mlsanityData to 7 Oct 2026

Vision mixture-of-experts

338 papers0 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: experts, image, moe, expert, mixture-of-experts

Key facts. Vision mixture-of-experts: 338 papers on arXiv since 2017 (data through 7 Oct 2026). 94 of its 338 mapped papers (28%) cite “Scaling Vision with Sparse Mixture of Experts” (2021, arXiv 2106.05974). 27 of its 338 mapped papers (8%) cite “From Sparse to Soft Mixtures of Experts” (2023, arXiv 2308.00951). 10 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

10 new papers, 17 Sep – 7 Oct; 0 this week.

  1. Earlier · 10
  2. RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection
  3. LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration
  4. Fine-Tuning VLM for Enhancing AI's Spatial Intelligence: Understanding 3D and 2D Rotations also fits: MoE in reinforcement learning and robotics
  5. DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference also fits: Multimodal MoE models
  6. Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
  7. From Routing Signals to Selective Review: Visual regrounding in MoE VLMs
  8. DIET: Deletion-response Expert Trimming for Video Diffusion Transformers also fits: Expert routing strategies
  9. SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Models also fits: MoE theory and gating functions
  10. EviDETR: Preserving Query-Relevant Temporal Evidence for Moment Retrieval and Highlight Detection
  11. C2FXNet: Coarse-to-Fine Scene Expert for Unified Object Detection across Adverse Weather

Foundations

Most cited by papers here

  1. Scaling Vision with Sparse Mixture of Experts2021cited by 94 here
  2. From Sparse to Soft Mixtures of Experts2023cited by 27 here
  3. Deep Mixture of Experts via Shallow Embedding2018cited by 21 here
  4. Hard Mixtures of Experts for Large Scale Weakly Supervised Vision2017cited by 13 here
  5. Go Wider Instead of Deeper2021cited by 11 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 133 here
  2. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 88 here
  3. 2021Scaling Vision with Sparse Mixture of Expertscited by 94 here
  4. 2022ST-MoE: Designing Stable and Transferable Sparse Expert Modelscited by 24 here
  5. 2022Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Expertscited by 24 here
  6. 2022Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpointscited by 12 here
  7. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 18 here
  8. 2024Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Expertscited by 13 here
16 more it builds on, not in this chain
  1. 2017Hard Mixtures of Experts for Large Scale Weakly Supervised Visioncited by 13 here
  2. 2018Deep Mixture of Experts via Shallow Embeddingcited by 21 here
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 118 here
  4. 2021DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learningcited by 14 here
  5. 2021Go Wider Instead of Deepercited by 11 here
  6. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 38 here
  7. 2022DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scalecited by 21 here
  8. 2022Mixture-of-Experts with Expert Choice Routingcited by 42 here
  9. 2022On the Representation Collapse of Sparse Mixture of Expertscited by 12 here
  10. 2022Tutel: Adaptive Mixture-of-Experts at Scalecited by 20 here
  11. 2023From Sparse to Soft Mixtures of Expertscited by 27 here
  12. 2023Robust Mixture-of-Expert Training for Convolutional Neural Networkscited by 11 here
  13. 2024Mixtral of Expertscited by 29 here
  14. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 35 here
  15. 2024OpenMoE: An Early Effort on Open Mixture-of-Experts Language Modelscited by 12 here
  16. 2024DeepSeek-V3 Technical Reportcited by 20 here

The 24 most cited of 349.

Browse

30 of 338, ranked 6–35

  1. 6Scaling Diffusion Transformers to 16 Billion Parameters202411
  2. 7Robust Mixture-of-Expert Training for Convolutional Neural Networks202311
  3. 8RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths202310
  4. 9Sparse Mixture-of-Experts are Domain Generalizable Learners202210
  5. 10On the Adversarial Robustness of Mixture of Experts202210
  6. 11Residual Mixture of Experts20229
  7. 12A Review of Sparse Expert Models in Deep Learning20228
  8. 13Scaling Vision-Language Models with Sparse Mixture of Experts20237
  9. 14Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability20227
  10. 15M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design20227
All 30
  1. 16Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations20207
  2. 17EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing20246
  3. 18Edge-Aware Autoencoder Design for Real-Time Mixture-of-Experts Image Compression20226
  4. 19LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes20255
  5. 20ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts20245
  6. 21Complexity Experts are Task-Discriminative Learners for Any Image Restoration20245
  7. 22DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets20235
  8. 233D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation20254
  9. 24Mixture of Nested Experts: Adaptive Processing of Visual Tokens20244
  10. 25Mixture of Experts in Image Classification: What's the Sweet Spot?20244
  11. 26UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity20244
  12. 27MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection20234
  13. 28Cross-token Modeling with Conditional Computation20214
  14. 29Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach20253
  15. 30Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts20253
  16. 31Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance20253
  17. 32Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense20243
  18. 33Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts20243
  19. 34MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration20243
  20. 35RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering20243