Cover Image

DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Tong, Lei, Mingkun, Yuan, Liangyu, Yang, Yanming, Song, Chenxi, Wang, Yang, Zhu, Beier, Zhang, Chi
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

Few-Step Diffusion Sampling Through Instance-Aware Discretizations
by: Yuan, Liangyu, et al.
Published: (2026)

Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
by: Wang, Ruoyu, et al.
Published: (2025)

Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
by: Yuan, Liangyu, et al.
Published: (2026)

Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models
by: Zhu, Beier, et al.
Published: (2025)

StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements
by: Lei, Mingkun, et al.
Published: (2024)

Parallel Diffusion Solver via Residual Dirichlet Policy Optimization
by: Wang, Ruoyu, et al.
Published: (2025)

Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning
by: Guo, Juncen, et al.
Published: (2025)

Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control
by: Song, Chenxi, et al.
Published: (2025)

FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing
by: Li, Guangzhao, et al.
Published: (2025)

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

Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration
by: Yang, Mengyu, et al.
Published: (2025)

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation
by: Zhao, Wangbo, et al.
Published: (2025)

Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning
by: Zhang, Tong, 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)

DyArtbank: Diverse Artistic Style Transfer via Pre-trained Stable Diffusion and Dynamic Style Prompt Artbank
by: Zhang, Zhanjie, et al.
Published: (2025)

Optimizing Few-Step Sampler for Diffusion Probabilistic Model
by: Huang, Jen-Yuan
Published: (2024)

CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization
by: Feng, Xiaoman, et al.
Published: (2026)

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

Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
by: Tong, Baoshun, et al.
Published: (2024)

You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts
by: Dou, Hongkun, et al.
Published: (2025)

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
by: Sui, Yang, et al.
Published: (2024)

Detail++: Training-Free Detail Enhancer for Text-to-Image Diffusion Models
by: Chen, Lifeng, et al.
Published: (2025)

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
by: Yang, Le, et al.
Published: (2024)

Variance-Aware Adaptive Weighting for Diffusion Model Training
by: Sun, Nanlong, et al.
Published: (2026)

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
by: Zhao, Chenxi, et al.
Published: (2026)

Dynamic Multi-level Weighted Alignment Network for Zero-shot Sketch-based Image Retrieval
by: Su, Hanwen, et al.
Published: (2025)

Weighted Reverse Convolution for Feature Upsampling
by: Li, Wentong, et al.
Published: (2026)

DyMorph-B2I: Dynamic and Morphology-Guided Binary-to-Instance Segmentation for Renal Pathology
by: Zhao, Leiyue, et al.
Published: (2025)

Enhancing Diffusion-Weighted Images (DWI) for Diffusion MRI: Is it Enough without Non-Diffusion-Weighted B=0 Reference?
by: Wu, Yinzhe, et al.
Published: (2025)

Prompt-aligned Gradient for Prompt Tuning
by: Zhu, Beier, et al.
Published: (2022)

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
by: Kim, Changhoon, et al.
Published: (2023)

Bimanual Grasp Synthesis for Dexterous Robot Hands
by: Shao, Yanming, et al.
Published: (2024)

WaDi: Weight Direction-aware Distillation for One-step Image Synthesis
by: Wang, Lei, et al.
Published: (2026)

Learning Few-Step Diffusion Models by Trajectory Distribution Matching
by: Luo, Yihong, et al.
Published: (2025)

Selective Vision-Language Subspace Projection for Few-shot CLIP
by: Zhu, Xingyu, et al.
Published: (2024)

BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
by: Zheng, Xingyu, et al.
Published: (2024)

DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
by: Issachar, Noam, et al.
Published: (2025)

Enhancing Small-Scale Dataset Expansion with Triplet-Connection-based Sample Re-Weighting
by: Xiang, Ting, et al.
Published: (2025)

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

Free Lunch for Stabilizing Rectified Flow Inversion
by: Wang, Chenru, et al.
Published: (2026)