Cover Image

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Xibo, Fang, Jiarui, Li, Aoyu, Pan, Jinzhe
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
by: Fang, Jiarui, et al.
Published: (2024)

PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference
by: Fang, Jiarui, et al.
Published: (2024)

Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping
by: Zhou, Chao, et al.
Published: (2026)

Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
by: Fang, Gongfan, et al.
Published: (2024)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
by: Chen, Lei, et al.
Published: (2024)

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
by: Liu, Wenxuan, et al.
Published: (2024)

AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation
by: Zhang, Jian, et al.
Published: (2026)

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
by: Tian, Yuchuan, et al.
Published: (2024)

MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation
by: Krishnamurthy, Bharath, et al.
Published: (2026)

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
by: Zhang, Jiaji, et al.
Published: (2026)

DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing
by: Li, Qi, et al.
Published: (2025)

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
by: Deng, Juncan, et al.
Published: (2024)

ZigMa: A DiT-style Zigzag Mamba Diffusion Model
by: Hu, Vincent Tao, et al.
Published: (2024)

Ortho-Hydra: Orthogonalized Experts for DiT LoRA
by: Ji, Seunghyun
Published: (2026)

Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
by: Wang, Xiaoce, et al.
Published: (2026)

SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer
by: Zhu, Rui, et al.
Published: (2024)

Untwisting RoPE: Frequency Control for Shared Attention in DiTs
by: Mikaeili, Aryan, et al.
Published: (2026)

ViTs are Everywhere: A Comprehensive Study Showcasing Vision Transformers in Different Domain
by: Mia, Md Sohag, et al.
Published: (2023)

MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs
by: He, Xianglong, et al.
Published: (2025)

OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework
by: Zeng, Weixuan, et al.
Published: (2026)

DiT4Edit: Diffusion Transformer for Image Editing
by: Feng, Kunyu, et al.
Published: (2024)

LaVin-DiT: Large Vision Diffusion Transformer
by: Wang, Zhaoqing, et al.
Published: (2024)

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
by: Zhou, Zihan, et al.
Published: (2025)

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
by: Haridas, Akash, et al.
Published: (2026)

PTQ4DiT: Post-training Quantization for Diffusion Transformers
by: Wu, Junyi, et al.
Published: (2024)

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
by: Zhao, Lin, et al.
Published: (2026)

JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers
by: Byung-Ki, Kwon, et al.
Published: (2025)

LuxDiT: Lighting Estimation with Video Diffusion Transformer
by: Liang, Ruofan, et al.
Published: (2025)

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
by: Yang, Kaicheng, et al.
Published: (2025)

Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
by: Shah, Arya, et al.
Published: (2025)

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
by: Kodavanti, Sravanth, et al.
Published: (2026)

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
by: Lyu, Hengye, et al.
Published: (2026)

$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
by: Chen, Pengtao, et al.
Published: (2024)

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
by: Li, Zhimin, et al.
Published: (2024)

TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
by: Wang, Zhibo, et al.
Published: (2026)

Raformer: Redundancy-Aware Transformer for Video Wire Inpainting
by: Ji, Zhong, et al.
Published: (2024)

Octic Vision Transformers: Quicker ViTs Through Equivariance
by: Nordström, David, et al.
Published: (2025)

Human4DiT: 360-degree Human Video Generation with 4D Diffusion Transformer
by: Shao, Ruizhi, et al.
Published: (2024)

AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation
by: Choi, Jeongsoo, et al.
Published: (2025)

Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
by: Yang, Zhuoyi, et al.
Published: (2024)