Towards a universal language of concepts: A survey
cs.AI, cs.PL, cs.SC
Submitted: 2026-09-03
Updated: 2026-09-03
Comments: Originally completed as an M.S. capstone project at UCLA in 2022
License: http://creativecommons.org/licenses/by/4.0/
The gist: Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich structural formats.
Abstract
Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich structural formats. In this paper, we propose that programs are a strong candidate for universal representation of concepts. We review computational models of concept learning that use programs as their concept representation and evaluate their contribution toward a universal representational language.
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection