Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization

ArXi:2604.08324v2 Announce Type: replace-cross Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures. Latent Space Optimization (LSO) methods use neural encoders to map symbolic expressions into continuous spaces, transforming the combinatorial search into continuous optimization. SNIP (Meidani, 2024), a contrastive pre-