Copertina

Sortblock: Similarity-Aware Feature Reuse for Diffusion Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Hanqi, Zhang, Xu, Guan, Xiaoliu, Jiang, Lielin, Wang, Guanzhong, Chen, Zeyu, Liu, Yi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
di: Guan, Xiaoliu, et al.
Pubblicazione: (2025)

Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models
di: Liu, Xiao, et al.
Pubblicazione: (2024)

Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models
di: Guan, Xiaoliu, et al.
Pubblicazione: (2025)

Enabling Versatile Controls for Video Diffusion Models
di: Zhang, Xu, et al.
Pubblicazione: (2025)

BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
di: Zhang, Hui, et al.
Pubblicazione: (2025)

Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models
di: Ma, Xuran, et al.
Pubblicazione: (2025)

Novel Diffusion Models for Multimodal 3D Hand Trajectory Prediction
di: Ma, Junyi, et al.
Pubblicazione: (2025)

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

SADER: Structure-Aware Diffusion Framework with DEterministic Resampling for Multi-Temporal Remote Sensing Cloud Removal
di: Zhang, Yifan, et al.
Pubblicazione: (2026)

Ensembling Diffusion Models via Adaptive Feature Aggregation
di: Wang, Cong, et al.
Pubblicazione: (2024)

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models
di: So, Junhyuk, et al.
Pubblicazione: (2023)

Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation
di: Zuo, Yi, et al.
Pubblicazione: (2025)

Landscape-Awareness for Geometric View Diffusion Model
di: Chen, Yan-Ting, et al.
Pubblicazione: (2026)

PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
di: Ni, Feng, et al.
Pubblicazione: (2025)

Cluster-Aware Similarity Diffusion for Instance Retrieval
di: Luo, Jifei, et al.
Pubblicazione: (2024)

Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
di: Lee, Hangyeol, et al.
Pubblicazione: (2026)

Plug-and-Play Context Feature Reuse for Efficient Masked Generation
di: Liu, Xuejie, et al.
Pubblicazione: (2025)

Achieving Fine-grained Cross-modal Understanding through Brain-inspired Hierarchical Representation Learning
di: You, Weihang, et al.
Pubblicazione: (2026)

Diffusion^2: Dual Diffusion Model with Uncertainty-Aware Adaptive Noise for Momentary Trajectory Prediction
di: Luo, Yuhao, et al.
Pubblicazione: (2025)

Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers
di: Chen, Guantao, et al.
Pubblicazione: (2026)

CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
di: Chen, Xuhai, et al.
Pubblicazione: (2023)

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
di: Hu, Teng, et al.
Pubblicazione: (2023)

Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models
di: Yu, Gaotong, et al.
Pubblicazione: (2024)

DETRs Beat YOLOs on Real-time Object Detection
di: Zhao, Yian, et al.
Pubblicazione: (2023)

Going Beyond Feature Similarity: Effective Dataset Distillation based on Class-Aware Conditional Mutual Information
di: Zhong, Xinhao, et al.
Pubblicazione: (2024)

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
di: Tan, Xudong, et al.
Pubblicazione: (2025)

PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
di: Xu, Zihang, et al.
Pubblicazione: (2026)

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
di: Ma, Kexin, et al.
Pubblicazione: (2026)

Timestep-Aware Correction for Quantized Diffusion Models
di: Yao, Yuzhe, et al.
Pubblicazione: (2024)

Real-time Traffic Accident Anticipation with Feature Reuse
di: Song, Inpyo, et al.
Pubblicazione: (2025)

Visual Explanation via Similar Feature Activation for Metric Learning
di: Liao, Yi, et al.
Pubblicazione: (2025)

TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models
di: Peng, Yuqi, et al.
Pubblicazione: (2025)

QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition
di: Wang, Chengpeng, et al.
Pubblicazione: (2024)

Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
di: Zhu, Jingyuan, et al.
Pubblicazione: (2026)

Towards Memorization-Free Diffusion Models
di: Chen, Chen, et al.
Pubblicazione: (2024)

Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
di: Zhang, Jiangning, et al.
Pubblicazione: (2024)

Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features
di: Gao, Zheng, et al.
Pubblicazione: (2026)

Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions
di: Han, Zeyu, et al.
Pubblicazione: (2023)

CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model
di: Yin, Pengwei, et al.
Pubblicazione: (2024)

Accelerating Rectified Flow Models via Trajectory-Aware Caching
di: Liu, Xiao, et al.
Pubblicazione: (2026)