114 citations · 114 across the 9 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Prashant C. Raju
Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behav…
cs.LG2026
The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models
Prashant C. Raju
Foundation models for biology and physics optimize predictive accuracy, but their internal representations systematically fail to preserve the continuous geometry of the systems th…
cs.LG2026
Geometric Stability: The Missing Axis of Representations
Prashant C. Raju
Representational similarity methods compare the geometries of neural representations, but they do not measure how consistently the geometry of a single representation is recovered…