3 papers
cs.CL2026
Language Models Represent and Transform Concepts with Shared Geometry
Zhimin Hu, Lanhao Niu, Sashank Varma
How concepts are represented in neural networks is a fundamental question in machine learning. The dominant view treats concept representations as stationary geometric objects. Yet…
cs.CL2026
Are More Tokens Rational? Inference-Time Scaling in Language Models as Adaptive Resource Rationality
Zhimin Hu, Riya Roshan, Sashank Varma
Human reasoning is shaped by resource rationality -- optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the re…
cs.CL2026
The Representational Geometry of Number
Zhimin Hu, Lanhao Niu, Sashank Varma
A central question in cognitive science is whether conceptual representations converge onto a shared manifold to support generalization, or diverge into orthogonal subspaces to min…