3 papers
cs.LG2026
Geometry of Forgetting: Representation Flux in Continual Learning
Maksim A. Kazanskii
Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks. Existing methods pr…
cs.LG2026
How to Tame Grokking: Representation Geometry as a Control Signal
Maksim A Kazanskii
Grokking is a phenomenon in which neural networks initially memorize training data and only later exhibit strong generalization after prolonged optimization. Despite extensive rece…
astro-ph.EP2026
Space-Clock Elevator: Multi-Stage Orbital Transport via Rotating Tethers and Elliptical Nodes
Maksim A Kazanskii
Rotating space tethers have long been proposed as momentum-exchange devices capable of transporting payloads between orbital regimes without continuous propellant expenditure, offe…