmetric VAE for One-Step Video Super-Resolution Acceleration
di: Li, Jianze, et al.
Pubblicazione: (2025)

Unbiased Gradient Estimation for Event Binning via Functional Backpropagation
di: Chen, Jinze, et al.
Pubblicazione: (2026)

YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images
di: Liu, Chenguang, et al.
Pubblicazione: (2024)

You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection
di: Kuhse, Daniel, et al.
Pubblicazione: (2025)

You Only Look Twice! for Failure Causes Identification of Drill Bits
di: Yamani, Asma, et al.
Pubblicazione: (2024)

Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models
di: Li, Chao, et al.
Pubblicazione: (2025)

Common Diffusion Noise Schedules and Sample Steps are Flawed
di: Lin, Shanchuan, et al.
Pubblicazione: (2023)

A Decade of You Only Look Once (YOLO) for Object Detection: A Review
di: Ramos, Leo Thomas, et al.
Pubblicazione: (2025)

YotoR-You Only Transform One Representation
di: Villa, José Ignacio Díaz, et al.
Pubblicazione: (2024)

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

You Only Submit One Image to Find the Most Suitable Generative Model
di: Zhou, Zhi, et al.
Pubblicazione: (2024)

You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detection
di: Hong, Mingbo, et al.
Pubblicazione: (2024)

You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
di: Zhou, Huayi, et al.
Pubblicazione: (2025)

AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation
di: Tang, Shengkun, et al.
Pubblicazione: (2023)

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

You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes
di: Jia, Jinrang, et al.
Pubblicazione: (2026)

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