Coordination is a fundamental aspect of life. The advent of social media has made it integral also to online human interactions, such as those that characterize thriving online communities and social movements. At the same time, coordination is also core to effective disinformation, manipulation, and hate campaigns. This survey collects, categorizes, and critically discusses the body of work produced as a result of the growing interest on coordinated online behavior. We reconcile industry and academic definitions, propose a comprehensive framework to study coordinated online behavior, and review and critically discuss the existing detection and characterization methods. Our analysis identifies open challenges and promising directions of research, serving as a guide for scholars, practitioners, and policymakers in understanding and addressing the complexities inherent to online coordination.

The rise of large language models (LLMs) has enabled us to seek answers to inherently debatable questions on LLM chatbots, necessitating a reliable way to evaluate their ability. However, traditional QA benchmarks assume fixed answers are inadequate for this purpose. To address this, we introduce DebateQA, a dataset of 2,941 debatable questions, each accompanied by multiple human-annotated partial answers that capture a variety of perspectives. We develop two metrics: Perspective Diversity, which evaluates the comprehensiveness of perspectives, and Dispute Awareness, which assesses if the LLM acknowledges the question's debatable nature. Experiments demonstrate that both metrics align with human preferences and are stable across different underlying models. Using DebateQA with two metrics, we assess 12 popular LLMs and retrieval-augmented generation methods. Our findings reveal that while LLMs generally excel at recognizing debatable issues, their ability to provide comprehensive answers encompassing diverse perspectives varies considerably.

In the realm of machine learning and artificial intelligence, ensuring fairness in algorithmic decisionmaking has become an imperative challenge. This concern is driven by the growing awareness of the ethical and societal consequences stemming from automated systems. Unlike the traditional focuses that solely enhance statistical and machine learning algorithms across various performance metrics, the emphasis on fairness injects a nuanced layer of complexity into predictive modeling. It mandates a conscientious evaluation of how algorithmic predictions may perpetuate or mitigate existing biases, thereby influencing real-world outcomes across diverse societal sectors. The notion of fairness within the machine learning community includes a diverse array of definitions for what it means for an algorithm to be fair, with each definition informed by distinct ethical considerations and operational implications [Mitchell et al., 2021, Plecko and Bareinboim, 2022, Barocas et al., 2023]. This diversity often leads to a challenging paradox for practitioners and theorists alike, as adhering to one notion of fairness can sometimes contradict the requirements or objectives of another [Kleinberg et al., 2017, Corbett-Davies and Goel, 2018, Friedler et al., 2021]. The task of ensuring algorithmic fairness is made more complex by its inherently contextspecific nature, which demands careful consideration in selecting fairness criteria that are not only theoretically sound but also practically applicable and aligned with prevailing societal values.

Continuous monitoring and accurate detection of complex sleep patterns associated to different sleep-related conditions is essential, not only for enhancing sleep quality but also for preventing the risk of developing chronic illnesses associated to unhealthy sleep. Despite significant advances in research, achieving versatile recognition of various unhealthy and sub-healthy sleep patterns with simple wearable devices at home remains a significant challenge. Here, we report a robust and durable ultrasensitive strain sensor array printed on a smart garment, in its collar region. This solution allows detecting subtle vibrations associated with multiple sleep patterns at the extrinsic laryngeal muscles. Equipped with a deep learning neural network, it can precisely identify six sleep states-nasal breathing, mouth breathing, snoring, bruxism, central sleep apnea (CSA), and obstructive sleep apnea (OSA)-with an impressive accuracy of 98.6%, all without requiring specific positioning. We further demonstrate its explainability and generalization capabilities in practical applications. Explainable artificial intelligence (XAI) visualizations reflect comprehensive signal pattern analysis with low bias. Transfer learning tests show that the system can achieve high accuracy (overall accuracy of 95%) on new users with very few-shot learning (less than 15 samples per class). The scalable manufacturing process, robustness, high accuracy, and excellent generalization of the smart garment make it a promising tool for next-generation continuous sleep monitoring.

This paper aims to extend the code generation capability of large language models (LLMs) to automatically manage comprehensive software requirements from given textual descriptions. Such requirements include both functional (i.e. achieving expected behavior for inputs) and non-functional (e.g., time/space performance, robustness, maintainability) requirements. However, textual descriptions can either express requirements verbosely or may even omit some of them. We introduce ARCHCODE, a novel framework that leverages in-context learning to organize requirements observed in descriptions and to extrapolate unexpressed requirements from them. ARCHCODE generates requirements from given descriptions, conditioning them to produce code snippets and test cases. Each test case is tailored to one of the requirements, allowing for the ranking of code snippets based on the compliance of their execution results with the requirements. Public benchmarks show that ARCHCODE enhances to satisfy functional requirements, significantly improving Pass@k scores. Furthermore, we introduce HumanEval-NFR, the first evaluation of LLMs' non-functional requirements in code generation, demonstrating ARCHCODE's superiority over baseline methods. The implementation of ARCHCODE and the HumanEval-NFR benchmark are both publicly accessible.

This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an architecture search problem within convolutional neural networks (ConvNets). Our framework, dubbed \textbf{CoRa} (Optimal Quantization Residual \textbf{Co}nvolutional Operator Low-\textbf{Ra}nk Adaptation), is motivated by two key aspects. Firstly, quantization residual knowledge, i.e. the lost information between floating-point weights and quantized weights, has long been neglected by the research community. Reclaiming the critical residual knowledge, with an infinitesimal extra parameter cost, can reverse performance degradation without training. Secondly, state-of-the-art quantization frameworks search for optimal quantized weights to address the performance degradation. Yet, the vast search spaces in weight optimization pose a challenge for the efficient optimization in large models. For example, state-of-the-art BRECQ necessitates $2 \times 10^4$ iterations to quantize models. Fundamentally differing from existing methods, \textbf{CoRa} searches for the optimal architectures of low-rank adapters, reclaiming critical quantization residual knowledge, within the search spaces smaller compared to the weight spaces, by many orders of magnitude. The low-rank adapters approximate the quantization residual weights, discarded in previous methods. We evaluate our approach over multiple pre-trained ConvNets on ImageNet. \textbf{CoRa} achieves comparable performance against both state-of-the-art quantization-aware training and post-training quantization baselines, in $4$-bit and $3$-bit quantization, by using less than $250$ iterations on a small calibration set with $1600$ images. Thus, \textbf{CoRa} establishes a new state-of-the-art in terms of the optimization efficiency in low-bit quantization.

Deep neural networks (DNNs) are vulnerable to small adversarial perturbations of the inputs, posing a significant challenge to their reliability and robustness. Empirical methods such as adversarial training can defend against particular attacks but remain vulnerable to more powerful attacks. Alternatively, Lipschitz networks provide certified robustness to unseen perturbations but lack sufficient expressive power. To harness the advantages of both approaches, we design a novel two-step Optimal Transport induced Adversarial Defense (OTAD) model that can fit the training data accurately while preserving the local Lipschitz continuity. First, we train a DNN with a regularizer derived from optimal transport theory, yielding a discrete optimal transport map linking data to its features. By leveraging the map's inherent regularity, we interpolate the map by solving the convex integration problem (CIP) to guarantee the local Lipschitz property. OTAD is extensible to diverse architectures of ResNet and Transformer, making it suitable for complex data. For efficient computation, the CIP can be solved through training neural networks. OTAD opens a novel avenue for developing reliable and secure deep learning systems through the regularity of optimal transport maps. Empirical results demonstrate that OTAD can outperform other robust models on diverse datasets.

This research investigates biases in text-to-image (TTI) models for the Indic languages widely spoken across India. It evaluates and compares the generative performance and cultural relevance of leading TTI models in these languages against their performance in English. Using the proposed IndicTTI benchmark, we comprehensively assess the performance of 30 Indic languages with two open-source diffusion models and two commercial generation APIs. The primary objective of this benchmark is to evaluate the support for Indic languages in these models and identify areas needing improvement. Given the linguistic diversity of 30 languages spoken by over 1.4 billion people, this benchmark aims to provide a detailed and insightful analysis of TTI models' effectiveness within the Indic linguistic landscape.

Machine learning (ML) is revolutionising drug discovery by expediting the prediction of small molecule properties essential for developing new drugs. These properties -- including absorption, distribution, metabolism and excretion (ADME)-- are crucial in the early stages of drug development since they provide an understanding of the course of the drug in the organism, i.e., the drug's pharmacokinetics. However, existing methods lack personalisation and rely on manually crafted ML algorithms or pipelines, which can introduce inefficiencies and biases into the process. To address these challenges, we propose a novel evolutionary-based automated ML method (AutoML) specifically designed for predicting small molecule properties, with a particular focus on pharmacokinetics. Leveraging the advantages of grammar-based genetic programming, our AutoML method streamlines the process by automatically selecting algorithms and designing predictive pipelines tailored to the particular characteristics of input molecular data. Results demonstrate AutoML's effectiveness in selecting diverse ML algorithms, resulting in comparable or even improved predictive performances compared to conventional approaches. By offering personalised ML-driven pipelines, our method promises to enhance small molecule research in drug discovery, providing researchers with a valuable tool for accelerating the development of novel therapeutic drugs.

The non-profit settlement sector in Canada supports newcomers in achieving successful integration. This sector faces increasing operational pressures amidst rising immigration targets, which highlights a need for enhanced efficiency and innovation, potentially through reliable AI solutions. The ad-hoc use of general-purpose generative AI, such as ChatGPT, might become a common practice among newcomers and service providers to address this need. However, these tools are not tailored for the settlement domain and can have detrimental implications for immigrants and refugees. We explore the risks that these tools might pose on newcomers to first, warn against the unguarded use of generative AI, and second, to incentivize further research and development in creating AI literacy programs as well as customized LLMs that are aligned with the preferences of the impacted communities. Crucially, such technologies should be designed to integrate seamlessly into the existing workflow of the settlement sector, ensuring human oversight, trustworthiness, and accountability.