学习重要内容：基于相对误差驱动样本选择的优先概念学习
Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection
为视觉语言模型指令微调提供一种无需额外标注与辅助模型的数据选择机制：按技能维度追踪学习进度，优先采样「尚未掌握且难度适中」的样本，可直接用于构建更省数据、省算力的 VLM 微调流程。
原文依据 the model tracks its learning progress across skills and selects the most informative samples
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论指令微调是近期视觉语言模型（VLM）取得成功的关键，但其代价高昂——需要大规模数据集、高质量标注以及大量算力预算。我们提出基于相对误差驱动样本选择的优先概念学习（PROGRESS），一个在数据与算力上都高效的框架，使 VLM 能够根据训练过程中不断演变的需求，动态选择接下来要学习的内容。在每个阶段，模型追踪其在各项技能上的学习进展，并选择信息量最大的样本——即那些它尚未掌握、但在当前训练阶段又不过于困难的样本。该策略有效地控制了技能的习得过程以及技能的学习顺序。具体而言，我们从学习进展最高的技能中采样，优先选择提升最快的技能。与先前方法不同，PROGRESS 不需要预先的答案标注，仅在需要时查询答案，不依赖来自辅助 VLM 的额外监督，也不需要为数据选择进行算力开销大的梯度计算。在多个不同规模的指令微调数据集上的实验表明，PROGRESS 以少得多的数据和监督，持续优于最优基线。此外，我们展示了很强的跨架构泛化能力以及对更大模型的可迁移性，验证了 PROGRESS 是一种可扩展的高效学习方案。
英文原文摘要 1488 字符
Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale datasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept learninG via Relative Error-driven Sample Selection (PROGRESS), a data- and compute-efficient framework that enables VLMs to dynamically select what to learn next based on their evolving needs during training. At each stage, the model tracks its learning progress across skills and selects the most informative samples-those it has not already mastered and that are not too difficult to learn at the current stage of training. This strategy effectively controls skill acquisition and the order in which skills are learned. Specifically, we sample from skills showing the highest learning progress, prioritizing those with the most rapid improvement. Unlike prior methods, PROGRESS requires no upfront answer annotations, queries answers only on a need basis, avoids reliance on additional supervision from auxiliary VLMs, and does not require compute-heavy gradient computations for data selection. Experiments across multiple instruction-tuning datasets of varying scales demonstrate that PROGRESS consistently outperforms state-of-the-art baselines with much less data and supervision. Additionally, we show strong cross-architecture generalization and transferability to larger models, validating PROGRESS as a scalable solution for efficient learning.