We provide an extended version of the Experimental Setup from Section 5 below. Linear Model This domain involves learning a linear model when the underlying mapping between features and predictions is cubic. Concretely, the aim is to choose the top B =1 out of N = 50 resources using a linear model. The fact that the features can be seen as 1-dimensional allows us to visualize the learned models (as seen in Figure 4). Predict: Given a feature xn U[0,1], use a linear model to predict the utility ˆyof choosing resource n, where the true utility is given by yn = 10x3n 6.5xn.

The variation is very small, and so we can conclude that the model is not sensitive to the initialization.

They obtain 0.5% and 0.7% gains over those with

The classification of human-performed assembly tasks is essential in collaborative robotics to ensure safety, anticipate robot actions, and facilitate robot learning. However, achieving reliable classification is challenging when segmenting tasks into smaller primitive actions is unfeasible, requiring us to classify long assembly tasks that encompass multiple primitive actions. In this study, we propose classifying long assembly sequential tasks based on hand landmark coordinates and compare the performance of two well-established classifiers, LSTM and Transformer, as well as a recent model, xLSTM. We used the HRC scenario proposed in the CT benchmark, which includes long assembly tasks that combine actions such as insertions, screw fastenings, and snap fittings. Testing was conducted using sequences gathered from both the human operator who performed the training sequences and three new operators. The testing results of real-padded sequences for the LSTM, Transformer, and xLSTM models was 72.9%, 95.0% and 93.2% for the training operator, and 43.5%, 54.3% and 60.8% for the new operators, respectively. The LSTM model clearly underperformed compared to the other two approaches. As expected, both the Transformer and xLSTM achieved satisfactory results for the operator they were trained on, though the xLSTM model demonstrated better generalization capabilities to new operators. The results clearly show that for this type of classification, the xLSTM model offers a slight edge over Transformers.

Recent work has shown that successful per-domain generalizing action policies can be learned. Scaling behavior, from small training instances to large test instances, is the key objective; and the use of validation instances larger than training instances is one key to achieve it. Prior work has used fixed validation sets. Here, we introduce a method generating the validation set dynamically, on the fly, increasing instance size so long as informative and feasible. We also introduce refined methodology for evaluating scaling behavior, generating test instances systematically to guarantee a given confidence in coverage performance for each instance size. In experiments, dynamic validation improves scaling behavior of GNN policies in all 9 domains used.

The Visually Rich Form Document Intelligence and Understanding (VRDIU) Track B focuses on the localization of key information in document images. The goal is to develop a method capable of localizing objects in both digital and handwritten documents, using only digital documents for training. This paper presents a simple yet effective approach that includes a document augmentation phase and an object detection phase. Specifically, we augment the training set of digital documents by mimicking the appearance of handwritten documents. Our experiments demonstrate that this pipeline enhances the models' generalization ability and achieves high performance in the competition.

Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determine the adequacy of a dataset prior to training and evaluating a model's performance would be an essential tool for anyone engaged in experimental design or data collection. However, despite the need for it, the ability to prospectively assess data sufficiency remains an elusive capability. We report here on two experiments undertaken in an attempt to better ascertain whether or not basic descriptive statistical measures can be indicative of how effective a dataset will be at training a resulting model. Leveraging the effect size of our features, this work first explores whether or not a correlation exists between effect size, and resulting model performance (theorizing that the magnitude of the distinction between classes could correlate to a classifier's resulting success). We then explore whether or not the magnitude of the effect size will impact the rate of convergence of our learning rate, (theorizing again that a greater effect size may indicate that the model will converge more rapidly, and with a smaller sample size needed). Our results appear to indicate that this is not an effective heuristic for determining adequate sample size or projecting model performance, and therefore that additional work is still needed to better prospectively assess adequacy of data.

Stock market forecasting has been a topic of extensive research, aiming to provide investors with optimal stock recommendations for higher returns. In recent years, this field has gained even more attention due to the widespread adoption of deep learning models. While these models have achieved impressive accuracy in predicting stock behavior, tailoring them to specific scenarios has become increasingly important. Election Day represents one such critical scenario, characterized by intensified market volatility, as the winning candidate's policies significantly impact various economic sectors and companies. To address this challenge, we propose the Election Day Stock Market Forecasting (EDSMF) Model. Our approach leverages the contextual capabilities of large language models alongside specialized agents designed to analyze the political and economic consequences of elections. By building on a state-of-the-art architecture, we demonstrate that EDSMF improves the predictive performance of the S&P 500 during this uniquely volatile day.

Synthetic data is increasingly being used to address the lack of labeled images in uncommon domains for deep learning tasks. A prominent example is 2D pose estimation of animals, particularly wild species like zebras, for which collecting real-world data is complex and impractical. However, many approaches still require real images, consistency and style constraints, sophisticated animal models, and/or powerful pre-trained networks to bridge the syn-to-real gap. Moreover, they often assume that the animal can be reliably detected in images or videos, a hypothesis that often does not hold, e.g. in wildlife scenarios or aerial images. To solve this, we use synthetic data generated with a 3D photorealistic simulator to obtain the first synthetic dataset that can be used for both detection and 2D pose estimation of zebras without applying any of the aforementioned bridging strategies. Unlike previous works, we extensively train and benchmark our detection and 2D pose estimation models on multiple real-world and synthetic datasets using both pre-trained and non-pre-trained backbones. These experiments show how the models trained from scratch and only with synthetic data can consistently generalize to real-world images of zebras in both tasks. Moreover, we show it is possible to easily generalize those same models to 2D pose estimation of horses with a minimal amount of real-world images to account for the domain transfer. Code, results, trained models; and the synthetic, training, and validation data, including 104K manually labeled frames, are provided as open-source at https://zebrapose.is.tue.mpg.de/