mlsanityData to 7 Oct 2026

How agents see things: On visual representations in an emergent language game

arXiv 1808.10696 ↗First posted 31 Aug 2018cs.CL cs.LGcited by 45

Not on the map. Why?

Abstract (arXiv)

There is growing interest in the language developed by agents interacting in emergent-communication settings. Earlier studies have focused on the agents' symbol usage, rather than on their representation of visual input. In this paper, we consider the referential games of Lazaridou et al. (2017) and investigate the representations the agents develop during their evolving interaction. We find that the agents establish successful communication by inducing visual representations that almost perfectly align with each other, but, surprisingly, do not capture the conceptual properties of the objects depicted in the input images. We conclude that, if we are interested in developing language-like communication systems, we must pay more attention to the visual semantics agents associate to the symbols they use.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 4; 2023: 13; 2024: 9; 2025: 2; 2026: 4.

45 papers.

Sort:

By area:

  1. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  2. 2021Emergent Communication of Generalizationscited by 41
  3. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  4. 2021Interpretable agent communication from scratch (with a generic visual processor emerging on the side)cited by 25
  5. 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
  6. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  7. 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
  8. 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
  9. 2021Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communicationcited by 12
  10. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  11. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  12. 2023Referential communication in heterogeneous communities of pre-trained visual deep networkscited by 10
33 more
  1. 2021Interaction-Grounded Learningcited by 9
  2. 2023Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Modelscited by 8
  3. 2024The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communicationcited by 7
  4. 2022Trust-based Consensus in Multi-Agent Reinforcement Learning Systemscited by 6
  5. 2021The emergence of visual semantics through communication gamescited by 5
  6. 2024Language Evolution with Deep Learningcited by 5
  7. 2024Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergencecited by 5
  8. 2025CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressurescited by 5
  9. 2023Learning Multi-Object Positional Relationships via Emergent Communicationcited by 4
  10. 2021Discrete representations in neural models of spoken languagecited by 3
  11. 2023ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formationcited by 3
  12. 2024What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language modelscited by 3
  13. 2021Sparse Communication via Mixed Distributionscited by 2
  14. 2022Recommendations for Systematic Research on Emergent Languagecited by 2
  15. 2022Mathematically Modeling the Lexicon Entropy of Emergent Languagecited by 2
  16. 2023Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minimacited by 2
  17. 2023Context-dependent communication under environmental constraintscited by 2
  18. 2023Emergent Communication with Attentioncited by 2
  19. 2024ELCC: the Emergent Language Corpus Collectioncited by 2
  20. 2024Semantics and Spatiality of Emergent Communicationcited by 2
  21. 2023Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Modelscited by 1
  22. 2023Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agentscited by 1
  23. 2024A Combinatorial Approach to Neural Emergent Communicationcited by 1
  24. 2024SimSiam Naming Game: A Unified Approach for Emergent Communication and Representation Learningcited by 1
  25. 2026CtD: Composition through Decomposition in Emergent Communicationcited by 1
  26. 2021Compositionality Through Language Transmission, using Artificial Neural Networkscited by 0
  27. 2021Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent?cited by 0
  28. 2023ETHER: Aligning Emergent Communication for Hindsight Experience Replaycited by 0
  29. 2023Grounded Language Acquisition From Object and Action Imagerycited by 0
  30. 2025VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantizationcited by 0
  31. 2026Automated Semantic Rules Detection (ASRD) for Emergent Communication Interpretationcited by 0
  32. 2026Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agentscited by 0
  33. 2026EmCom-Diffusion: Probing Visual Reflection in Emergent Languages via Image Generationcited by 0