Early-exit networks reduce inference cost by allowing ``easy'' inputs to stop early, but practical deployment hinges on knowing \emph{when} early exit is safe. We introduce SAFE-KD, a universal multi-exit wrapper for modern vision backbones that couples hierarchical distillation with \emph{conformal risk control}. SAFE-KD attaches lightweight exit heads at intermediate depths, distills a strong teacher into all exits via Decoupled Knowledge Distillation (DKD), and enforces deep-to-shallow consistency between exits. At inference, we calibrate per-exit stopping thresholds on a held-out set using conformal risk control (CRC) to guarantee a user-specified \emph{selective} misclassification risk (among the samples that exit early) under exchangeability. Across multiple datasets and architectures, SAFE-KD yields improved accuracy compute trade-offs, stronger calibration, and robust performance under corruption while providing finite-sample risk guarantees.
Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
The Hebrew University of Jerusalem, Israel（特拉维夫大学）；Bar Ilan University, Israel（巴伊兰大学）；Ben-Gurion University of the Negev, Israel（贝纳亚克大学）；University of California, Riverside, USA（加州大学河滨分校）
Balancing Stability and Plasticity in Sequentially Trained Early-Exiting Neural Networks
TICLab, International University of Rabat, Morocco（拉巴特国际大学TIC实验室，摩洛哥）；College of Computing, University Mohammed VI Polytechnic, Morocco（摩洛哥穆莱·伊斯梅尔Polytechnic大学计算机学院）；School of Electronic and Electrical Engineering, University of Leeds, UK（利兹大学电子与电气工程学院）
How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies
Jagiellonian University（雅盖隆大学）；University of Warsaw（华沙大学）；Warsaw University of Technology（华沙技术大学）；IDEAS Research Institute（IDEAS研究所）；Department of Information Engineering, Electronics, and Telecommunications (DIET) at Sapienza, University of Rome, Italy（罗马大学萨皮恩扎信息工程、电子与电信系）；Wroclaw University of Science and Technology（波兹南科学与技术大学）
Safe Self-Refinement for Transformer-based Domain Adaptation
Stony Brook University（石溪大学）；XPeng Motors（小鹏汽车）
无监督的领域自适应（UDA）旨在利用标签丰富的源域来解决相关未标记目标域上的任务。这是一个具有挑战性的问题，特别是当一个大的域之间的差距位于源和目标域。本文提出了一种新的解决方案SSRT（Safe Self-Refinement for Transformer-based领域自适应），从两个方面进行了改进。首先，由于视觉Transformer在各种视觉任务中的成功，我们为SSRT配备了一个Transformer骨干。我们发现，视觉Transformer与简单的对抗性适应的组合超过了最好的报告卷积神经网络（CNN）的结果，基于具有挑战性的DomainNet基准，显示其强大的可转移特征表示。其次，为了降低模型崩溃的风险，提高知识转移的有效性与大差距的领域之间，我们提出了一个安全的自我完善策略。具体而言，SSRT利用扰动的目标域数据的预测来细化模型。由于视觉Transformer的模型容量很大，并且在这种具有挑战性的任务中的预测可能是有噪声的，因此设计了一种安全的训练机制来自适应地调整学习配置。在几个广泛测试的UDA基准上进行了广泛的评估，SSRT始终获得最佳性能，包括在Bull-Home上的85.43%，在VisDA-2017上的88.76%和在DomainNet上的45.2%。
Department of Computer Science, Control and Management Engineering, Sapienza University of Rome, Rome, Italy（计算机科学与控制管理工程系，罗马萨皮恩扎大学，意大利罗马）；Institute of Information Science and Technologies "Alessandro Faedo" - ISTI-CNR, Pisa, Italy（信息科学与技术研究所 "Alessandro Faedo" - ISTI-CNR，意大利比萨）；Information Engineering Department, University of Pisa, Pisa, Italy（信息工程系，比萨大学，意大利比萨）；CNRS, i3S, Inria（国家科学研究中心 CNRS、i3S、Inria）
