现有的视频理解数据集主要集中在人类的互动上，几乎没有关注“在野外”设置，在户外录制了视频。我们提出了Wildqa，这是一个视频理解外部设置中录制的视频的数据集。除了视频问答（视频质量质量检查）外，我们还介绍了确定给定问答（视频证据选择）视觉支持的新任务。通过使用各种基线模型的评估，我们表明Wildqa对愿景和语言研究社区构成了新的挑战。该数据集可在https://lit.eecs.umich.edu/wildqa/上找到。

Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics. As in other fields of deep learning, tools have been devised to extract features such as sequence motifs that can explain the predictions made by a trained network. Here we intend to go beyond explainable machine learning and introduce SEISM, a selective inference procedure to test the association between these extracted features and the predicted phenotype. In particular, we discuss how training a one-layer convolutional network is formally equivalent to selecting motifs maximizing some association score. We adapt existing sampling-based selective inference procedures by quantizing this selection over an infinite set to a large but finite grid. Finally, we show that sampling under a specific choice of parameters is sufficient to characterize the composite null hypothesis typically used for selective inference-a result that goes well beyond our particular framework. We illustrate the behavior of our method in terms of calibration, power and speed and discuss its power/speed trade-off with a simpler data-split strategy. SEISM paves the way to an easier analysis of neural networks used in regulatory genomics, and to more powerful methods for genome wide association studies (GWAS).

Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to reconstruction attacks. Inspired by the success of games (i.e., probabilistic experiments) to study security properties in cryptography, some authors describe privacy inference risks in machine learning using a similar game-based style. However, adversary capabilities and goals are often stated in subtly different ways from one presentation to the other, which makes it hard to relate and compose results. In this paper, we present a game-based framework to systematize the body of knowledge on privacy inference risks in machine learning.

The emergence of large pretrained models has enabled language models to achieve superior performance in common NLP tasks, including language modeling and question answering, compared to previous static word representation methods. Augmenting these models with a retriever to retrieve the related text and documents as supporting information has shown promise in effectively solving NLP problems in a more interpretable way given that the additional knowledge is injected explicitly rather than being captured in the models' parameters. In spite of the recent progress, our analysis on retriever-augmented language models shows that this class of language models still lack reasoning over the retrieved documents. In this paper, we study the strengths and weaknesses of different retriever-augmented language models such as REALM, kNN-LM, FiD, ATLAS, and Flan-T5 in reasoning over the selected documents in different tasks. In particular, we analyze the reasoning failures of each of these models and study how the models' failures in reasoning are rooted in the retriever module as well as the language model.

Graph learning problems are typically approached by focusing on learning the topology of a single graph when signals from all nodes are available. However, many contemporary setups involve multiple related networks and, moreover, it is often the case that only a subset of nodes is observed while the rest remain hidden. Motivated by this, we propose a joint graph learning method that takes into account the presence of hidden (latent) variables. Intuitively, the presence of the hidden nodes renders the inference task ill-posed and challenging to solve, so we overcome this detrimental influence by harnessing the similarity of the estimated graphs. To that end, we assume that the observed signals are drawn from a Gaussian Markov random field with latent variables and we carefully model the graph similarity among hidden (latent) nodes. Then, we exploit the structure resulting from the previous considerations to propose a convex optimization problem that solves the joint graph learning task by providing a regularized maximum likelihood estimator. Finally, we compare the proposed algorithm with different baselines and evaluate its performance over synthetic and real-world graphs.

Vision Transformers (ViTs) have become a dominant paradigm for visual representation learning with self-attention operators. Although these operators provide flexibility to the model with their adjustable attention kernels, they suffer from inherent limitations: (1) the attention kernel is not discriminative enough, resulting in high redundancy of the ViT layers, and (2) the complexity in computation and memory is quadratic in the sequence length. In this paper, we propose a novel attention operator, called lightweight structure-aware attention (LiSA), which has a better representation power with log-linear complexity. Our operator learns structural patterns by using a set of relative position embeddings (RPEs). To achieve log-linear complexity, the RPEs are approximated with fast Fourier transforms. Our experiments and ablation studies demonstrate that ViTs based on the proposed operator outperform self-attention and other existing operators, achieving state-of-the-art results on ImageNet, and competitive results on other visual understanding benchmarks such as COCO and Something-Something-V2. The source code of our approach will be released online.

In this work, we estimate the depth in which domestic waste are located in space from a mobile robot in outdoor scenarios. As we are doing this calculus on a broad range of space (0.3 - 6.0 m), we use RGB-D camera and LiDAR fusion. With this aim and range, we compare several methods such as average, nearest, median and center point, applied to those which are inside a reduced or non-reduced Bounding Box (BB). These BB are obtained from segmentation and detection methods which are representative of these techniques like Yolact, SOLO, You Only Look Once (YOLO)v5, YOLOv6 and YOLOv7. Results shown that, applying a detection method with the average technique and a reduction of BB of 40%, returns the same output as segmenting the object and applying the average method. Indeed, the detection method is faster and lighter in comparison with the segmentation one. The committed median error in the conducted experiments was 0.0298 ${\pm}$ 0.0544 m.

Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The method of moving frames is classical for deriving operators invariant to the action of a Lie group in a manifold.Recently, a rotation and translation equivariant neural network for image data was proposed based on the moving frames approach. In this paper we significantly improve that approach by reducing the computation of moving frames to only one, at the input stage, instead of repeated computations at each layer. The equivariance of the resulting architecture is proved theoretically and we build a rotation and translation equivariant neural network to process volumes, i.e. signals on the 3D space. Our trained model overperforms the benchmarks in the medical volume classification of most of the tested datasets from MedMNIST3D.

Predicting discrete events in time and space has many scientific applications, such as predicting hazardous earthquakes and outbreaks of infectious diseases. History-dependent spatio-temporal Hawkes processes are often used to mathematically model these point events. However, previous approaches have faced numerous challenges, particularly when attempting to forecast one or multiple future events. In this work, we propose a new neural architecture for multi-event forecasting of spatio-temporal point processes, utilizing transformers, augmented with normalizing flows and probabilistic layers. Our network makes batched predictions of complex history-dependent spatio-temporal distributions of future discrete events, achieving state-of-the-art performance on a variety of benchmark datasets including the South California Earthquakes, Citibike, Covid-19, and Hawkes synthetic pinwheel datasets. More generally, we illustrate how our network can be applied to any dataset of discrete events with associated markers, even when no underlying physics is known.

安全可靠的自主驾驶堆栈（AD）的设计是我们时代最具挑战性的任务之一。预计这些广告将在具有完全自主权的高度动态环境中驱动，并且比人类更大的可靠性。从这个意义上讲，要高效，安全地浏览任意复杂的流量情景，广告必须具有预测周围参与者的未来轨迹的能力。当前的最新模型通常基于复发，图形和卷积网络，在车辆预测的背景下取得了明显的结果。在本文中，我们探讨了在生成模型进行运动预测中注意力的影响，考虑到物理和社会环境以计算最合理的轨迹。我们首先使用LSTM网络对过去的轨迹进行编码，该网络是计算社会背景的多头自我发言模块的输入。另一方面，我们制定了一个加权插值来计算最后一个观测框中的速度和方向，以便计算可接受的目标点，从HDMAP信息的可驱动的HDMAP信息中提取，这代表了我们的物理环境。最后，我们的发电机的输入是从多元正态分布采样的白噪声矢量，而社会和物理环境则是其条件，以预测可行的轨迹。我们使用Argoverse运动预测基准1.1验证我们的方法，从而实现竞争性的单峰结果。