SNIP++: Fine-Grained Symbolic-Numerical Alignment for Symbolic Regression
Mathematical expressions and the numerical behavior they produce are two views of the same underlying function, and connecting them is central to scientific discovery. Symbolic Regression (SR) relies on this connection directly: it searches for an expression that reproduces a given behavior. Recent multi-modal models l...
Benjamin Léger, Shubham Gupta, S. Mammeri et al.
· 0 citations