Image de couverture de livre

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Park, Byeongjun, Go, Hyojun, Kim, Jin-Young, Woo, Sangmin, Ham, Seokil, Kim, Changick
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Diffusion Model Patching via Mixture-of-Prompts
par: Ham, Seokil, et autres
Publié: (2024)

Denoising Task Routing for Diffusion Models
par: Park, Byeongjun, et autres
Publié: (2023)

Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis
par: Park, Byeongjun, et autres
Publié: (2022)

SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
par: Go, Hyojun, et autres
Publié: (2024)

SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering
par: Park, Byeongjun, et autres
Publié: (2025)

Denoising Task Difficulty-based Curriculum for Training Diffusion Models
par: Kim, Jin-Young, et autres
Publié: (2024)

VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling
par: Go, Hyojun, et autres
Publié: (2025)

Generating Human Motion Videos using a Cascaded Text-to-Video Framework
par: Nam, Hyelin, et autres
Publié: (2025)

Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition
par: Lee, Sumin, et autres
Publié: (2024)

RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models
par: Woo, Sangmin, et autres
Publié: (2024)

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
par: Woo, Sangmin, et autres
Publié: (2024)

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
par: Chung, Hyungjin, et autres
Publié: (2025)

Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
par: Ham, Seokil, et autres
Publié: (2024)

Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments
par: Kwon, Soonwoo, et autres
Publié: (2025)

ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Function
par: Kim, Jin-Young, et autres
Publié: (2023)

Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition
par: Nugroho, Muhammad Adi, et autres
Publié: (2024)

TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Experts
par: Jeon, Jeimin, et autres
Publié: (2026)

One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images
par: Kwon, Byeongjun, et autres
Publié: (2025)

Towards Efficient Vision State Space Models via Token Merging
par: Park, Jinyoung, et autres
Publié: (2025)

Addressing Negative Transfer in Diffusion Models
par: Go, Hyojun, et autres
Publié: (2023)

BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation
par: Yoo, Youngju, et autres
Publié: (2025)

Station2Radar: query conditioned gaussian splatting for precipitation field
par: Kim, Doyi, et autres
Publié: (2026)

VideoMamba: Spatio-Temporal Selective State Space Model
par: Park, Jinyoung, et autres
Publié: (2024)

A-IDE : Agent-Integrated Denoising Experts
par: Cho, Uihyun, et autres
Publié: (2025)

ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding
par: Park, Byeongjun, et autres
Publié: (2025)

Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
par: Seo, Minseok, et autres
Publié: (2025)

Long-tailed Adversarial Training with Self-Distillation
par: Cho, Seungju, et autres
Publié: (2025)

Indirect Gradient Matching for Adversarial Robust Distillation
par: Lee, Hongsin, et autres
Publié: (2023)

Enhancing Robustness in Incremental Learning with Adversarial Training
par: Cho, Seungju, et autres
Publié: (2023)

Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking
par: Zhu, Yabin, et autres
Publié: (2026)

What and When to Look?: Temporal Span Proposal Network for Video Relation Detection
par: Woo, Sangmin, et autres
Publié: (2021)

Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models
par: Jeong, Jinho, et autres
Publié: (2025)

MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting
par: Jin, In-Hwan, et autres
Publié: (2025)

PECI-Net: Bolus segmentation from video fluoroscopic swallowing study images using preprocessing ensemble and cascaded inference
par: Park, Dougho, et autres
Publié: (2024)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
par: Kim, Hee-Seon, et autres
Publié: (2024)

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation
par: Zou, Xuechao, et autres
Publié: (2025)

Generalizable Slum Detection from Satellite Imagery with Mixture-of-Experts
par: Lee, Sumin, et autres
Publié: (2025)

Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
par: Park, Dogyun, et autres
Publié: (2025)

Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
par: Fang, Gongfan, et autres
Publié: (2024)

SCU-CGAN: Enhancing Fire Detection through Synthetic Fire Image Generation and Dataset Augmentation
par: Kim, Ju-Young, et autres
Publié: (2025)