Imagen de Portada

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	So, Junhyuk, Lee, Jungwon, Park, Eunhyeok
Formato:	Preprint
Publicado:	2023
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
por: So, Junhyuk, et al.
Publicado: (2025)

PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models
por: So, Junhyuk, et al.
Publicado: (2025)

Grouped Speculative Decoding for Autoregressive Image Generation
por: So, Junhyuk, et al.
Publicado: (2025)

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
por: Liu, Jiacheng, et al.
Publicado: (2025)

Selective Aggregation of Attention Maps Improves Diffusion-Based Visual Interpretation
por: Park, Jungwon, et al.
Publicado: (2026)

freePruner: A Training-free Approach for Large Multimodal Model Acceleration
por: Xu, Bingxin, et al.
Publicado: (2024)

Fast Sampling Through The Reuse Of Attention Maps In Diffusion Models
por: Hunter, Rosco, et al.
Publicado: (2023)

VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension
por: Park, Hyejin, et al.
Publicado: (2026)

Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
por: Park, Jungwon, et al.
Publicado: (2024)

Task-Specific Preconditioner for Cross-Domain Few-Shot Learning
por: Kang, Suhyun, et al.
Publicado: (2024)

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
por: Kim, Mingyeong, et al.
Publicado: (2026)

Upsample Guidance: Scale Up Diffusion Models without Training
por: Hwang, Juno, et al.
Publicado: (2024)

Retro: Reusing teacher projection head for efficient embedding distillation on Lightweight Models via Self-supervised Learning
por: Nguyen, Khanh-Binh, et al.
Publicado: (2024)

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
por: Chu, Huanpeng, et al.
Publicado: (2025)

Self-Supervised Score-Based Despeckling for SAR Imagery via Log-Domain Transformation
por: Heo, Junhyuk
Publicado: (2026)

Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
por: Lee, Dohun, et al.
Publicado: (2025)

Inference-Time Diffusion Model Distillation
por: Park, Geon Yeong, et al.
Publicado: (2024)

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

Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models
por: Fan, Jiawei, et al.
Publicado: (2026)

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
por: He, Wenkun, et al.
Publicado: (2025)

Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas
por: Silveria, Austin, et al.
Publicado: (2025)

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
por: Zou, Chang, et al.
Publicado: (2026)

Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis
por: Wang, Zixuan, et al.
Publicado: (2025)

ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology
por: Jung, Hyun Do, et al.
Publicado: (2026)

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
por: Lee, Sangin, et al.
Publicado: (2026)

MagicFace: Training-free Universal-Style Human Image Customized Synthesis
por: Wang, Yibin, et al.
Publicado: (2024)

Any6D: Model-free 6D Pose Estimation of Novel Objects
por: Lee, Taeyeop, et al.
Publicado: (2025)

CacheQuant: Comprehensively Accelerated Diffusion Models
por: Liu, Xuewen, et al.
Publicado: (2025)

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation
por: Lee, ByeongCheol, et al.
Publicado: (2026)

See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
por: Park, Jaehyun, et al.
Publicado: (2026)

360 in the Wild: Dataset for Depth Prediction and View Synthesis
por: Park, Kibaek, et al.
Publicado: (2024)

MANGO: A Global Single-Date Paired Dataset for Mangrove Segmentation
por: Heo, Junhyuk, et al.
Publicado: (2026)

Unmasking Bias in Diffusion Model Training
por: Yu, Hu, et al.
Publicado: (2023)

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
por: Du, Yilun, et al.
Publicado: (2023)

CF3: Compact and Fast 3D Feature Fields
por: Lee, Hyunjoon, et al.
Publicado: (2025)

HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention
por: Zheng, Xuzhe, et al.
Publicado: (2026)

Accelerating Diffusion Models with One-to-Many Knowledge Distillation
por: Zhang, Linfeng, et al.
Publicado: (2024)

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
por: Kwon, Taesung, et al.
Publicado: (2026)

Accelerating Diffusion Transformers with Token-wise Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

AVAM: Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering
por: Zeng, Kang, et al.
Publicado: (2025)