Model predictive task sampling for efficient and robust adaptation

作者：Qi Wang, Zehao Xiao, Yixiu Mao, Yun Qu, Jiayi Shen, Yiqin Lv, Xiangyang Ji · 发表于：Nature Communications · 年份：2026 · DOI：10.1038/s41467-026-74004-0 · 被引用次数：4 · 研究领域：Advanced Vision and Imaging、Domain Adaptation and Few-Shot Learning、Image Enhancement Techniques

Abstract Foundation models have revolutionized general-purpose problem-solving, offering rapidtask adaptation through pretraining, meta-training, and finetuning. Recent crucial advances in these paradigms reveal the importance of challenging taskprioritized sampling to enhance adaptation robustness under distribution shifts. However, ranking task difficulties over iteration as a preliminary step typically requiresexhaustive task evaluation, which is practically unaffordable in computation and data-annotation. This study provides a novel perspective to illuminate the possibility of leveraging thedual importance of adaptation robustness and learning efficiency, particularly inscenarios where task evaluation is risky or costly, such as iterative agent-environmentinteractions for robotic policy evaluation or computationally intensive inference steps forfinetuning foundation models. Firstly, we introduce Model Predictive Task Sampling (MPTS), a framework that bridgesthe task space and adaptation risk landscape, providing a theoretical foundation forrobust active task sampling. MPTS employs a generative model to characterize the episodic optimization process andpredicts task-specific adaptation risk via posterior inference. The resulting risk learner amortizes the costly evaluation of task adaptationperformance and provably approximates task difficulty rankings. MPTS seamlesslyintegrates into zero-shot, few-shot, and supervised finetuning settings. Empirically, we conduct extensiv...