3 papers
cs.LG2026
Same Compression Principle, Different Geometry: Rate-Distortion Signatures Dissociate Biological and Artificial Visual Systems
Leyla Roksan Caglar, Pedro A. M. Mediano, Baihan Lin
Efficient coding theory predicts that biological perceptual systems compress sensory input optimally under resource constraints, with the systematic structure of errors reflecting…
cs.CV2026
Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision
Leyla Roksan Caglar, Pedro A. M. Mediano, Baihan Lin
To humans, a robin seems more like a bird than a bird seems like a robin, but does this asymmetry also hold for machine vision? Humans and modern vision models can match each other…
cs.IR2026
PeReGrINE: Evaluating Personalized Review Fidelity with User Item Graph Context
Steven Au, Baihan Lin
We introduce PeReGrINE, a benchmark and evaluation framework for personalized review generation grounded in graph-structured user--item evidence. PeReGrINE restructures Amazon Revi…