AI RESEARCH
Continual Learning as a Multiphase Moving-Boundary Problem
arXiv CS.LG
•
ArXi:2606.01863v1 Announce Type: new Continual learning struggles to balance retaining past knowledge with absorbing new tasks. Stefan-CL elegantly resolves this stability-plasticity dilemma through the physics of melting. It frames consolidated knowledge as a protected "solid" and unused capacity as an adaptable "liquid." As the network learns, this boundary expands, governed by a "latent heat" tuning dial.