Cover Image

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Krause, Felix, Phan, Timy, Gui, Ming, Baumann, Stefan Andreas, Hu, Vincent Tao, Ommer, Björn
Format:	Preprint
Published:	2025
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

Guiding Token-Sparse Diffusion Models
by: Krause, Felix, et al.
Published: (2026)

What If : Understanding Motion Through Sparse Interactions
by: Baumann, Stefan Andreas, et al.
Published: (2025)

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
by: Gui, Ming, et al.
Published: (2025)

Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
by: Schusterbauer, Johannes, et al.
Published: (2026)

Boosting Latent Diffusion with Flow Matching
by: Schusterbauer, Johannes, et al.
Published: (2023)

DisMo: Disentangled Motion Representations for Open-World Motion Transfer
by: Ressler-Antal, Thomas, et al.
Published: (2025)

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

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
by: Baumann, Stefan Andreas, et al.
Published: (2024)

MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
by: Fuest, Michael, et al.
Published: (2025)

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
by: Schusterbauer, Johannes, et al.
Published: (2025)

[MASK] is All You Need
by: Hu, Vincent Tao, et al.
Published: (2024)

Diffusion Models and Representation Learning: A Survey
by: Fuest, Michael, et al.
Published: (2024)

CleanDIFT: Diffusion Features without Noise
by: Stracke, Nick, et al.
Published: (2024)

Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
by: Schusterbauer, Johannes, et al.
Published: (2026)

Distillation of Diffusion Features for Semantic Correspondence
by: Fundel, Frank, et al.
Published: (2024)

DepthFM: Fast Monocular Depth Estimation with Flow Matching
by: Gui, Ming, et al.
Published: (2024)

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models
by: Stracke, Nick, et al.
Published: (2024)

Scaling Image Tokenizers with Grouped Spherical Quantization
by: Wang, Jiangtao, et al.
Published: (2024)

Learning Long-term Motion Embeddings for Efficient Kinematics Generation
by: Stracke, Nick, et al.
Published: (2026)

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
by: Prestel, Ulrich, et al.
Published: (2026)

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
by: Ma, Pingchuan, et al.
Published: (2025)

Does VLM Classification Benefit from LLM Description Semantics?
by: Ma, Pingchuan, et al.
Published: (2024)

ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment
by: Aghdam, Amir, et al.
Published: (2025)

Envisioning the Future, One Step at a Time
by: Baumann, Stefan Andreas, et al.
Published: (2026)

Unsupervised View-Invariant Human Posture Representation
by: Sardari, Faegheh, et al.
Published: (2021)

Training Class-Imbalanced Diffusion Model Via Overlap Optimization
by: Yan, Divin, et al.
Published: (2024)

Memory Efficient Matting with Adaptive Token Routing
by: Lin, Yiheng, et al.
Published: (2024)

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation
by: Davtyan, Aram, et al.
Published: (2024)

Quantum Denoising Diffusion Models
by: Kölle, Michael, et al.
Published: (2024)

Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
by: Wang, Jiajun, et al.
Published: (2024)

VORTA: Efficient Video Diffusion via Routing Sparse Attention
by: Sun, Wenhao, et al.
Published: (2025)

SuperADD: Training-free Class-agnostic Anomaly Segmentation -- CVPR 2026 VAND 4.0 Workshop Challenge Industrial Track
by: Roming, Lukas, et al.
Published: (2026)

Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics
by: Li, Yitong, et al.
Published: (2025)

Training-Free Efficient Video Generation via Dynamic Token Carving
by: Zhang, Yuechen, et al.
Published: (2025)

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing
by: Hu, Taihang, et al.
Published: (2025)

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis
by: Yeganeh, Yousef, et al.
Published: (2024)

Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
by: Ren, Bin, et al.
Published: (2025)

TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference
by: Hu, Junshan, et al.
Published: (2025)

SparseDiT: Token Sparsification for Efficient Diffusion Transformer
by: Chang, Shuning, et al.
Published: (2024)

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
by: Liu, Haozhe, et al.
Published: (2025)