When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often trained to solve the target tasks directly.Inspired by human learning, we propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals that are used to pre-train a model before tackling the target task. We focus on classification tasks, and design the intermediate tasks using an automatically constructed label hierarchy. We train the model at each level of the hierarchy, from coarse labels to fine labels, transferring acquired knowledge across these levels. For instance, the model will first learn to distinguish animals from objects, and then use this acquired knowledge when learning to classify among more fine-grained classes such as cat, dog, car, and truck. Most existing curriculum learning algorithms for supervised learning consist of scheduling the order in which the training examples are presented to the model. In contrast, our approach focuses on the output space of the model. We evaluate our method on several established datasets and show significant performance gains especially on classification problems with many labels. We also evaluate on a new synthetic dataset which allows us to study multiple aspects of our method.
MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs
National University of Singapore（新加坡国立大学）；HeartVoice Medical Technology（心声医疗科技）；University of Science and Technology of China（中国科学技术大学）；Sir Run Run Shaw Hospital, Zhejiang University School of Medicine（浙江大学医学院附属邵逸夫医院）；Peking University（北京大学）；Institute of Medical Technology, Health Science Center of Peking University（北京大学医学部医学技术研究院）
AutoLoop: Fast Visual SLAM Fine-tuning through Agentic Curriculum Learning
University of Haifa（海法大学）；Leon H. Charney School of Marine Sciences（莱昂·H·查尼海洋科学学院）；Hatter Department of Marine Technologies（哈特海洋技术系）；Swarm & AI Lab (SAIL)（群体与人工智能实验室（SAIL））
Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models
HiThink Research（海思思考研究院）；Auburn University（奥本大学）；Kent State University（肯特州立大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；Inria（法国国家信息与自动化研究所）；University of Montpellier（蒙彼利埃大学）；CNRS（法国国家科学研究中心）；LNCC（巴西国家计算科学实验室）；Fudan University（复旦大学）；BEDI Cloud（北电云）
从粗到细的Q-注意力通过以从粗到细的方式离散化平移空间来实现样本高效的机器人操作，其中分辨率在层次结构中的每一层逐渐增加。虽然有效，但Q-attention遭受“粗糙的模糊性”-当体素化非常粗糙时，如果不首先以更精细的分辨率进行检查，就无法区分外观相似的对象。为了解决这个问题，我们建议将Q-attention设想为一棵树，它可以扩展并用于在每个Q-attention深度处累积前k个体素的值估计。当我们的扩展，Q-attention with Tree Expansion（QTE），在注意力驱动的机器人操作（ARM）系统中取代标准的Q-attention时，我们能够完成更大的任务集;特别是那些遭受“粗糙模糊”的任务。除了在12个RLBench任务中评估我们的方法外，我们还表明，在涉及小对象的现实任务中，性能的提高是显而易见的。
CurricuLLM: Designing Personalized and Workforce-Aligned Cybersecurity Curricula Using Fine-Tuned LLMs
Lund University, Department of Electrical；University of Helsinki, Department of Computer Science, Helsinki, Finland；Helsinki Institute for Information Technology, Helsinki, Finland；Karlstad University, Department of Mathematics \& Computer Science, Karlstad, Sweden
From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与技术学院）；Tongyi Lab, Alibaba Group（阿里巴巴集团通义实验室）；The Hong Kong University of Science and Technology（香港科技大学）；Guangzhou University（广州大学）
Multi-Scale Context-Guided Lumbar Spine Disease Identification with Coarse-to-fine Localization and Classification
Center for Data Science, Peking University（北京大学数据科学中心）；National Engineering Laboratory for Big Data Analysis and Applications, Peking University（北京大学大数据分析与应用国家工程实验室）；National Biomedical Imaging Center, Peking University（北京大学生物医学成像国家中心）
Closing the Gap: Data-Centric Fine-Tuning of Vision Language Models for the Standardized Exam Questions
organization= Department of Computer Engineering, Middle East Technical University (METU) , city= Ankara , country= Türkiye；organization= METU-DTX Digital Transformation \& Innovation Centre, METU , city= Ankara , country= Türkiye
Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment
Graduate School of Arts and Science, University of Tokyo（东京大学艺术与科学研究生院）
