Cover Image

FastUSP: A Multi-Level Collaborative Acceleration Framework for Distributed Diffusion Model Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Li, Guandong
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

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

Layout Control and Semantic Guidance with Attention Loss Backward for T2I Diffusion Model
by: Li, Guandong
Published: (2024)

LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference
by: Li, Guandong
Published: (2026)

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

EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models
by: Xie, Jiajian, et al.
Published: (2025)

Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-Commerce
by: Li, Guandong
Published: (2024)

E-Commerce Inpainting with Mask Guidance in Controlnet for Reducing Overcompletion
by: Li, Guandong
Published: (2024)

A Two-Stage Dual-Path Framework for Text Tampering Detection and Recognition
by: Li, Guandong, et al.
Published: (2024)

Edit Spillover as a Probe: Do Image Editing Models Implicitly Understand World Relations?
by: Li, Guandong, et al.
Published: (2026)

Accelerating Video Diffusion Models via Distribution Matching
by: Zhu, Yuanzhi, et al.
Published: (2024)

Intelligent Parsing: An Automated Parsing Framework for Extracting Design Semantics from E-commerce Creatives
by: Li, Guandong, et al.
Published: (2023)

FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference
by: Bajpai, Divya Jyoti, et al.
Published: (2026)

Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization
by: Li, Guandong, et al.
Published: (2026)

PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning
by: Li, Guandong, et al.
Published: (2026)

Edit Fidelity Field: Semantics-Aware Region Isolation for Training-Free Scene Text Editing
by: Li, Guandong, et al.
Published: (2026)

FlexID: Training-Free Flexible Identity Injection via Intent-Aware Modulation for Text-to-Image Generation
by: Li, Guandong, et al.
Published: (2026)

AdaEdit: Adaptive Temporal and Channel Modulation for Flow-Based Image Editing
by: Li, Guandong, et al.
Published: (2026)

AttnRouter: Per-Category Attention Routing for Training-Free Image Editing on MMDiT
by: Li, Guandong, et al.
Published: (2026)

EditIDv2: Editable ID Customization with Data-Lubricated ID Feature Integration for Text-to-Image Generation
by: Li, Guandong, et al.
Published: (2025)

MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture
by: Li, Guandong, et al.
Published: (2025)

Hyperspectral Image Classification via Transformer-based Spectral-Spatial Attention Decoupling and Adaptive Gating
by: Li, Guandong, et al.
Published: (2025)

Expert Kernel Generation Network Driven by Contextual Mapping for Hyperspectral Image Classification
by: Li, Guandong, et al.
Published: (2025)

DVI: Disentangling Semantic and Visual Identity for Training-Free Personalized Generation
by: Li, Guandong, et al.
Published: (2025)

Efficient Dynamic Attention 3D Convolution for Hyperspectral Image Classification
by: Li, Guandong, et al.
Published: (2025)

Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification
by: Li, Guandong, et al.
Published: (2025)

3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image Classification
by: Li, Guandong, et al.
Published: (2025)

Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification
by: Li, Guandong, et al.
Published: (2025)

EditID: Training-Free Editable ID Customization for Text-to-Image Generation
by: Li, Guandong, et al.
Published: (2025)

Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models
by: Yan, Chenqian, et al.
Published: (2024)

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
by: Li, Muyang, et al.
Published: (2024)

Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
by: Lee, Yunghee, et al.
Published: (2025)

FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
by: Selvaraju, Pratheba, et al.
Published: (2024)

A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
by: Moon, Taehong, et al.
Published: (2024)

A Wireless Collaborated Inference Acceleration Framework for Plant Disease Recognition
by: Zhu, Hele, et al.
Published: (2025)

Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference
by: Yu, Zihao, et al.
Published: (2023)

FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction
by: Lee, Donghyun, et al.
Published: (2025)

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
by: Pan, Jiayi, et al.
Published: (2025)

DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model
by: Zhang, Han, et al.
Published: (2025)

RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
by: Zhao, Wangbo, et al.
Published: (2025)

Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
by: Li, Senmao, et al.
Published: (2023)