Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks. Developing similar techniques for satellite imagery presents significant opportunities as unlabelled data is plentiful and the inherent temporal and multi-spectral structure provides avenues to further improve existing pre-training strategies. In this paper, we present SatMAE, a pre-training framework for temporal or multi-spectral satellite imagery based on Masked Autoencoder (MAE). To leverage temporal information, we include a temporal embedding along with independently masking image patches across time. In addition, we demonstrate that encoding multi-spectral data as groups of bands with distinct spectral positional encodings is beneficial. Our approach yields strong improvements over previous state-of-the-art techniques, both in terms of supervised learning performance on benchmark datasets (up to " 7%), and transfer learning performance on downstream remote sensing tasks, including land cover classification (up to " 14%) and semantic segmentation.

Video question answering (VideoQA) is a complex task that requires diverse multimodal data for training. Manual annotation of questions and answers for videos, however, is tedious and prohibits scalability. To tackle this problem, recent methods consider zero-shot settings with no manual annotation of visual question-answer. In particular, a promising approach adapts frozen autoregressive language models pretrained on Web-scale text-only data to multi-modal inputs. In contrast, we here build on frozen bidirectional language models (BiLM) and show that such an approach provides a stronger and cheaper alternative for zero-shot VideoQA. In particular, (i) we combine visual inputs with the frozen BiLM using light trainable modules, (ii) we train such modules using Web-scraped multi-modal data, and finally (iii) we perform zero-shot VideoQA inference through masked language modeling, where the masked text is the answer to a given question. Our proposed approach, FrozenBiLM, outperforms the state of the art in zero-shot VideoQA by a significant margin on a variety of datasets, including LSMDC-FiB, iVQA, MSRVTT-QA, MSVD-QA, ActivityNet-QA, TGIF-FrameQA, How2QA and TVQA. It also demonstrates competitive performance in the few-shot and fully-supervised setting. Our code and models are publicly available at [1].

Learning molecular representation is a critical step in molecular machine learning that significantly influences modeling success, particularly in data-scarce situations. The concept of broadly pre-training neural networks has advanced fields such as computer vision, natural language processing, and protein engineering. However, similar approaches for small organic molecules have not achieved comparable success. In this work, we introduce a novel pre-training strategy, substrate scope contrastive learning, which learns atomic representations tailored to chemical reactivity. This method considers the grouping of substrates and their yields in published substrate scope tables as a measure of their similarity or dissimilarity in terms of chemical reactivity. We focus on 20,798 aryl halides in the CAS Content Collection spanning thousands of publications to learn a representation of aryl halide reactivity. We validate our pre-training approach through both intuitive visualizations and comparisons to traditional reactivity descriptors and physical organic chemistry principles. The versatility of these embeddings is further evidenced in their application to yield prediction, regioselectivity prediction, and the diverse selection of new substrates. This work not only presents a chemistry-tailored neural network pre-training strategy to learn reactivity-aligned atomic representations, but also marks a first-of-its-kind approach to benefit from the human bias in substrate scope design.

Many elections are conducted sequentially, where interim results are known to the electorate and can be used by voters to inform their decisions. Given empirical work showing that voters tend to vote for the leading candidates when votes are public [MM+15; ZM+15; RR+17; MG+20; AG22], it is natural to consider the strategic aspect of choosing when to vote in such settings. The power of strategic vote timing is illustrated by the commonplace show-of-hands vote: "early bird" voters may sway undecided voters to follow in their direction. Furthermore, if there are costs associated with voting (e. g., having to commute to a distant polling station), waiting to observe interim results allows voters to save costs, if their preferred outcome appears to have garnered enough support to win. In particular, previous work found that voting costs affect voter turnout in blockchain governance voting, where votes are irrevocable and interim results are public [DY+23; MP+23]. This also applies to settings in which costs may be implicit, such as in democratic deliberation dialogues [FP+23] and social networks [AB+12], where voters may face social consequences if their vote does not conform to the accepted norms (e. g., liking a controversial social media post). 1

This survey paper presents a comprehensive analysis of crime prediction methodologies, exploring the various techniques and technologies utilized in this area. The paper covers the statistical methods, machine learning algorithms, and deep learning techniques employed to analyze crime data, while also examining their effectiveness and limitations. We propose a methodological taxonomy that classifies crime prediction algorithms into specific techniques. This taxonomy is structured into four tiers, including methodology category, methodology sub-category, methodology techniques, and methodology sub-techniques. Empirical and experimental evaluations are provided to rank the different techniques. The empirical evaluation assesses the crime prediction techniques based on four criteria, while the experimental evaluation ranks the algorithms that employ the same sub-technique, the different sub-techniques that employ the same technique, the different techniques that employ the same methodology sub-category, the different methodology sub-categories within the same category, and the different methodology categories. The combination of methodological taxonomy, empirical evaluations, and experimental comparisons allows for a nuanced and comprehensive understanding of crime prediction algorithms, aiding researchers in making informed decisions. Finally, the paper provides a glimpse into the future of crime prediction techniques, highlighting potential advancements and opportunities for further research in this field

While random forests are commonly used for regression problems, existing methods often lack adaptability in complex situations or lose optimality under simple, smooth scenarios. In this study, we introduce the adaptive split balancing forest (ASBF), capable of learning tree representations from data while simultaneously achieving minimax optimality under the Lipschitz class. To exploit higher-order smoothness levels, we further propose a localized version that attains the minimax rate under the H\"older class $\mathcal{H}^{q,\beta}$ for any $q\in\mathbb{N}$ and $\beta\in(0,1]$. Rather than relying on the widely-used random feature selection, we consider a balanced modification to existing approaches. Our results indicate that an over-reliance on auxiliary randomness may compromise the approximation power of tree models, leading to suboptimal results. Conversely, a less random, more balanced approach demonstrates optimality. Additionally, we establish uniform upper bounds and explore the application of random forests in average treatment effect estimation problems. Through simulation studies and real-data applications, we demonstrate the superior empirical performance of the proposed methods over existing random forests.

With the release of Generative AI systems such as ChatGPT, an increasing interest in using Artificial Intelligence (AI) has been observed across domains, including higher education. While emerging statistics show the popularity of using AI amongst undergraduate students, little is yet known about students' perceptions regarding AI including self-reported benefits and concerns from their actual usage, in particular in distance learning contexts. Using a two-step, mixed-methods approach, we examined the perceptions of ten online and distance learning students from diverse disciplines regarding the design of a hypothetical AI Digital Assistant (AIDA). In the first step, we captured students' perceptions via interviews, while the second step supported the triangulation of data by enabling students to share, compare, and contrast perceptions with those of peers. All participants agreed on the usefulness of such an AI tool while studying and reported benefits from using it for real-time assistance and query resolution, support for academic tasks, personalisation and accessibility, together with emotional and social support. Students' concerns related to the ethical and social implications of implementing AIDA, data privacy and data use, operational challenges, academic integrity and misuse, and the future of education. Implications for the design of AI-tailored systems are also discussed.

Distributed training of deep neural networks faces three critical challenges: privacy preservation, communication efficiency, and robustness to fault and adversarial behaviors. Although significant research efforts have been devoted to addressing these challenges independently, their synthesis remains less explored. In this paper, we propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm. Particularly, in terms of privacy guarantees, compared to the existing sign-based approach StoSign, the proposed method improves the dimension dependence on the gradient size and enjoys privacy amplification by mini-batch sampling while ensuring a comparable convergence rate. We also prove that TernaryVote is robust when less than 50% of workers are blind attackers, which matches that of SIGNSGD with majority vote. Extensive experimental results validate the effectiveness of the proposed algorithm.

The global food delivery market provides many opportunities for AI-based services that can improve the efficiency of feeding the world. This paper presents the Cloud Kitchen platform as a decision-making tool for restaurants with food delivery and a simulator to evaluate the impact of the decisions. The platform consists of a Technology-Specific Bridge (TSB) that provides an interface for communicating with restaurants or the simulator. TSB uses a PDDL model to represent decisions embedded in the Unified Planning Framework (UPF). Decision-making, which concerns allocating customers' orders to vehicles and deciding in which order the customers will be served (for each vehicle), is done via a Vehicle Routing Problem with Time Windows (VRPTW), an efficient tool for this problem. We show that decisions made by our platform can improve customer satisfaction by reducing the number of delayed deliveries using a real-world historical dataset.

The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent studies have shown that their inference efficiency deteriorates when generating text in languages other than English. This results in increased inference time and costs. Cross-lingual vocabulary adaptation methods have been proposed for adapting models to a target language aiming to improve downstream performance. However, the effectiveness of these methods on increasing inference efficiency of generative LLMs has yet to be explored. In this paper, we perform an empirical study of various cross-lingual vocabulary adaptation methods on five generative LLMs (including monolingual and multilingual models) across four typologically-diverse languages and four natural language understanding tasks. We find that cross-lingual vocabulary adaptation substantially contributes to LLM inference speedups of up to 271.5%. We also show that adapting LLMs that have been pre-trained on more balanced multilingual data results in downstream performance comparable to the original models.