arXiv Machine Learning June 16, 2026 By Maoliang Li, Haojing Chen, Jiayu Chen, Zihao Zheng, Xinhao Sun, Hailong Zou, Xiang Chen

MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers

Read the original on arXiv Machine Learning →

arXiv:2606. 15615v1 Announce Type: new Abstract: Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation across timesteps.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

1d ago

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching

arXiv:2412. 18911v3 Announce Type: replace-cross Abstract: Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs.

By Chang Zou, Shikang Zheng, Evelyn Zhang, Runlin Guo, Haohang Xu, Zhengyi Shi, Conghui He, Xuming Hu, Linfeng Zhang

llms diffusion

arXiv Machine Learning

Jul 31

FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference

arXiv:2607. 27842v1 Announce Type: cross Abstract: Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive.

By Hanshuai Cui, Zhiqing Tang, Zhi Yao, Qianli Ma, Fanshuai Meng, Weijia Jia

diffusion

arXiv Machine Learning

Aug 3

OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference

arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.

By Zhikang Xie, Xichen Ye, Yifan Wu, Haoshen Yu, Li chenan, Peizhu Gong, Weizhong Zhang, Cheng Jin

diffusion reinforcement-learning

arXiv Machine Learning

Jul 28

MMOE: Modernizing Diffusion Transformers with Efficient Expert Design

arXiv:2607. 24665v1 Announce Type: cross Abstract: Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows.

By Yanhao Jia, Jiepeng Wang, Haibin Huang, Chi Zhang, Erik Cambria, Xuelong Li

llms diffusion efficiency

arXiv Machine Learning

Aug 12

Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation

arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.

By Gongli Zhang, Zhulin Liu, C. L. Philip Chen

rag efficiency

arXiv AI

Jul 13

Sticky Routing: Training MoE Models for Memory-Efficient Inference

arXiv:2607. 08780v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing constant weight swapping between slow storage and fast memory on edge devices.

By Ali Kayyam

llms fine-tuning

Related stories

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching

FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference

OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference

MMOE: Modernizing Diffusion Transformers with Efficient Expert Design

Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation

Sticky Routing: Training MoE Models for Memory-Efficient Inference