Knowledge distillation (KD) has gained a lot of attention in the field of model compression for edge devices thanks to its effectiveness in compressing large powerful networks into smaller lower-capacity models. Online distillation, in which both the teacher and the student are learning collaboratively, has also gained much interest due to its ability to improve on the performance of the networks involved. The Kullback-Leibler (KL) divergence ensures the proper knowledge transfer between the teacher and student. However, most online KD techniques present some bottlenecks under the network capacity gap. By cooperatively and simultaneously training, the models the KL distance becomes incapable of properly minimizing the teacher's and student's distributions. Alongside accuracy, critical edge device applications are in need of well-calibrated compact networks. Confidence calibration provides a sensible way of getting trustworthy predictions. We propose BD-KD: Balancing of Divergences for online Knowledge Distillation. We show that adaptively balancing between the reverse and forward divergences shifts the focus of the training strategy to the compact student network without limiting the teacher network's learning process. We demonstrate that, by performing this balancing design at the level of the student distillation loss, we improve upon both performance accuracy and calibration of the compact student network. We conducted extensive experiments using a variety of network architectures and show improvements on multiple datasets including CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet. We illustrate the effectiveness of our approach through comprehensive comparisons and ablations with current state-of-the-art online and offline KD techniques.

Granular jamming has recently become popular in soft robotics with widespread applications including industrial gripping, surgical robotics and haptics. Previous work has investigated the use of various techniques that exploit the nature of granular physics to improve jamming performance, however this is generally underrepresented in the literature compared to its potential impact. We present the first research that exploits vibration-based fluidisation actively (e.g., during a grip) to elicit bespoke performance from granular jamming grippers. We augment a conventional universal gripper with a computer-controllled audio exciter, which is attached to the gripper via a 3D printed mount, and build an automated test rig to allow large-scale data collection to explore the effects of active vibration. We show that vibration in soft jamming grippers can improve holding strength. In a series of studies, we show that frequency and amplitude of the waveforms are key determinants to performance, and that jamming performance is also dependent on temporal properties of the induced waveform. We hope to encourage further study focused on active vibrational control of jamming in soft robotics to improve performance and increase diversity of potential applications.

Fruit harvesting has recently experienced a shift towards soft grippers that possess compliance, adaptability, and delicacy. In this context, pneumatic grippers are popular, due to provision of high deformability and compliance, however they typically possess limited grip strength. Jamming possesses strong grip capability, however has limited deformability and often requires the object to be pushed onto a surface to attain a grip. This paper describes a hybrid gripper combining pneumatics (for deformation) and jamming (for grip strength). Our gripper utilises a torus (donut) structure with two chambers controlled by pneumatic and vacuum pressure respectively, to conform around a target object. The gripper displays good adaptability, exploiting pneumatics to mould to the shape of the target object where jamming can be successfully harnessed to grip. The main contribution of the paper is design, fabrication, and characterisation of the first hybrid gripper that can use granular jamming in free space, achieving significantly larger retention forces compared to pure pneumatics. We test our gripper on a range of different sizes and shapes, as well as picking a broad range of real fruit.

The introductory programming sequence has been the focus of much research in computing education. The recent advent of several viable and freely-available AI-driven code generation tools present several immediate opportunities and challenges in this domain. In this position paper we argue that the community needs to act quickly in deciding what possible opportunities can and should be leveraged and how, while also working on how to overcome or otherwise mitigate the possible challenges. Assuming that the effectiveness and proliferation of these tools will continue to progress rapidly, without quick, deliberate, and concerted efforts, educators will lose advantage in helping shape what opportunities come to be, and what challenges will endure. With this paper we aim to seed this discussion within the computing education community.

知识蒸馏（KD）是压缩边缘设备深层分类模型的有效工具。但是，KD的表现受教师和学生网络之间较大容量差距的影响。最近的方法已诉诸KD的多个教师助手（TA）设置，该设置依次降低了教师模型的大小，以相对弥合这些模型之间的尺寸差距。本文提出了一种称为“知识蒸馏”课程专家选择的新技术，以有效地增强在容量差距问题下对紧凑型学生的学习。该技术建立在以下假设的基础上：学生网络应逐渐使用分层的教学课程来逐步指导，因为它可以从较低（较高的）容量教师网络中更好地学习（硬）数据样本。具体而言，我们的方法是一种基于TA的逐渐的KD技术，它每个输入图像选择单个教师，该课程是基于通过对图像进行分类的难度驱动的课程的。在这项工作中，我们凭经验验证了我们的假设，并对CIFAR-10，CIFAR-100，CINIC-10和Imagenet数据集进行了严格的实验，并在类似VGG的模型，Resnets和WideresNets架构上显示出提高的准确性。

基于BERT的微调模型在内存，计算和时间上是资源密集的。尽管许多先前的工作旨在通过压缩技术（例如修剪）提高推论效率，但这些作品并未明确解决培训对下游任务的计算挑战。我们介绍了学习者模块和启动，新颖的方法，以利用预训练的语言模型的过度参数化，以获得收敛速度和资源利用率的好处。学习者模块通过微调参数的微调来导航1）有效训练的双结合，以及2）通过确保快速收敛和高度度量得分有效训练。我们在Distilbert上的结果表明，学习者在与基础方面的表现或超过基线。学习者训练7倍的参数比胶水上的最新方法少。在可乐方面，学习者快速调整20％，并且资源利用率显着降低。

粒状干扰在软机器人中的应用是最近和有希望的新技术，为创建更高的性能机器人设备提供令人兴奋的可能性。通过在含有颗粒物质内的膜内的真空压力施加真空压力来实现粒状干扰，并且从设计角度来看特别是有趣的，因为可以利用设计参数的多种设计参数来诱导各种有用的行为。迄今为止，已经研究了变量（如晶粒形状和尺寸）以及膜材料的效果作为诱导定制抓握性能的手段，但是由于其特定地，尚未研究其他主要贡献因素，膜形态膜形态学两种准确建模和制造的复杂性。该研究介绍了优化颗粒干扰夹具的膜形态，组合多材料3D打印和进化算法来搜索Materio中的各种形态设计空间的研究。在单个运行中打印整个几代，并测试夹持器保持力并用作健身测量。我们的方法是相对可扩展的，规避需要建模，并保证所考虑的夹具的真实表现。结果表明，膜形态是夹具性能的关键决定因素。可以看到常见的高性能设计以优化粒状夹持器产生抓地力的所有三种主要识别机制，与标准夹持形态有显着不同，并概括跨越一系列测试对象。

Designing experiments often requires balancing between learning about the true treatment effects and earning from allocating more samples to the superior treatment. While optimal algorithms for the Multi-Armed Bandit Problem (MABP) provide allocation policies that optimally balance learning and earning, they tend to be computationally expensive. The Gittins Index (GI) is a solution to the MABP that can simultaneously attain optimality and computationally efficiency goals, and it has been recently used in experiments with Bernoulli and Gaussian rewards. For the first time, we present a modification of the GI rule that can be used in experiments with exponentially-distributed rewards. We report its performance in simulated 2- armed and 3-armed experiments. Compared to traditional non-adaptive designs, our novel GI modified design shows operating characteristics comparable in learning (e.g. statistical power) but substantially better in earning (e.g. direct benefits). This illustrates the potential that designs using a GI approach to allocate participants have to improve participant benefits, increase efficiencies, and reduce experimental costs in adaptive multi-armed experiments with exponential rewards.

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.

Extracting complex structures from grid-based data is a common key step in automated medical image analysis. The conventional solution to recovering tree-structured geometries typically involves computing the minimal cost path through intermediate representations derived from segmentation masks. However, this methodology has significant limitations in the context of projective imaging of tree-structured 3D anatomical data such as coronary arteries, since there are often overlapping branches in the 2D projection. In this work, we propose a novel approach to predicting tree connectivity structure which reformulates the task as an optimization problem over individual steps of a recursive process. We design and train a two-stage model which leverages the UNet and Transformer architectures and introduces an image-based prompting technique. Our proposed method achieves compelling results on a pair of synthetic datasets, and outperforms a shortest-path baseline.