3 papers
cs.LG2026
Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
Jesseba Fernando, Grigori Guitchounts
Large language models are remarkably capable, yet how computation propagates through their layers remains poorly understood. A growing line of work treats depth as discrete time an…
cs.LG2025
Bound by semanticity: universal laws governing the generalization-identification tradeoff
Marco Nurisso, Jesseba Fernando, Raj Deshpande +9
Intelligent systems must deploy internal representations that are simultaneously structured -- to support broad generalization -- and selective -- to preserve input identity. We ex…
cs.AI2025
Transformer Dynamics: A neuroscientific approach to interpretability of large language models
Jesseba Fernando, Grigori Guitchounts
As artificial intelligence models have exploded in scale and capability, understanding of their internal mechanisms remains a critical challenge. Inspired by the success of dynamic…