SOURCE-LINKED INTELLIGENCE

Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter-efficient fine-tuning methods, they adopted an overly restrictive Subspace Orthogonality condition. In this paper, we introduce a purely post-hoc and tuning-agnostic weight rectification framework that achieves Parameter Space Orthogonality, which is the necessary and sufficient condition for preserving historical performance to the first order. By projecting parameter updates into the JAcobian NUll Space (JANUS), our method signific

Read original source ↗ Open in workspace

recordType

paper

region

Global