mlsanityData to 14 Oct 2026

CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering

arXiv 2604.16930 ↗First posted 18 Apr 2026cs.CV cs.AIcited by 1

On the map: Mixture-of-experts → Multimodal MoE models

Abstract (arXiv)

Visual Question Answering (VQA) requires models to identify the correct answer options based on both visual and textual evidence. Recent Mixture-of-Experts (MoE) methods improve option reasoning by grouping similar concepts or routing based on examples. However, unstable routing can lead to inconsistent expert selection in the same question type, while overly stable routing may reduce flexibility. To address this, we propose Concept-Guided Routing framework (CoGR-MoE), which incorporates semantics of the answer options to guide expert selection in the training phase. Next, option features are used to reweight the selected experts, producing discriminative representations for each candidate option. These option-level representations are further used for option comparison and optimized via contrastive learning. The experimental results indicate that CoGR-MoE delivers strong performance across multiple VQA tasks, demonstrating the effectiveness of our approach.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts. Builds on 31 of its 40 references that are in the map. First posted on arXiv 18 Apr 2026.

Builds on

31 of 40 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data16 Nov
  2. 2025I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts25 May
  3. 2025MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering8 Mar
  4. 2025CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering1 Mar
  5. 2025R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts27 Feb
  6. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Models29 Jan

Other references · 25

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  4. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  5. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  6. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  7. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 858
  8. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 710
  9. 2015Visual7W: Grounded Question Answering in Imagescited by 318
  10. 2021IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoningcited by 267
  11. 2025A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applicationscited by 91
  12. 2019GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answeringcited by 78
13 more
  1. 2024MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Modelscited by 46
  2. 2024Mixture of Experts Meets Prompt-Based Continual Learningcited by 43
  3. 2024MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Modelscited by 42
  4. 2025MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Designcited by 30
  5. 2025Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidancecited by 26
  6. 2024Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Modelscited by 14
  7. 2025Probing Semantic Routing in Large Mixture-of-Expert Modelscited by 14
  8. 2025Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMscited by 7
  9. 2025ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specializationcited by 7
  10. 2024MH-MoE: Multi-Head Mixture-of-Expertscited by 4
  11. 2025Massively Multimodal Foundation Models: A Framework for Capturing Interactions with Specialized Mixture-of-Expertscited by 4
  12. 2024Expert-Token Resonance MoE: Bidirectional Routing with Efficiency Affinity-Driven Active Selectioncited by 3
  13. 2025Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failurescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering
  2. 2022Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning
  3. 2022Guiding Visual Question Answering with Attention Priors
  4. 2025Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation
  5. 2024II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering
  6. 2024Find The Gap: Knowledge Base Reasoning For Visual Question Answering
  7. 2026AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
  8. 2024Rationale-guided Prompting for Knowledge-based Visual Question Answering