Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization 事件

Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization arXiv:2606.00132v1 Announce Type: cross Abstract: While finetuning effectively adapts foundation models to specialized downstream tasks, it can degrade nontarget capabilities acquired during pretraining. Existing forgetting aware methods typically seek safer updates through specialized initialization or fixed constraints, but do not regulate the adaptation preservation trade-off during training. We propose Foundatio