mlsanityData to 7 Oct 2026

Explainable Neural Computation via Stack Neural Module Networks

arXiv 1807.08556 ↗First posted 23 Jul 2018cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be interpretable to assist users in both development and prediction. Existing models designed to produce interpretable traces of their decision-making process typically require these traces to be supervised at training time. In this paper, we present a novel neural modular approach that performs compositional reasoning by automatically inducing a desired sub-task decomposition without relying on strong supervision. Our model allows linking different reasoning tasks though shared modules that handle common routines across tasks. Experiments show that the model is more interpretable to human evaluators compared to other state-of-the-art models: users can better understand the model's underlying reasoning procedure and predict when it will succeed or fail based on observing its intermediate outputs.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 19; 2022: 16; 2023: 10; 2024: 4; 2025: 5.

54 papers.

Sort:

By area:

  1. 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
  2. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  3. 2023Neurons in Large Language Models: Dead, N-gram, Positionalcited by 88
  4. 2021Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoningcited by 68
  5. 2021Video as Conditional Graph Hierarchy for Multi-Granular Question Answeringcited by 68
  6. 2021Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Languagecited by 55
  7. 2023Zero-Shot Video Question Answering with Procedural Programscited by 37
  8. 2021Greedy Gradient Ensemble for Robust Visual Question Answeringcited by 34
  9. 2022Vision-Language Intelligence: Tasks, Representation Learning, and Large Modelscited by 28
  10. 2024TANGO: Training-free Embodied AI Agents for Open-world Taskscited by 26
  11. 2021Learning by Planning: Language-Guided Global Image Editingcited by 25
  12. 2021Separating Skills and Concepts for Novel Visual Question Answeringcited by 24
38 more
  1. 2021Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsulescited by 22
  2. 2022FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relationscited by 20
  3. 2021ProTo: Program-Guided Transformer for Program-Guided Taskscited by 19
  4. 2024Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQAcited by 18
  5. 2021LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answeringcited by 17
  6. 2021Towards Language-guided Visual Recognition via Dynamic Convolutionscited by 17
  7. 20233D-Aware Visual Question Answering about Parts, Poses and Occlusionscited by 16
  8. 2021Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Imagescited by 14
  9. 2022Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Treescited by 14
  10. 2022VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challengescited by 14
  11. 2024On The Specialization of Neural Modulescited by 14
  12. 2022REX: Reasoning-aware and Grounded Explanationcited by 12
  13. 2021VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Taskscited by 11
  14. 2022SimVQA: Exploring Simulated Environments for Visual Question Answeringcited by 8
  15. 2024A Comprehensive Survey on Visual Question Answering Datasets and Algorithmscited by 8
  16. 2022Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answeringcited by 7
  17. 2023Prospective Role of Foundation Models in Advancing Autonomous Vehiclescited by 7
  18. 2022Multimodal Dialogue State Trackingcited by 6
  19. 2025A Theory of Initialisation's Impact on Specialisationcited by 6
  20. 2022Semantic-aware Modular Capsule Routing for Visual Question Answeringcited by 5
  21. 2021Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answeringcited by 4
  22. 2022Pruning for Feature-Preserving Circuits in CNNscited by 4
  23. 2023Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoningcited by 4
  24. 2025Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Modelscited by 4
  25. 2025A Neurosymbolic Agent System for Compositional Visual Reasoningcited by 4
  26. 2022From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answeringcited by 3
  27. 2022Visually Grounded VQA by Lattice-based Retrievalcited by 3
  28. 2022Learning Label Modular Prompts for Text Classification in the Wildcited by 3
  29. 2023Interactive Visual Task Learning for Robotscited by 3
  30. 2023Detection-based Intermediate Supervision for Visual Question Answeringcited by 3
  31. 2021How to Design Sample and Computationally Efficient VQA Modelscited by 2
  32. 2021NAAQA: A Neural Architecture for Acoustic Question Answeringcited by 2
  33. 2021Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networkscited by 2
  34. 2022Learning to Collocate Visual-Linguistic Neural Modules for Image Captioningcited by 2
  35. 2023A Survey on Interpretable Cross-modal Reasoningcited by 2
  36. 2023Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AIcited by 2
  37. 2022Visual Superordinate Abstraction for Robust Concept Learningcited by 1
  38. 2021Understanding in Artificial Intelligencecited by 0

50 most cited of 54 All 54 (JSON)