Cover Image

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Myunsoo, Ki, Donghyeon, Shim, Seong-Woong, Lee, Byung-Jun
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FALCON: False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment
by: Kim, Myunsoo, et al.
Published: (2025)

Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
by: Jo, Sangwoo, et al.
Published: (2026)

Prior-Guided Diffusion Planning for Offline Reinforcement Learning
by: Ki, Donghyeon, et al.
Published: (2025)

Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing
by: Jung, Yunji, et al.
Published: (2024)

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
by: Liu, Yaofang, et al.
Published: (2024)

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
by: Pan, Zizheng, et al.
Published: (2024)

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
by: Han, Jiaqi, et al.
Published: (2026)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
by: Sun, Haojun, et al.
Published: (2024)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
by: You, Haoran, et al.
Published: (2024)

The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks
by: Kim, Bum Jun, et al.
Published: (2024)

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
by: Kang, Donghwa, et al.
Published: (2025)

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
by: Zhu, Haowei, et al.
Published: (2026)

DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling
by: Lee, Han-Jin, et al.
Published: (2025)

Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models
by: Lee, Kyungryeol, et al.
Published: (2026)

Rethinking Timesteps Samplers and Prediction Types
by: Xie, Bin, et al.
Published: (2025)

In Search of a Data Transformation That Accelerates Neural Field Training
by: Seo, Junwon, et al.
Published: (2023)

Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability
by: Won, Soyoun, et al.
Published: (2023)

Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task
by: Kim, Yunho, et al.
Published: (2024)

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

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations
by: Kim, Myunsoo, et al.
Published: (2025)

Training-free Diffusion Model Alignment with Sampling Demons
by: Yeh, Po-Hung, et al.
Published: (2024)

Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
by: Lee, Byung Hyun, et al.
Published: (2025)

DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models
by: Ryu, Hyogon, et al.
Published: (2025)

CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
by: Kim, Junho, et al.
Published: (2024)

Denoising Task Difficulty-based Curriculum for Training Diffusion Models
by: Kim, Jin-Young, et al.
Published: (2024)

Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing
by: Kim, Joowon, et al.
Published: (2025)

Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models
by: Kim, Donghoon, et al.
Published: (2024)

Training Unbiased Diffusion Models From Biased Dataset
by: Kim, Yeongmin, et al.
Published: (2024)

Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
by: Huang, An, et al.
Published: (2026)

Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration
by: Wei, Yuanxin, et al.
Published: (2025)

STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformers
by: Kang, Donghwa, et al.
Published: (2025)

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
by: Guo, Bowei, et al.
Published: (2025)

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

Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion Sampling
by: Belardi, Christian, et al.
Published: (2026)

Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer
by: Lee, Hakjin, et al.
Published: (2023)

Activation-wise Propagation: A One-Timestep Strategy for Spiking Neural Networks
by: Song, Jian, et al.
Published: (2025)

Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
by: Dufour, Nicolas, et al.
Published: (2024)

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
by: Lee, Dongyeun, et al.
Published: (2025)

RBF-Solver: A Multistep Sampler for Diffusion Probabilistic Models via Radial Basis Functions
by: Park, Soochul, et al.
Published: (2026)

Ditto: Accelerating Diffusion Model via Temporal Value Similarity
by: Kim, Sungbin, et al.
Published: (2025)