mlsanityData to 7 Oct 2026

Learning to Compose Neural Networks for Question Answering

arXiv 1601.01705 ↗First posted 7 Jan 2016cs.CL cs.CV cs.NEcited by 85

Not on the map. Why?

Abstract (arXiv)

We describe a question answering model that applies to both images and structured knowledge bases. The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. Parameters for these modules are learned jointly with network-assembly parameters via reinforcement learning, with only (world, question, answer) triples as supervision. Our approach, which we term a dynamic neural model network, achieves state-of-the-art results on benchmark datasets in both visual and structured domains.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jan 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 15; 2023: 29; 2024: 13; 2025: 4; 2026: 2.

85 papers.

Sort:

By area:

  1. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  2. 2022Lifting the Curse of Multilinguality by Pre-training Modular Transformerscited by 145
  3. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  4. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  5. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  6. 2023NeurASP: Embracing Neural Networks into Answer Set Programmingcited by 92
  7. 2023Modular Deep Learningcited by 82
  8. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 74
  9. 2021Continual Learning via Local Module Compositioncited by 61
  10. 2023NS3D: Neuro-Symbolic Grounding of 3D Objects and Relationscited by 57
  11. 2021Complex Knowledge Base Question Answering: A Surveycited by 52
  12. 2023Modular Visual Question Answering via Code Generationcited by 47
38 more
  1. 2022Neural Approaches to Conversational Information Retrievalcited by 41
  2. 2022On the Explainability of Natural Language Processing Deep Modelscited by 37
  3. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  4. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  5. 2023What's Left? Concept Grounding with Logic-Enhanced Foundation Modelscited by 33
  6. 2022Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?cited by 31
  7. 2024On the Challenges and Opportunities in Generative AIcited by 31
  8. 2023Dissociating language and thought in large language modelscited by 27
  9. 2023The Relational Bottleneck as an Inductive Bias for Efficient Abstractioncited by 26
  10. 2023From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunitiescited by 24
  11. 2021Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiabilitycited by 18
  12. 2023GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEscited by 18
  13. 2021Distribution Matching for Rationalizationcited by 14
  14. 2021Cognitive Visual Commonsense Reasoning Using Dynamic Working Memorycited by 14
  15. 2022VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challengescited by 14
  16. 2023Neurosymbolic Grounding for Compositional World Modelscited by 14
  17. 2023API-Assisted Code Generation for Question Answering on Varied Table Structurescited by 14
  18. 2023Examining Modularity in Multilingual LMs via Language-Specialized Subnetworkscited by 13
  19. 2021Hopper: Multi-hop Transformer for Spatiotemporal Reasoningcited by 12
  20. 2021Interpretable Visual Understanding with Cognitive Attention Networkcited by 12
  21. 2021VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Taskscited by 11
  22. 2021Truth-Conditional Captioning of Time Series Datacited by 11
  23. 2022Grammar-Based Grounded Lexicon Learningcited by 10
  24. 2022Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Modelscited by 10
  25. 2023MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Modelcited by 10
  26. 2021Table-based Fact Verification with Salience-aware Learningcited by 9
  27. 2023NEUCORE: Neural Concept Reasoning for Composed Image Retrievalcited by 8
  28. 2024Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learnerscited by 8
  29. 2024A Comprehensive Survey on Visual Question Answering Datasets and Algorithmscited by 8
  30. 20233VL: Using Trees to Improve Vision-Language Models' Interpretabilitycited by 7
  31. 2024From Frege to chatGPT: Compositionality in language, cognition, and deep neural networkscited by 7
  32. 2021How to find a good image-text embedding for remote sensing visual question answering?cited by 6
  33. 2022Breakpoint Transformers for Modeling and Tracking Intermediate Beliefscited by 6
  34. 2023Conceptual Framework for Autonomous Cognitive Entitiescited by 6
  35. 2023Recursive Visual Programmingcited by 6
  36. 2021KANDINSKYPatterns -- An experimental exploration environment for Pattern Analysis and Machine Intelligencecited by 5
  37. 2021Designing an Automatic Agent for Repeated Language based Persuasion Gamescited by 5
  38. 2021Topos and Stacks of Deep Neural Networkscited by 5

50 most cited of 85 All 85 (JSON)