With the rapid development of artificial intelligence technology, especially the increasingly widespread application of question-and-answer systems, high-quality question generation has become a key component in supporting the development of these systems. This article focuses on knowledge-based question generation technology, which aims to enable computers to simulate the human questioning process based on understanding specific texts or knowledge bases. In light of the issues of hallucination and knowledge gaps present in large-scale language models when applied to knowledge-intensive tasks, this paper proposes an enhanced question generation method that incorporates contrastive learning. This method utilizes multiple models to jointly mine domain knowledge and uses contrastive learning to guide the model in reducing noise and hallucinations in generation. Experimental results show that by designing prompts containing contrasting examples, the model's performance in question generation improves considerably, particularly when contrasting instructions and examples are used simultaneously, leading to the highest quality of generated questions and improved accuracy. These results demonstrate that the method proposed in this study, which combines contrasting context and chain-of-thought prompts, can effectively improve both the quality and the practicality of question generation.

-- We present a new millimeter-scale bimorph actuator for microrobotic applications, driven by feedforward controlled shape-memory alloy (SMA) wires. The device weighs 10 mg, measures 14 mm in length, and occupies a volume of 4.8 mm The experimentally measured operational bandwidth is on the order of 20 Hz, and the unimorph and bimorph maximum low-frequency displacement outputs are on the order of 3.5 and 7 mm, respectively. T o test and demonstrate the functionality and suitability of the actuator for microrobotics, we developed the Fish-&-Ribbon-Inspired Small Swimming Harmonic roBot (FRISSHBot). Loosely inspired by carangiformes, the FRISSHBot leverages fluid-structure interaction (FSI) phenomena to propel itself forward, weighs 30 mg, measures 34 mm in length, operates at frequencies of up to 4 Hz, and swims at speeds of up to 3.06 mm s This robot is the lightest and smallest swimmer with onboard actuation developed to date. The vision of insect-scale robotic swarms working in harmony with humans to complete essential tasks for society will become a reality only once critical challenges in microfabrication, sensing, actuation, power, and computation are solved. One of these challenges is the creation of lightweight microactuators with low power consumption and versatile functionality. Numerous advanced and novel mm-to-cm-scale microsystems have been developed during the past few years using predominantly piezoelectric [1]-[8], electromagnetic [9]-[12], dielectric-elastomer (DE) [13]- [16], rotational motor [17]-[20], and shape-memory alloy (SMA) [21]-[25] actuation technologies. While, in the aggregate, these results represent innovation and progress in microrobotic design, rapid prototyping, control performance, autonomy, and energy efficiency, all the platforms presented in [1]-[20] are limited by the need for complex electronics and lack of sources of power with high energy densities. For obvious reasons, microactuators that require low operational power and simple electronics, generate high-force outputs, and exhibit high versatility are a superior choice for advanced autonomous microrobotics. One promising technological path in this direction is SMA-based actuation of the type presented in [21]-[25], which exhibits high-work densities (HWD) and requires low voltages of operation-- typically, 1 to 25 V.

Large Language Models have advanced clinical Natural Language Generation, creating opportunities to manage the volume of medical text. However, the high-stakes nature of medicine requires reliable evaluation, which remains a challenge. In this narrative review, we assess the current evaluation state for clinical summarization tasks and propose future directions to address the resource constraints of expert human evaluation.

The application of Shapley values to high-dimensional, time-series-like data is computationally challenging - and sometimes impossible. For $N$ inputs the problem is $2^N$ hard. In image processing, clusters of pixels, referred to as superpixels, are used to streamline computations. This research presents an efficient solution for time-seres-like data that adapts the idea of superpixels for Shapley value computation. Motivated by a forensic DNA classification example, the method is applied to multivariate time-series-like data whose features have been classified by a convolutional neural network (CNN). In DNA processing, it is important to identify alleles from the background noise created by DNA extraction and processing. A single DNA profile has $31,200$ scan points to classify, and the classification decisions must be defensible in a court of law. This means that classification is routinely performed by human readers - a monumental and time consuming process. The application of a CNN with fast computation of meaningful Shapley values provides a potential alternative to the classification. This research demonstrates the realistic, accurate and fast computation of Shapley values for this massive task

We study retrieving a set of documents that covers various perspectives on a complex and contentious question (e.g., will ChatGPT do more harm than good?). We curate a Benchmark for Retrieval Diversity for Subjective questions (BERDS), where each example consists of a question and diverse perspectives associated with the question, sourced from survey questions and debate websites. On this data, retrievers paired with a corpus are evaluated to surface a document set that contains diverse perspectives. Our framing diverges from most retrieval tasks in that document relevancy cannot be decided by simple string matches to references. Instead, we build a language model based automatic evaluator that decides whether each retrieved document contains a perspective. This allows us to evaluate the performance of three different types of corpus (Wikipedia, web snapshot, and corpus constructed on the fly with retrieved pages from the search engine) paired with retrievers. Retrieving diverse documents remains challenging, with the outputs from existing retrievers covering all perspectives on only 33.74% of the examples. We further study the impact of query expansion and diversity-focused reranking approaches and analyze retriever sycophancy. Together, we lay the foundation for future studies in retrieval diversity handling complex queries.

Accurately recognizing a revisited place is crucial for embodied agents to localize and navigate. This requires visual representations to be distinct, despite strong variations in camera viewpoint and scene appearance. Existing visual place recognition pipelines encode the "whole" image and search for matches. This poses a fundamental challenge in matching two images of the same place captured from different camera viewpoints: "the similarity of what overlaps can be dominated by the dissimilarity of what does not overlap". We address this by encoding and searching for "image segments" instead of the whole images. We propose to use open-set image segmentation to decompose an image into `meaningful' entities (i.e., things and stuff). This enables us to create a novel image representation as a collection of multiple overlapping subgraphs connecting a segment with its neighboring segments, dubbed SuperSegment. Furthermore, to efficiently encode these SuperSegments into compact vector representations, we propose a novel factorized representation of feature aggregation. We show that retrieving these partial representations leads to significantly higher recognition recall than the typical whole image based retrieval. Our segments-based approach, dubbed SegVLAD, sets a new state-of-the-art in place recognition on a diverse selection of benchmark datasets, while being applicable to both generic and task-specialized image encoders. Finally, we demonstrate the potential of our method to ``revisit anything'' by evaluating our method on an object instance retrieval task, which bridges the two disparate areas of research: visual place recognition and object-goal navigation, through their common aim of recognizing goal objects specific to a place. Source code: https://github.com/AnyLoc/Revisit-Anything.

Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized corpora. The deficiency can come from long-distance dependencies which are hard to capture by language models, and overfitting to co-occurrence patterns and distracting clues in the training text. To address these issues, the paper proposes a method to enhance knowledge learning during language model pretraining, by enhancing elusive but important clues in text discovered by the language model themselves. We found that larger language models pay more attention to non-obvious but important clues, which are often overlooked by smaller language models. Therefore, we can identify these clues by contrasting the attention weights of large and small language models. We use the identified clues as a guide to perform token-dropout data augmentation on the training text, and observed a significant boost in both small and large models' performance in fact memorization. This shows that the behavior contrast between more and less-performant language models contains important clues for knowledge learning, and it can be ``amplified" for a straight-forward improvement in knowledge learning efficiency.

Most recommender systems adopt collaborative filtering (CF) and provide recommendations based on past collective interactions. Therefore, the performance of CF algorithms degrades when few or no interactions are available, a scenario referred to as cold-start. To address this issue, previous work relies on models leveraging both collaborative data and side information on the users or items. Similar to multimodal learning, these models aim at combining collaborative and content representations in a shared embedding space. In this work we propose a novel technique for multimodal recommendation, relying on a multimodal Single-Branch embedding network for Recommendation (SiBraR). Leveraging weight-sharing, SiBraR encodes interaction data as well as multimodal side information using the same single-branch embedding network on different modalities. This makes SiBraR effective in scenarios of missing modality, including cold start. Our extensive experiments on large-scale recommendation datasets from three different recommendation domains (music, movie, and e-commerce) and providing multimodal content information (audio, text, image, labels, and interactions) show that SiBraR significantly outperforms CF as well as state-of-the-art content-based RSs in cold-start scenarios, and is competitive in warm scenarios. We show that SiBraR's recommendations are accurate in missing modality scenarios, and that the model is able to map different modalities to the same region of the shared embedding space, hence reducing the modality gap.

Predicting hospital length of stay (LoS) stands as a critical factor in shaping public health strategies. This data serves as a cornerstone for governments to discern trends, patterns, and avenues for enhancing healthcare delivery. In this study, we introduce a robust hybrid deep learning model, a combination of Multi-layer Convolutional (CNNs) deep learning, Gated Recurrent Units (GRU), and Dense neural networks, that outperforms 11 conventional and state-of-the-art Machine Learning (ML) and Deep Learning (DL) methodologies in accurately forecasting inpatient hospital stay duration. Our investigation delves into the implementation of this hybrid model, scrutinising variables like geographic indicators tied to caregiving institutions, demographic markers encompassing patient ethnicity, race, and age, as well as medical attributes such as the CCS diagnosis code, APR DRG code, illness severity metrics, and hospital stay duration. Statistical evaluations reveal the pinnacle LoS accuracy achieved by our proposed model (CNN-GRU-DNN), which averages at 89% across a 10-fold cross-validation test, surpassing LSTM, BiLSTM, GRU, and Convolutional Neural Networks (CNNs) by 19%, 18.2%, 18.6%, and 7%, respectively. Accurate LoS predictions not only empower hospitals to optimise resource allocation and curb expenses associated with prolonged stays but also pave the way for novel strategies in hospital stay management. This avenue holds promise for catalysing advancements in healthcare research and innovation, inspiring a new era of precision-driven healthcare practices.

Federated Learning (FL) has emerged as a machine learning approach able to preserve the privacy of user's data. Applying FL, clients train machine learning models on a local dataset and a central server aggregates the learned parameters coming from the clients, training a global machine learning model without sharing user's data. However, the state-of-the-art shows several approaches to promote attacks on FL systems. For instance, inverting or leaking gradient attacks can find, with high precision, the local dataset used during the training phase of the FL. This paper presents an approach, called Deep Leakage from Gradients with Feedback Blending (DLG-FB), which is able to improve the inverting gradient attack, considering the spatial correlation that typically exists in batches of images. The performed evaluation shows an improvement of 19.18% and 48,82% in terms of attack success rate and the number of iterations per attacked image, respectively.