We propose in this paper, STANLEY, a STochastic gradient ANisotropic LangEvin dYnamics, for sampling high dimensional data. With the growing efficacy and potential of Energy-Based modeling, also known as non-normalized probabilistic modeling, for modeling a generative process of different natures of high dimensional data observations, we present an end-to-end learning algorithm for Energy-Based models (EBM) with the purpose of improving the quality of the resulting sampled data points. While the unknown normalizing constant of EBMs makes the training procedure intractable, resorting to Markov Chain Monte Carlo (MCMC) is in general a viable option. Realizing what MCMC entails for the EBM training, we propose in this paper, a novel high dimensional sampling method, based on an anisotropic stepsize and a gradient-informed covariance matrix, embedded into a discretized Langevin diffusion. We motivate the necessity for an anisotropic update of the negative samples in the Markov Chain by the nonlinearity of the backbone of the EBM, here a Convolutional Neural Network. Our resulting method, namely STANLEY, is an optimization algorithm for training Energy-Based models via our newly introduced MCMC method. We provide a theoretical understanding of our sampling scheme by proving that the sampler leads to a geometrically uniformly ergodic Markov Chain. Several image generation experiments are provided in our paper to show the effectiveness of our method.

If machine learning models were to achieve superhuman abilities at various reasoning or decision-making tasks, how would we go about evaluating such models, given that humans would necessarily be poor proxies for ground truth? In this paper, we propose a framework for evaluating superhuman models via consistency checks. Our premise is that while the correctness of superhuman decisions may be impossible to evaluate, we can still surface mistakes if the model's decisions fail to satisfy certain logical, human-interpretable rules. We instantiate our framework on three tasks where correctness of decisions is hard to evaluate due to either superhuman model abilities, or to otherwise missing ground truth: evaluating chess positions, forecasting future events, and making legal judgments. We show that regardless of a model's (possibly superhuman) performance on these tasks, we can discover logical inconsistencies in decision making. For example: a chess engine assigning opposing valuations to semantically identical boards; GPT-4 forecasting that sports records will evolve non-monotonically over time; or an AI judge assigning bail to a defendant only after we add a felony to their criminal record.

Recent approaches to word sense disambiguation (WSD) utilize encodings of the sense gloss (definition), in addition to the input context, to improve performance. In this work we demonstrate that this approach can be adapted for use in multiword expression (MWE) identification by training models which use gloss and context information to filter MWE candidates produced by a rule-based extraction pipeline. Our approach substantially improves precision, outperforming the state-of-the-art in MWE identification on the DiMSUM dataset by up to 1.9 F1 points and achieving competitive results on the PARSEME 1.1 English dataset. Our models also retain most of their WSD performance, showing that a single model can be used for both tasks. Finally, building on similar approaches using Bi-encoders for WSD, we introduce a novel Poly-encoder architecture which improves MWE identification performance.

Urban environments are intricate systems where the breakdown of critical infrastructure can impact both the economic and social well-being of communities. Electricity systems hold particular significance, as they are essential for other infrastructure, and disruptions can trigger widespread consequences. Typically, assessing electricity availability requires ground-level data, a challenge in conflict zones and regions with limited access. This study shows how satellite imagery, social media, and information extraction can monitor blackouts and their perceived causes. Night-time light data (in March 2019 for Caracas, Venezuela) is used to indicate blackout regions. Twitter data is used to determine sentiment and topic trends, while statistical analysis and topic modeling delved into public perceptions regarding blackout causes. The findings show an inverse relationship between nighttime light intensity. Tweets mentioning the Venezuelan President displayed heightened negativity and a greater prevalence of blame-related terms, suggesting a perception of government accountability for the outages.

Recently, we have proposed a framework for verification of agents' abilities in asynchronous multi-agent systems, together with an algorithm for automated reduction of models. The semantics was built on the modeling tradition of distributed systems. As we show here, this can sometimes lead to counterintuitive interpretation of formulas when reasoning about the outcome of strategies. First, the semantics disregards finite paths, and thus yields unnatural evaluation of strategies with deadlocks. Secondly, the semantic representations do not allow to capture the asymmetry between proactive agents and the recipients of their choices. We propose how to avoid the problems by a suitable extension of the representations and change of the execution semantics for asynchronous MAS. We also prove that the model reduction scheme still works in the modified framework.

There's much, much more to the rainforest than meets the eye. Even a highly trained observer can struggle to pick out individual animals in the tangle of plant life--animals that are often specifically adapted to hide from their enemies. Listen to the music of the forest, though, and you can get a decent idea of the species by their chirps, croaks, and grunts. This is why scientists are increasingly bugging rainforests with microphones--a burgeoning field known as bioacoustics--and using AI to automatically parse sounds to identify species. Writing today in the journal Nature Communications, researchers describe a proof-of-concept project in the lowland Chocó region of Ecuador that shows the potential power of bioacoustics in conserving forests.

Random Forest (RF) is a well-known data-driven algorithm applied in several fields thanks to its flexibility in modeling the relationship between the response variable and the predictors, also in case of strong non-linearities. In environmental applications, it often occurs that the phenomenon of interest may present spatial and/or temporal dependence that is not taken explicitly into account by RF in its standard version. In this work, we propose a taxonomy to classify strategies according to when (Pre-, In- and/or Post-processing) they try to include the spatial information into regression RF. Moreover, we provide a systematic review and classify the most recent strategies adopted to "adjust" regression RF to spatially dependent data, based on the criteria provided by the Preferred Reporting Items for Systematic reviews and Meta-Analysis (PRISMA). The latter consists of a reproducible methodology for collecting and processing existing literature on a specified topic from different sources. PRISMA starts with a query and ends with a set of scientific documents to review: we performed an online query on the 25$^{th}$ October 2022 and, in the end, 32 documents were considered for review. The employed methodological strategies and the application fields considered in the 32 scientific documents are described and discussed. This work falls inside the Agriculture Impact On Italian Air (AgrImOnIA) project.

Anomaly detection methods identify examples that do not follow the expected behaviour, typically in an unsupervised fashion, by assigning real-valued anomaly scores to the examples based on various heuristics. These scores need to be transformed into actual predictions by thresholding, so that the proportion of examples marked as anomalies equals the expected proportion of anomalies, called contamination factor. Unfortunately, there are no good methods for estimating the contamination factor itself. We address this need from a Bayesian perspective, introducing a method for estimating the posterior distribution of the contamination factor of a given unlabeled dataset. We leverage on outputs of several anomaly detectors as a representation that already captures the basic notion of anomalousness and estimate the contamination using a specific mixture formulation. Empirically on 22 datasets, we show that the estimated distribution is well-calibrated and that setting the threshold using the posterior mean improves the anomaly detectors' performance over several alternative methods. All code is publicly available for full reproducibility.

This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. Significant concerns emerge when addressing cultural sensitivity and local values. To address this, the paper proposes a comprehensive solution that includes further pre-training with Arabic texts, Supervised Fine-Tuning (SFT) utilizing native Arabic instructions, and GPT-4 responses in Arabic, alongside Reinforcement Learning with AI Feedback (RLAIF) employing a reward model attuned to local culture and values. The goal is to cultivate culturally cognizant and value-aligned Arabic LLMs capable of accommodating the diverse, application-specific needs of Arabic-speaking communities. Comprehensive evaluations reveal that the resulting model, dubbed 'AceGPT', sets the state-of-the-art standard for open Arabic LLMs across various benchmarks, including the instruction-following benchmark (i.e., Arabic Vicuna-80 and Arabic AlpacaEval), knowledge benchmark (i.e., Arabic MMLU and EXAMs), and the newly introduced Arabic Cultural and Value Alignment benchmark. Notably, AceGPT outperforms Turbo in the popular Vicuna-80 benchmark when evaluated with GPT-4, despite the benchmark's limited scale. Codes, data, and models are in https://github.com/FreedomIntelligence/AceGPT.

Advances in robotic automation, high-performance computing (HPC), and artificial intelligence (AI) encourage us to conceive of science factories: large, general-purpose computation- and AI-enabled self-driving laboratories (SDLs) with the generality and scale needed both to tackle large discovery problems and to support thousands of scientists. Science factories require modular hardware and software that can be replicated for scale and (re)configured to support many applications. To this end, we propose a prototype modular science factory architecture in which reconfigurable modules encapsulating scientific instruments are linked with manipulators to form workcells, that can themselves be combined to form larger assemblages, and linked with distributed computing for simulation, AI model training and inference, and related tasks. Workflows that perform sets of actions on modules can be specified, and various applications, comprising workflows plus associated computational and data manipulation steps, can be run concurrently. We report on our experiences prototyping this architecture and applying it in experiments involving 15 different robotic apparatus, five applications (one in education, two in biology, two in materials), and a variety of workflows, across four laboratories. We describe the reuse of modules, workcells, and workflows in different applications, the migration of applications between workcells, and the use of digital twins, and suggest directions for future work aimed at yet more generality and scalability. Code and data are available at https://ad-sdl.github.io/wei2023 and in the Supplementary Information