多实施学习（MIL）被广泛用于对病理整体幻灯片图像（WSIS）的计算机辅助解释，以解决缺乏像素或贴片的注释。通常，这种方法直接应用“自然图像驱动”的MIL算法，该算法忽略了WSIS的多尺度（即金字塔）性质。现成的MIL算法通常部署在单个WSIS（例如20x放大倍率）上，而人类病理学家通常以多尺度的方式汇总全球和局部模式（例如，通过放大不同大型）。在这项研究中，我们提出了一种新型的跨尺度注意机制，以明确地将尺度间相互作用汇总到单个MIL网络的克罗恩病（CD）（CD），这是炎症性肠病的一种形式。本文的贡献是两个方面：（1）提出了一种跨尺度注意机制，以从不同分辨率的多尺度相互作用汇总特征； （2）生成差异多尺度注意的可视化，以定位可解释的病变模式。通过训练来自20名CD患者的约250,000 H＆E染色的上升结肠（AC）斑块，在不同尺度上训练30个健康对照样品，我们的方法在曲线下（AUC）得分为0.8924，与基线模型相比达到0.8924。官方实施可在https://github.com/hrlblab/cs-mil上公开获得。

放射学报告含有在其解释图像中被放射科学家记录的多样化和丰富的临床异常。放射发现的综合语义表示将使广泛的次要使用应用来支持诊断，分类，结果预测和临床研究。在本文中，我们提出了一种新的放射学报告语料库，注释了临床调查结果。我们的注释模式捕获了可观察到的病理发现的详细说明（“病变”）和其他类型的临床问题（“医学问题”）。该模式使用了基于事件的表示来捕获细粒细节，包括断言，解剖学，特征，大小，计数等。我们的黄金标准语料库包含总共500个注释的计算机断层扫描（CT）报告。我们利用两个最先进的深度学习架构提取了触发器和论证实体，包括伯特。然后，我们使用基于BERT的关系提取模型预测触发器和参数实体（称为参数角色）之间的连接。我们使用预先从我们的机构的300万放射学报告预先培训的BERT模型实现了最佳提取性能：90.9％-93.4％f1用于查找触发器的触发器72.0％-85.6％f1，用于参数角色。为了评估型号的概括性，我们使用了从模拟胸部X射线（MIMIC-CXR）数据库中随机采样的外部验证。该验证集的提取性能为95.6％，用于发现触发器和参数角色的79.1％-89.7％，表明模型与具有不同的成像模型的跨机构数据一致。我们从模拟CXR数据库中的所有放射学报告中提取了查找事件，并为研究界提供了提取。

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.

New architecture GPUs like A100 are now equipped with multi-instance GPU (MIG) technology, which allows the GPU to be partitioned into multiple small, isolated instances. This technology provides more flexibility for users to support both deep learning training and inference workloads, but efficiently utilizing it can still be challenging. The vision of this paper is to provide a more comprehensive and practical benchmark study for MIG in order to eliminate the need for tedious manual benchmarking and tuning efforts. To achieve this vision, the paper presents MIGPerf, an open-source tool that streamlines the benchmark study for MIG. Using MIGPerf, the authors conduct a series of experiments, including deep learning training and inference characterization on MIG, GPU sharing characterization, and framework compatibility with MIG. The results of these experiments provide new insights and guidance for users to effectively employ MIG, and lay the foundation for further research on the orchestration of hybrid training and inference workloads on MIGs. The code and results are released on https://github.com/MLSysOps/MIGProfiler. This work is still in progress and more results will be published soon.

The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the enormous success of data augmentation currently remains limited to single-modality tasks like image classification. Indeed, it is particularly difficult to augment each modality while preserving the overall semantic structure of the data; for example, a caption may no longer be a good description of an image after standard augmentations have been applied, such as translation. Moreover, it is challenging to specify reasonable transformations that are not tailored to a particular modality. In this paper, we introduce LeMDA, Learning Multimodal Data Augmentation, an easy-to-use method that automatically learns to jointly augment multimodal data in feature space, with no constraints on the identities of the modalities or the relationship between modalities. We show that LeMDA can (1) profoundly improve the performance of multimodal deep learning architectures, (2) apply to combinations of modalities that have not been previously considered, and (3) achieve state-of-the-art results on a wide range of applications comprised of image, text, and tabular data.

Artificial Intelligence (AI) and its applications have sparked extraordinary interest in recent years. This achievement can be ascribed in part to advances in AI subfields including Machine Learning (ML), Computer Vision (CV), and Natural Language Processing (NLP). Deep learning, a sub-field of machine learning that employs artificial neural network concepts, has enabled the most rapid growth in these domains. The integration of vision and language has sparked a lot of attention as a result of this. The tasks have been created in such a way that they properly exemplify the concepts of deep learning. In this review paper, we provide a thorough and an extensive review of the state of the arts approaches, key models design principles and discuss existing datasets, methods, their problem formulation and evaluation measures for VQA and Visual reasoning tasks to understand vision and language representation learning. We also present some potential future paths in this field of research, with the hope that our study may generate new ideas and novel approaches to handle existing difficulties and develop new applications.

State-of-the-art performance in electroencephalography (EEG) decoding tasks is currently often achieved with either Deep-Learning or Riemannian-Geometry-based decoders. Recently, there is growing interest in Deep Riemannian Networks (DRNs) possibly combining the advantages of both previous classes of methods. However, there are still a range of topics where additional insight is needed to pave the way for a more widespread application of DRNs in EEG. These include architecture design questions such as network size and end-to-end ability as well as model training questions. How these factors affect model performance has not been explored. Additionally, it is not clear how the data within these networks is transformed, and whether this would correlate with traditional EEG decoding. Our study aims to lay the groundwork in the area of these topics through the analysis of DRNs for EEG with a wide range of hyperparameters. Networks were tested on two public EEG datasets and compared with state-of-the-art ConvNets. Here we propose end-to-end EEG SPDNet (EE(G)-SPDNet), and we show that this wide, end-to-end DRN can outperform the ConvNets, and in doing so use physiologically plausible frequency regions. We also show that the end-to-end approach learns more complex filters than traditional band-pass filters targeting the classical alpha, beta, and gamma frequency bands of the EEG, and that performance can benefit from channel specific filtering approaches. Additionally, architectural analysis revealed areas for further improvement due to the possible loss of Riemannian specific information throughout the network. Our study thus shows how to design and train DRNs to infer task-related information from the raw EEG without the need of handcrafted filterbanks and highlights the potential of end-to-end DRNs such as EE(G)-SPDNet for high-performance EEG decoding.

Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing studies visually analyze the mechanisms of convolutional neural networks, an analogous exploration of ViTs remains challenging. In this paper, we first address the obstacles to performing visualizations on ViTs. Assisted by these solutions, we observe that neurons in ViTs trained with language model supervision (e.g., CLIP) are activated by semantic concepts rather than visual features. We also explore the underlying differences between ViTs and CNNs, and we find that transformers detect image background features, just like their convolutional counterparts, but their predictions depend far less on high-frequency information. On the other hand, both architecture types behave similarly in the way features progress from abstract patterns in early layers to concrete objects in late layers. In addition, we show that ViTs maintain spatial information in all layers except the final layer. In contrast to previous works, we show that the last layer most likely discards the spatial information and behaves as a learned global pooling operation. Finally, we conduct large-scale visualizations on a wide range of ViT variants, including DeiT, CoaT, ConViT, PiT, Swin, and Twin, to validate the effectiveness of our method.

National research evaluation initiatives and incentive schemes have previously chosen between simplistic quantitative indicators and time-consuming peer review, sometimes supported by bibliometrics. Here we assess whether artificial intelligence (AI) could provide a third alternative, estimating article quality using more multiple bibliometric and metadata inputs. We investigated this using provisional three-level REF2021 peer review scores for 84,966 articles submitted to the UK Research Excellence Framework 2021, matching a Scopus record 2014-18 and with a substantial abstract. We found that accuracy is highest in the medical and physical sciences Units of Assessment (UoAs) and economics, reaching 42% above the baseline (72% overall) in the best case. This is based on 1000 bibliometric inputs and half of the articles used for training in each UoA. Prediction accuracies above the baseline for the social science, mathematics, engineering, arts, and humanities UoAs were much lower or close to zero. The Random Forest Classifier (standard or ordinal) and Extreme Gradient Boosting Classifier algorithms performed best from the 32 tested. Accuracy was lower if UoAs were merged or replaced by Scopus broad categories. We increased accuracy with an active learning strategy and by selecting articles with higher prediction probabilities, as estimated by the algorithms, but this substantially reduced the number of scores predicted.

Motion planning and control in autonomous car racing are one of the most challenging and safety-critical tasks due to high speed and dynamism. The lower-level control nodes are expected to be highly optimized due to resource constraints of onboard embedded processing units, although there are strict latency requirements. Some of these guarantees can be provided at the application level, such as using ROS2's Real-Time executors. However, the performance can be far from satisfactory as many modern control algorithms (such as Model Predictive Control) rely on solving complicated online optimization problems at each iteration. In this paper, we present a simple yet effective multi-threading technique to optimize the throughput of online-control algorithms for resource-constrained autonomous racing platforms. We achieve this by maintaining a systematic pool of worker threads solving the optimization problem in parallel which can improve the system performance by reducing latency between control input commands. We further demonstrate the effectiveness of our method using the Model Predictive Contouring Control (MPCC) algorithm running on Nvidia's Xavier AGX platform.