Image de couverture de livre

LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Li, Guandong
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
par: Gao, Huanlin, et autres
Publié: (2026)

LP-DETR: Layer-wise Progressive Relations for Object Detection
par: Kang, Zhengjian, et autres
Publié: (2025)

Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers
par: Li, Guandong
Publié: (2026)

DeepIcon: A Hierarchical Network for Layer-wise Icon Vectorization
par: Bing, Qi, et autres
Publié: (2024)

SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
par: Qian, Chen, et autres
Publié: (2026)

Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks
par: Alcover-Couso, Roberto, et autres
Publié: (2024)

Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning
par: Tang, Hao, et autres
Publié: (2024)

Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion
par: Li, Jiawei, et autres
Publié: (2024)

Intelligent Parsing: An Automated Parsing Framework for Extracting Design Semantics from E-commerce Creatives
par: Li, Guandong, et autres
Publié: (2023)

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference
par: Pei, Xiaohuan, et autres
Publié: (2024)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
par: Tang, Zicong, et autres
Publié: (2025)

AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference
par: Huang, Kai, et autres
Publié: (2025)

DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models
par: Polowczyk, Alicja, et autres
Publié: (2026)

VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
par: Jiang, Pengfei, et autres
Publié: (2025)

LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging
par: Wang, Xinyu, et autres
Publié: (2026)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
par: Zou, Chang, et autres
Publié: (2024)

Terminal Velocity Matching
par: Zhou, Linqi, et autres
Publié: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
par: Zou, Chang, et autres
Publié: (2024)

Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models
par: Li, Changlin, et autres
Publié: (2025)

Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning
par: Devoto, Alessio, et autres
Publié: (2024)

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
par: Zhu, Xuanyu, et autres
Publié: (2026)

DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding
par: Choraria, Moulik, et autres
Publié: (2025)

Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers
par: Li, Guandong
Publié: (2026)

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models
par: Meng, Yu, et autres
Publié: (2025)

InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching
par: Wang, Dayu, et autres
Publié: (2026)

Exploiting Style Latent Flows for Generalizing Deepfake Video Detection
par: Choi, Jongwook, et autres
Publié: (2024)

Towards Deconfounded Image-Text Matching with Causal Inference
par: Li, Wenhui, et autres
Publié: (2024)

Rethinking Cross-Layer Information Routing in Diffusion Transformers
par: Xu, Chao, et autres
Publié: (2026)

CAFlow: Adaptive-Depth Single-Step Flow Matching for Efficient Histopathology Super-Resolution
par: Yoshai, Elad, et autres
Publié: (2026)

Flow-GRPO: Training Flow Matching Models via Online RL
par: Liu, Jie, et autres
Publié: (2025)

Flow-OPD: On-Policy Distillation for Flow Matching Models
par: Fang, Zhen, et autres
Publié: (2026)

Motion-Aware Caching for Efficient Autoregressive Video Generation
par: Xu, Jing, et autres
Publié: (2026)

EUGens: Efficient, Unified, and General Dense Layers
par: Kim, Sang Min, et autres
Publié: (2024)

Efficient Flow Matching using Latent Variables
par: Samaddar, Anirban, et autres
Publié: (2025)

Restrictive Hierarchical Semantic Segmentation for Stratified Tooth Layer Detection
par: Banks, Ryan, et autres
Publié: (2025)

ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
par: Kim, Suyoung, et autres
Publié: (2026)

Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals
par: Li, Hanze, et autres
Publié: (2025)

Channel-wise Vector Quantization
par: Song, Wei, et autres
Publié: (2026)

TrajFlow: Multi-modal Motion Prediction via Flow Matching
par: Yan, Qi, et autres
Publié: (2025)

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding
par: Cheng, Shuang, et autres
Publié: (2025)