1
CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs
用频谱有界骨干解决大模型持续微调中灾难性遗忘与跨任务改进的矛盾，模块化方案有新思路
arXiv:2606.00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learnin…