Cover Image

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ren, Sucheng, Yu, Qihang, He, Ju, Yuille, Alan, Chen, Liang-Chieh
Format:	Preprint
Published:	2025
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

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
by: Ren, Sucheng, et al.
Published: (2025)

Frequency-Aware Flow Matching for High-Quality Image Generation
by: Ren, Sucheng, et al.
Published: (2026)

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
by: Ren, Sucheng, et al.
Published: (2024)

ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling
by: Liu, Qihao, et al.
Published: (2025)

ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Access
by: Yang, Timing, et al.
Published: (2025)

Dictionary-based Framework for Interpretable and Consistent Object Parsing
by: Zhang, Tiezheng, et al.
Published: (2025)

ViTamin: Designing Scalable Vision Models in the Vision-Language Era
by: Chen, Jieneng, et al.
Published: (2024)

A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
by: He, Ju, et al.
Published: (2023)

Large Language Models are Universal Reasoners for Visual Generation
by: Ren, Sucheng, et al.
Published: (2026)

SPFormer: Enhancing Vision Transformer with Superpixel Representation
by: Mei, Jieru, et al.
Published: (2024)

ViT-5: Vision Transformers for The Mid-2020s
by: Wang, Feng, et al.
Published: (2026)

FlowTok: Flowing Seamlessly Across Text and Image Tokens
by: He, Ju, et al.
Published: (2025)

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
by: Ren, Sucheng, et al.
Published: (2024)

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
by: Ren, Sucheng, et al.
Published: (2024)

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
by: Liu, Qihao, et al.
Published: (2024)

Rejuvenating image-GPT as Strong Visual Representation Learners
by: Ren, Sucheng, et al.
Published: (2023)

HResFormer: Hybrid Residual Transformer for Volumetric Medical Image Segmentation
by: Ren, Sucheng, et al.
Published: (2024)

Randomized Autoregressive Visual Generation
by: Yu, Qihang, et al.
Published: (2024)

Autoregressive Video Generation beyond Next Frames Prediction
by: Ren, Sucheng, et al.
Published: (2025)

Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
by: Paul, Soumava, et al.
Published: (2024)

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
by: Liu, Haoyu, et al.
Published: (2026)

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
by: Ren, Sucheng, et al.
Published: (2024)

Autoregressive Image Generation with Masked Bit Modeling
by: Yu, Qihang, et al.
Published: (2026)

Unifying Global-Local Representations in Salient Object Detection with Transformer
by: Ren, Sucheng, et al.
Published: (2021)

Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers
by: Sun, Wenhao, et al.
Published: (2026)

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

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
by: Kim, Dongwon, et al.
Published: (2025)

CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model
by: Yuan, Xiaoding, et al.
Published: (2024)

Mamba-R: Vision Mamba ALSO Needs Registers
by: Wang, Feng, et al.
Published: (2024)

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
by: Wang, Feng, et al.
Published: (2024)

AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation
by: Yin, Xuanhua, et al.
Published: (2026)

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
by: Kerssies, Tommie, et al.
Published: (2026)

Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
by: Zhou, Xin, et al.
Published: (2025)

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
by: Fang, Haipeng, et al.
Published: (2025)

ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers
by: Huang, Lianghua, et al.
Published: (2024)

COCONut: Modernizing COCO Segmentation
by: Deng, Xueqing, et al.
Published: (2024)

Computer Vision and Its Relationship to Cognitive Science: A perspective from Bayes Decision Theory
by: Yuille, Alan, et al.
Published: (2026)

Efficient Large Multi-modal Models via Visual Context Compression
by: Chen, Jieneng, et al.
Published: (2024)

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
by: Zeng, Fanhu, et al.
Published: (2025)

SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
by: Yan, Zhengan, et al.
Published: (2026)