VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization

arXiv:2503.04940 · cs.CL, cs.AI · Submitted 2025-03-06 · Read on arXiv

cs.CL, cs.AI

Submitted: 2025-03-06

Updated: 2026-10-13

Code: https://github.com/deepmind/dsprites-dataset

Terminology

• Quantization — 2× in this paper · explained in 12 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Vector Quantized Emergent Language — 1× in this paper

Sources

• Word-order biases in deep-agent emergent communication
• Compositionality and Generalization in Emergent Languages
• To Populate is To Regulate
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence
• EGG: a toolkit for research on Emergence of lanGuage in Games
• ShapeWorld - A new test methodology for multimodal language understanding
• Multi-Agent Cooperation and the Emergence of (Natural) Language
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• NWT: Towards natural audio-to-video generation with representation learning
• DINOv2: Learning Robust Visual Features without Supervision
• Compositional Languages Emerge in a Neural Iterated Learning Model
• Linking Emergent and Natural Languages via Corpus Transfer
• Vector-quantized Image Modeling with Improved VQGAN

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering