揭秘大模型在持续预训练中如何习得、保留与遗忘概念，理解AI认知的关键研究。
arXiv:2601.03570v2 Announce Type: replace Abstract: Human beings primarily understand the world through concepts (e.g., dog), abstract mental represen…
用测试增强学习替代海量语料，为语言模型持续预训练省下高额计算成本，稳准快。
arXiv:2608.11788v1 Announce Type: cross Abstract: Continual pre-training (CPT) has been widely adopted as a method for domain adaptation in large lang…
用谱视角剖析大模型领域适应，Diffract方法为持续预训练提供新洞察。
arXiv:2608.10850v1 Announce Type: new Abstract: We study continual pre-training (CPT) as a mechanism for adapting general-purpose large language model…
少数据也能训出强安全大模型，这项研究用最少Token实现领域自适应预训练，大幅降低算力门槛。
arXiv:2507.02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure…
探究数据混合与模型架构对非洲语言持续预训练的影响，为低资源语言建模提供前沿实证与设计指南。
arXiv:2601.06395v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly multilingual, yet open models continue to underperfo…
LLM继续预训练中，超参数配置可预测的缩放规律，告别启发式搜索与高昂成本
arXiv:2606.05610v1 Announce Type: new Abstract: The efficacy of continued pre-training for Large Language Models (LLMs) hinges upon hyperparameter con…
冻结深层、训练浅层，可解释的层分配策略让持续预训练更高效
arXiv:2605.11416v2 Announce Type: replace Abstract: Selective layer-wise updates are essential for low-cost continued pre-training of Large Language M…
揭示大模型英语偏见真相，证明持续预训练成本优势不存在，语言专用投资或成必然。
arXiv:2605.15613v1 Announce Type: new Abstract: Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate…