mlsanityData to 7 Oct 2026

MME: Mixture of Mesh Experts with Random Walk Transformer Gating

arXiv 2603.00828 ↗First posted 28 Feb 2026cs.CVcited by 0

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

In recent years, various methods have been proposed for mesh analysis, each offering distinct advantages and often excelling on different object classes. We present a novel Mixture of Experts (MoE) framework designed to harness the complementary strengths of these diverse approaches. We propose a new gate architecture that encourages each expert to specialise in the classes it excels in. Our design is guided by two key ideas: (1) random walks over the mesh surface effectively capture the regions that individual experts attend to, and (2) an attention mechanism that enables the gate to focus on the areas most informative for each expert's decision-making. To further enhance performance, we introduce a dynamic loss balancing scheme that adjusts a trade-off between diversity and similarity losses throughout the training, where diversity prompts expert specialization, and similarity enables knowledge sharing among the experts. Our framework achieves state-of-the-art results in mesh classification, retrieval, and semantic segmentation tasks. Our code is available at: https://github.com/amirbelder/MME-Mixture-of-Mesh-Experts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 54 of its 82 references that are in the map. First posted on arXiv 28 Feb 2026.

Builds on

54 of 82 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation16 Dec
  2. 2024Neural Experts: Mixture of Experts for Implicit Neural Representations29 Oct
  3. 2024Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering15 Jul
  4. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Experts19 May

Other references · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  6. 2022Mixture-of-Experts with Expert Choice Routingcited by 611
  7. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  8. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  9. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  10. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  11. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  12. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
38 more
  1. 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 235
  2. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  3. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  4. 2019Soft Actor-Critic for Discrete Action Settingscited by 161
  5. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  6. 2024Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Expertscited by 107
  7. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  8. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  9. 2023TextDeformer: Geometry Manipulation using Text Guidancecited by 94
  10. 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70
  11. 2018MeshCNN: A Network with an Edgecited by 69
  12. 2024MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Expertscited by 61
  13. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  14. 2021SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Expertscited by 48
  15. 2024MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priorscited by 48
  16. 2018Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networkscited by 44
  17. 2020Primal-Dual Mesh Convolutional Neural Networkscited by 44
  18. 2021Deep Reinforcement Learning in Computer Vision: A Comprehensive Surveycited by 42
  19. 2019An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learningcited by 38
  20. 2019Hyp-RL : Hyperparameter Optimization by Reinforcement Learningcited by 36
  21. 2020MeshWalker: Deep Mesh Understanding by Random Walkscited by 32
  22. 20223D Highlighter: Localizing Regions on 3D Shapes via Text Descriptionscited by 32
  23. 2021Survey on reinforcement learning for language processingcited by 31
  24. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  25. 2021Diversity Matters When Learning From Ensemblescited by 27
  26. 2022A Survey on Dynamic Neural Networks for Natural Language Processingcited by 24
  27. 2022NeurMiPs: Neural Mixture of Planar Experts for View Synthesiscited by 23
  28. 2018Surface Networks via General Coverscited by 22
  29. 2024MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesiscited by 22
  30. 2021Universal Spectral Adversarial Attacks for Deformable Shapescited by 14
  31. 2024Leveraging Mixture of Experts for Improved Speech Deepfake Detectioncited by 14
  32. 2024MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Expertscited by 12
  33. 2022What's the Situation with Intelligent Mesh Generation: A Survey and Perspectivescited by 9
  34. 2021AttWalk: Attentive Cross-Walks for Deep Mesh Analysiscited by 5
  35. 2023A Game of Bundle Adjustment -- Learning Efficient Convergencecited by 4
  36. 2022Random Walks for Adversarial Meshescited by 3
  37. 2023MeT: A Graph Transformer for Semantic Segmentation of 3D Meshescited by 3
  38. 2025InfoGNN: End-to-end deep learning on mesh via graph neural networkscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization
  2. 2024ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
  3. 2024Routers in Vision Mixture of Experts: An Empirical Study
  4. 2024Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
  5. 2026Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
  6. 2026Domain-Specialized Object Detection via Model-Level Mixtures of Experts
  7. 2022Residual Mixture of Experts
  8. 2024Mixture of Experts in Image Classification: What's the Sweet Spot?