Cover Image

Taming Outlier Tokens in Diffusion Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Xiaoyu, Wang, Yifei, Fu, Tsu-Jui, Chen, Liang-Chieh, Gan, Zhe, Wei, Chen
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Taming Latent Diffusion Model for Neural Radiance Field Inpainting
by: Lin, Chieh Hubert, et al.
Published: (2024)

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality
by: Hu, Jerry Yao-Chieh, et al.
Published: (2024)

Taming Diffusion for Dataset Distillation with High Representativeness
by: Zhao, Lin, et al.
Published: (2025)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
by: You, Haoran, et al.
Published: (2024)

Masked Autoencoders Are Effective Tokenizers for Diffusion Models
by: Chen, Hao, et al.
Published: (2025)

Diffusion Autoencoders are Scalable Image Tokenizers
by: Chen, Yinbo, et al.
Published: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
by: Zou, Chang, et al.
Published: (2024)

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
by: Lee, Dongyeun, et al.
Published: (2025)

Neural Isometries: Taming Transformations for Equivariant ML
by: Mitchel, Thomas W., et al.
Published: (2024)

Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
by: Shrestha, Rajesh, et al.
Published: (2026)

RDPM: Solve Diffusion Probabilistic Models via Recurrent Token Prediction
by: Wu, Xiaoping, et al.
Published: (2024)

High-Resolution Image Synthesis via Next-Token Prediction
by: Chen, Dengsheng, et al.
Published: (2024)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
by: Zou, Chang, et al.
Published: (2024)

FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation
by: Bai, Yunwei, et al.
Published: (2024)

MeanFlow Transformers with Representation Autoencoders
by: Hu, Zheyuan, et al.
Published: (2025)

Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models
by: Wu, Xiaoyu, et al.
Published: (2024)

DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders
by: Hong, Susung, et al.
Published: (2025)

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers
by: Chen, Pengtao, et al.
Published: (2025)

High-Order Matching for One-Step Shortcut Diffusion Models
by: Chen, Bo, et al.
Published: (2025)

STIV: Scalable Text and Image Conditioned Video Generation
by: Lin, Zongyu, et al.
Published: (2024)

FrameBridge: Improving Image-to-Video Generation with Bridge Models
by: Wang, Yuji, et al.
Published: (2024)

Universal Approximation of Visual Autoregressive Transformers
by: Chen, Yifang, et al.
Published: (2025)

Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models
by: Burgess, James, et al.
Published: (2023)

Robustness Tokens: Towards Adversarial Robustness of Transformers
by: Pulfer, Brian, et al.
Published: (2025)

Scaling Diffusion Transformers Efficiently via $μ$P
by: Zheng, Chenyu, et al.
Published: (2025)

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
by: Chu, Huanpeng, et al.
Published: (2025)

Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
by: Jeong, Wooseong, et al.
Published: (2025)

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
by: Liu, Runtao, et al.
Published: (2024)

Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach
by: Yang, Yaoxin, et al.
Published: (2025)

H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
by: Li, Wenhao, et al.
Published: (2025)

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
by: Li, Wenhao, et al.
Published: (2023)

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
by: Qin, Yiming, et al.
Published: (2025)

Visual Autoregressive Transformers Must Use $Ω(n^2 d)$ Memory
by: Cao, Yang, et al.
Published: (2025)

ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detection
by: Chiang, Jui-Che, et al.
Published: (2024)

Non-Linear Outlier Synthesis for Out-of-Distribution Detection
by: Doorenbos, Lars, et al.
Published: (2024)

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
by: Chen, Hao, et al.
Published: (2024)

Towards Precise Scaling Laws for Video Diffusion Transformers
by: Yin, Yuanyang, et al.
Published: (2024)

CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network
by: Bai, Jia-Hau, et al.
Published: (2024)

Feature Purified Transformer With Cross-level Feature Guiding Decoder For Multi-class OOD and Anomaly Deteciton
by: Lin, Jerry Chun-Wei, et al.
Published: (2024)

TinyFusion: Diffusion Transformers Learned Shallow
by: Fang, Gongfan, et al.
Published: (2024)