AI RESEARCH
The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models
arXiv CS.LG
•
ArXi:2604.04155v1 Announce Type: new Foundation models for biology and physics optimize predictive accuracy, but their internal representations systematically fail to preserve the continuous geometry of the systems they model. We identify the root cause: the Geometric Alignment Tax, an intrinsic cost of forcing continuous manifolds through discrete categorical bottlenecks.