Cover Image

When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Libo, Harn, Po-wei, He, Peixiong, Qin, Xiao
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression
by: Sun, Libo, et al.
Published: (2026)

Minimal-Intervention KV Retention via Set-Conditioned Diversity
by: Sun, Libo, et al.
Published: (2026)

Nucleus-Image: Sparse MoE for Image Generation
by: Akiti, Chandan, et al.
Published: (2026)

Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE
by: Bao, Wei, et al.
Published: (2026)

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
by: Wei, Yujie, et al.
Published: (2025)

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

Teacher-Guided Routing for Sparse Vision Mixture-of-Experts
by: Kada, Masahiro, et al.
Published: (2026)

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
by: Zheng, Youwei, et al.
Published: (2025)

VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models
by: Qin, Guangshuo, et al.
Published: (2026)

MoCHA: Advanced Vision-Language Reasoning with MoE Connector and Hierarchical Group Attention
by: Pang, Yuqi, et al.
Published: (2025)

When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains
by: Jeddi, Ahmadreza, et al.
Published: (2026)

BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing
by: Ma, Yingjie, et al.
Published: (2024)

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

Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Models
by: Wang, Peiran, et al.
Published: (2025)

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
by: Lin, Bin, et al.
Published: (2024)

Sparse Spectral LoRA: Routed Experts for Medical VLMs
by: Manzari, Omid Nejati, et al.
Published: (2026)

GNN-MoE: Context-Aware Patch Routing using GNNs for Parameter-Efficient Domain Generalization
by: Soliman, Mahmoud, et al.
Published: (2025)

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

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

When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT
by: Cheung, Matt Y., et al.
Published: (2025)

MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
by: Ko, Dohwan, et al.
Published: (2026)

SocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuning
by: Kawabata, Tomohito, et al.
Published: (2025)

GazeFormer-MoE: Context-Aware Gaze Estimation via CLIP and MoE Transformer
by: Zhao, Xinyuan, et al.
Published: (2026)

CBDES MoE: Hierarchically Decoupled Mixture-of-Experts for Functional Modules in Autonomous Driving
by: Xiang, Qi, et al.
Published: (2025)

AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro
by: Fang, Pengcheng, et al.
Published: (2026)

SparseLaneSTP: Leveraging Spatio-Temporal Priors with Sparse Transformers for 3D Lane Detection
by: Pittner, Maximilian, et al.
Published: (2026)

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
by: Chen, Feng, et al.
Published: (2025)

Vision Transformer with Sparse Scan Prior
by: Zhang, Yuguang, et al.
Published: (2024)

SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction
by: Tang, Pin, et al.
Published: (2024)

LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
by: Shu, Fangxun, et al.
Published: (2024)

MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting
by: Jin, In-Hwan, et al.
Published: (2025)

MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
by: Zhu, Xingkui, et al.
Published: (2024)

When Does Pruning Benefit Vision Representations?
by: Cassano, Enrico, et al.
Published: (2025)

Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
by: Shi, Yangming, et al.
Published: (2026)

MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning
by: Zhang, Qizhe, et al.
Published: (2023)

Leveraging Sparse Annotations for Leukemia Diagnosis on the Large Leukemia Dataset
by: Rehman, Abdul, et al.
Published: (2025)

OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning
by: Geng, Xinyu, et al.
Published: (2024)

Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
by: Qin, Chuan, et al.
Published: (2026)

QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
by: Feng, Weilun, et al.
Published: (2025)

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
by: Jiang, Songtao, et al.
Published: (2024)