Throughout history many traditions have believed that some fatal flaw in human nature tempts us to pursue powers we don't know how to handle. The Greek myth of Phaethon told of a boy who discovers that he is the son of Helios, the sun god. Wishing to prove his divine origin, Phaethon demands the privilege of driving the chariot of the sun. Helios warns Phaethon that no human can control the celestial horses that pull the solar chariot. But Phaethon insists, until the sun god relents. After rising proudly in the sky, Phaethon indeed loses control of the chariot. The sun veers off course, scorching all vegetation, killing numerous beings and threatening to burn the Earth itself. The gods reassert control of the sky and save the world. Two thousand years later, when the Industrial Revolution was making its first steps and machines began replacing humans in numerous tasks, Johann Wolfgang von Goethe published a similar cautionary tale titled The Sorcerer's Apprentice. Goethe's poem (later popularised as a Walt Disney animation starring Mickey Mouse) tells of an old sorcerer who leaves a young apprentice in charge of his workshop and gives him some chores to tend to while he is gone, such as fetching water from the river. The apprentice decides to make things easier for himself and, using one of the sorcerer's spells, enchants a broom to fetch the water for him.

Even though federated learning's potential to overcome Case-based interpretability is vital in explaining medical some of the current AI flaws is currently widely recognized, Artificial Intelligence (AI) model decisions. Generating it also introduces new challenges. The decentralized nature explanations for AI model decisions is paramount to increasing of federated learning guarantees compliance with privacy trust and allowing widespread adoption in clinical regulations but, at the same time, inhibits data access and practice [1]. We can find several approaches to producing inspection [7]. Non-accessible data means that identifying explanations in the scientific literature, from saliency maps bugs or detecting biases is impossible following conventional (highlighting image pixels driving the decision) to textual approaches. The same is true for case-based explainability.

Sign language translation has historically been peripheral to mainstream machine translation research. In order to help converge the fields, we introduce FLEURS-ASL, an extension of the multiway parallel benchmarks FLORES (for text) and FLEURS (for speech) to support their first sign language (as video), American Sign Language, translated by 5 Certified Deaf Interpreters. FLEURS-ASL can be used to evaluate a variety of tasks -- primarily sentence- and discourse-level translation -- between ASL and 200 other languages as text, or 102 languages as speech. We provide baselines for tasks from ASL to English text using a unified modeling approach that incorporates timestamp tokens and previous text tokens in a 34-second context window, trained on random video clips from YouTube-ASL. This model meets or exceeds the performance of phrase-level baselines while supporting a multitude of new tasks. We also use FLEURS-ASL to show that multimodal frontier models have virtually no understanding of ASL, underscoring the importance of including sign languages in standard evaluation suites.

Biases inherent in human endeavors pose significant challenges for machine learning, particularly in supervised learning that relies on potentially biased "ground truth" data. This reliance, coupled with models' tendency to generalize based on statistical maximal likelihood, can propagate and amplify biases, exacerbating societal issues. To address this, our study proposes a reflective methodology utilizing multiple Large Language Models (LLMs) engaged in a dynamic dialogue to uncover diverse perspectives. By leveraging conditional statistics, information theory, and divergence metrics, this novel approach fosters context-dependent linguistic behaviors, promoting unbiased outputs. Furthermore, it enables measurable progress tracking and explainable remediation actions to address identified biases.

This paper presents the VLEIBot^* (Very Little Eel-Inspired roBot), a 45-mg/23-mm^3 microrobotic swimmer that is propelled by a bioinspired anguilliform propulsor. The propulsor is excited by a single 6-mg high-work-density (HWD) microactuator and undulates periodically due to wave propagation phenomena generated by fluid-structure interaction (FSI) during swimming. The microactuator is composed of a carbon-fiber beam, which functions as a leaf spring, and shape-memory alloy (SMA) wires, which deform cyclically when excited periodically using Joule heating. The VLEIBot can swim at speeds as high as 15.1mm * s^{-1} (0.33 Bl * s^{-1}}) when driven with a heuristically-optimized propulsor. To improve maneuverability, we evolved the VLEIBot design into the 90-mg/47-mm^3 VLEIBot^+, which is driven by two propulsors and fully controllable in the two-dimensional (2D) space. The VLEIBot^+ can swim at speeds as high as 16.1mm * s^{-1} (0.35 Bl * s^{-1}), when driven with heuristically-optimized propulsors, and achieves turning rates as high as 0.28 rad * s^{-1}, when tracking path references. The measured root-mean-square (RMS) values of the tracking errors are as low as 4 mm.

Research on Life Cycle Assessment (LCA) is being conducted in various sectors, from analyzing building materials and components to comprehensive evaluations of entire structures. However, reviews of the existing literature have been unable to provide a comprehensive overview of research in this field, leaving scholars without a definitive guideline for future investigations. This paper aims to fill this gap, mapping more than twenty years of research. Using an innovative methodology that combines social network analysis and text mining, the paper examined 8024 scientific abstracts. The authors identified seven key thematic groups, building and sustainability clusters (BSCs). To assess their significance in the broader discourse on building and sustainability, the semantic brand score (SBS) indicator was applied. Additionally, building and sustainability trends were tracked, focusing on the LCA concept. The major research topics mainly relate to building materials and energy efficiency. In addition to presenting an innovative approach to reviewing extensive literature domains, the article also provides insights into emerging and underdeveloped themes, outlining crucial future research directions.

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency in both storage and computation. Additionally, prompting modifies only the LM's inputs and harnesses the generative capabilities of language models to address various downstream tasks in a unified manner. This significantly reduces the need for human labor in designing task-specific models. These advantages become even more evident as the number of tasks served by the LM scales up. Motivated by the strengths of prompting, we are the first to explore the potential of prompting speech LMs in the domain of speech processing. Recently, there has been a growing interest in converting speech into discrete units for language modeling. Our pioneer research demonstrates that these quantized speech units are highly versatile within our unified prompting framework. Not only can they serve as class labels, but they also contain rich phonetic information that can be re-synthesized back into speech signals for speech generation tasks. Specifically, we reformulate speech processing tasks into speech-to-unit generation tasks. As a result, we can seamlessly integrate tasks such as speech classification, sequence generation, and speech generation within a single, unified prompting framework. The experiment results show that the prompting method can achieve competitive performance compared to the strong fine-tuning method based on self-supervised learning models with a similar number of trainable parameters. The prompting method also shows promising results in the few-shot setting. Moreover, with the advanced speech LMs coming into the stage, the proposed prompting framework attains great potential.

The Airbnb search system grapples with many unique challenges as it continues to evolve. We oversee a marketplace that is nuanced by geography, diversity of homes, and guests with a variety of preferences. Crafting an efficient search system that can accommodate diverse guest needs, while showcasing relevant homes lies at the heart of Airbnb's success. Airbnb search has many challenges that parallel other recommendation and search systems but it has a unique information retrieval problem, upstream of ranking, called location retrieval. It requires defining a topological map area that is relevant to the searched query for homes listing retrieval. The purpose of this paper is to demonstrate the methodology, challenges, and impact of building a machine learning based location retrieval product from the ground up. Despite the lack of suitable, prevalent machine learning based approaches, we tackle cold start, generalization, differentiation and algorithmic bias. We detail the efficacy of heuristics, statistics, machine learning, and reinforcement learning approaches to solve these challenges, particularly for systems that are often unexplored by current literature.

A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS model with robustness under different acoustic environments. In this paper, we explore how to effectively apply adversarial examples to improve KWS robustness. We propose datasource-aware disentangled learning with adversarial examples to reduce the mismatch between the original and adversarial data as well as the mismatch across original training datasources. The KWS model architecture is based on depth-wise separable convolution and a simple attention module. Experimental results demonstrate that the proposed learning strategy improves false reject rate by $40.31%$ at $1%$ false accept rate on the internal dataset, compared to the strongest baseline without using adversarial examples. Our best-performing system achieves $98.06%$ accuracy on the Google Speech Commands V1 dataset.

Large Language Models have undoubtedly revolutionized the Natural Language Processing field, the current trend being to promote one-model-for-all tasks (sentiment analysis, translation, etc.). However, the statistical mechanisms at work in the larger language models struggle to exploit the relevant information when it is very sparse, when it is a weak signal. This is the case, for example, for the classification of long domain-specific documents, when the relevance relies on a single relevant word or on very few relevant words from technical jargon. In the medical domain, it is essential to determine whether a given report contains critical information about a patient's condition. This critical information is often based on one or few specific isolated terms. In this paper, we propose a hierarchical model which exploits a short list of potential target terms to retrieve candidate sentences and represent them into the contextualized embedding of the target term(s) they contain. A pooling of the term(s) embedding(s) entails the document representation to be classified. We evaluate our model on one public medical document benchmark in English and on one private French medical dataset. We show that our narrower hierarchical model is better than larger language models for retrieving relevant long documents in a domain-specific context.