Cover Image

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Yujie, Zhang, Shiwei, Yuan, Hangjie, Han, Yujin, Chen, Zhekai, Wang, Jiayu, Zou, Difan, Liu, Xihui, Zhang, Yingya, Liu, Yu, Shan, Hongming
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

TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
by: Chen, Zhekai, et al.
Published: (2025)

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
by: Qiu, Haonan, et al.
Published: (2024)

DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning
by: Wei, Yujie, et al.
Published: (2026)

Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
by: Han, Yujin, et al.
Published: (2025)

DreamRelation: Relation-Centric Video Customization
by: Wei, Yujie, et al.
Published: (2025)

GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference
by: Han, Yu, et al.
Published: (2025)

DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
by: Wei, Yujie, et al.
Published: (2024)

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
by: Chu, Ruihang, et al.
Published: (2025)

MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale
by: Falke, Tobias, et al.
Published: (2026)

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
by: Cai, Lingling, et al.
Published: (2024)

MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
by: Wei, Yujie, et al.
Published: (2026)

Grouter: Decoupling Routing from Representation for Accelerated MoE Training
by: Xu, Yuqi, et al.
Published: (2026)

Taming Consistency Distillation for Accelerated Human Image Animation
by: Wang, Xiang, et al.
Published: (2025)

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
by: Han, Yujin, et al.
Published: (2024)

Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs
by: Ye, Charles, et al.
Published: (2026)

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation
by: Zheng, Kening, et al.
Published: (2026)

Ada-K Routing: Boosting the Efficiency of MoE-based LLMs
by: Yue, Tongtian, et al.
Published: (2024)

DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models
by: Ma, Yifeng, et al.
Published: (2023)

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
by: Wang, Xiang, et al.
Published: (2025)

MoE-Sieve: Routing-Guided LoRA for Efficient MoE Fine-Tuning
by: Manzoni, Andrea
Published: (2026)

Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing
by: Min, Chengxi, et al.
Published: (2025)

Statistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving
by: Kou, Wei-Bin, et al.
Published: (2025)

BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
by: Wu, Juntong, et al.
Published: (2026)

Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations
by: Hu, Wentao, et al.
Published: (2026)

Capturing Conditional Dependence via Auto-regressive Diffusion Models
by: Huang, Xunpeng, et al.
Published: (2025)

MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration
by: Kong, Lingshun, et al.
Published: (2026)

Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction
by: Wei, Yujie, et al.
Published: (2026)

Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing
by: Huang, Hukai, et al.
Published: (2024)

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
by: Dong, Daize, et al.
Published: (2026)

ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning
by: Jin, Chao, et al.
Published: (2026)

AesRM: Improving Video Aesthetics with Expert-Level Feedback
by: Han, Yujin, et al.
Published: (2026)

HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction
by: Fang, Pengcheng, et al.
Published: (2025)

Harder Tasks Need More Experts: Dynamic Routing in MoE Models
by: Huang, Quzhe, et al.
Published: (2024)

Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts
by: Zhang, Chang-Bin, et al.
Published: (2024)

Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
by: Han, Yujin, et al.
Published: (2025)

MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
by: Chen, Zhekai, et al.
Published: (2026)

Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
by: Teng, Yao, et al.
Published: (2025)

D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving
by: Wang, Haodong, et al.
Published: (2025)

RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
by: Lv, Bo, et al.
Published: (2026)

Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures
by: Delibasoglu, Ibrahim
Published: (2026)