Continual Learning as a Multiphase Moving-Boundary Problem
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. By mathematically freezing the learned interior, Stefan-CL cuts forgetting to near zero, matching memory-heavy baselines without storing raw data, forging a beautiful, physics-grounded path for AI.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
HDL and plaque regression in a multiphase model of early atherosclerosis
Atherosclerotic plaques are accumulations of cholesterol-engorged macrophages in the artery wall. Plaque growth is initiated and sustained by the deposition of low density lipoproteins (LDL) in the artery wall. High dens…
regressionDeep Multiphase Level Set for Scene Parsing
Recently, Fully Convolutional Network (FCN) seems to be the go-to architecture for image segmentation, including semantic scene parsing. However, it is difficult for a generic FCN to discriminate pixels around the object…
Image SegmentationScene ParsingSemantic SegmentationOnline Continual Learning For Interactive Instruction Following Agents
In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realist…
Continual LearningIncremental LearningInstruction FollowingLearning Pore-scale Multiphase Flow from 4D Velocimetry
Multiphase flow in porous media underpins subsurface energy and environmental technologies, including geological CO$_2$ storage and underground hydrogen storage, yet pore-scale dynamics in realistic three-dimensional mat…
GenPANIS: A Latent-Variable Generative Framework for Forward and Inverse PDE Problems in Multiphase Media
Inverse problems and inverse design in multiphase media, i.e., recovering or engineering microstructures to achieve target macroscopic responses, require operating on discrete-valued material fields, rendering the proble…