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.

翻译：指令调优已成为近期视觉语言模型（VLMs）成功的关键，但其成本高昂——需要大规模数据集、高质量标注及大量计算预算。本文提出基于相对误差驱动样本选择的优先概念学习框架（PROGRESS），这是一种数据与计算高效的方法，使VLMs能够在训练过程中根据动态需求选择后续学习内容。在每个训练阶段，模型追踪各项技能的学习进度，并选择最具信息量的样本——即当前尚未掌握且难度适中的样本。该策略能有效控制技能获取路径及学习顺序。具体而言，我们从学习进度最快的技能中采样，优先选择提升最显著的部分。与现有方法相比，PROGRESS无需预先准备答案标注，仅按需查询答案，避免依赖辅助VLMs的额外监督，且无需通过计算密集型梯度计算进行数据选择。在多个不同规模的指令调优数据集上的实验表明，PROGRESS在使用更少数据和监督的情况下，持续优于现有先进基线方法。此外，我们展示了该方法具备强大的跨架构泛化能力及向更大模型的可迁移性，验证了PROGRESS作为高效学习方案的可扩展性。