Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Emergent Graphical Conventions in a Visual Communication Game
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| disable early decision (max-step) (ablation) | complete setting · unseen instance | communication accuracy (%): 70.37 -> 67.93 | Hurt |
| disable early decision (max-step) (ablation) | complete setting · seen | communication accuracy (%): 98.07 -> 86.27 | Hurt |
| freeze sender (sender-fixed) (ablation) | complete setting · seen | communication accuracy (%): 98.07 -> 99.60 | No clear effect |
| freeze sender (sender-fixed) (ablation) | complete setting · unseen class | communication accuracy (%): 39.40 -> 45.40 | No clear effect |
| use single sketching step (one-step) (ablation) | complete setting · seen | communication accuracy (%): 98.07 -> 22.87 | Hurt |
| disable early decision (max-step) (ablation) | complete setting · seen | average communication steps: 1.03 -> 7.00 | Hurt |
| freeze sender (sender-fixed) (ablation) | complete setting · seen | average communication steps: 1.03 -> 2.41 | Hurt |
| disable early decision (max-step) (ablation) | complete setting · Symbolicity (VGG sketch classification) | classification accuracy | Hurt |
| freeze sender (sender-fixed) (ablation) | complete setting · Symbolicity (VGG sketch classification) | classification accuracy | Hurt |
| replace retrieved sketches with evolved sketches (complete) (ablation) | VGG classifier · Symbolicity (VGG sketch classification) | classification accuracy | Helped |
| evolve sketches (complete) versus unevolved retrieve (ablation) | semanticity · Semanticity | correlation: 0.55 -> 0.43 | Hurt |
| replace REINFORCE with proposed surrogate learning (ablation) | complete setting · validation accuracy | convergence speed | Helped |
Closest papers by meaning
- Sketchtopia: A Dataset and Foundational Agents for Benchmarking Asynchronous Multimodal Communication with Iconic Feedback (CVPR 2025 · similarity 0.88)
- Bridging semantics and pragmatics in information-theoretic emergent communication (NeurIPS 2024 · similarity 0.88)
- Semantics and Spatiality of Emergent Communication (NeurIPS 2024 · similarity 0.87)
- Learning Multi-Object Positional Relationships via Emergent Communication (AAAI 2024 · similarity 0.86)
- Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments (ICLR 2024 · similarity 0.86)
- Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.