Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require LLMs to understand user queries, retrieve relevant information, and synthesize coherent and accurate responses. Given the increasing real-world deployment of such systems, comprehensive evaluation becomes crucial. To this end, we propose FRAMES (Factuality, Retrieval, And reasoning MEasurement Set), a high-quality evaluation dataset designed to test LLMs' ability to provide factual responses, assess retrieval capabilities, and evaluate the reasoning required to generate final answers. While previous work has provided datasets and benchmarks to evaluate these abilities in isolation, FRAMES offers a unified framework that provides a clearer picture of LLM performance in end-to-end RAG scenarios. Our dataset comprises challenging multi-hop questions that require the integration of information from multiple sources. The accuracy is significantly improved with our proposed multi-step retrieval pipeline, achieving an accuracy of 0.66 (>50% improvement). We hope our work will help bridge evaluation gaps and assist in developing more robust and capable RAG systems.

Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechanism. The inference consists of prefilling and decoding phases. Although several attempts have been made to accelerate decoding, the inefficiency of the prefilling phase, especially for long-context tasks, remains a challenge. In this paper, we observe a locality in query criticality during the prefilling phase of long-context processing: adjacent query tokens tend to focus on similar subsets of the past Key-Value (KV) cache. Based on this observation, we propose CritiPrefill, a criticality-based segment-wise prefilling method. This method partitions the input sequence's queries and KV cache into segments and blocks, utilizing a segment-wise algorithm to estimate the query criticality. By pruning non-critical computations between query segments and cache blocks in the self-attention mechanism, the prefilling process can be significantly accelerated. Extensive evaluations on multiple long-context datasets show up to 2.7x speedup on Llama3-8B and 3.0x speedup on Yi-9B for 128K context length on a single A100 GPU, with minimal quality degradation.

Graph signal processing deals with algorithms and signal representations that leverage graph structures for multivariate data analysis. Often said graph topology is not readily available and may be time-varying, hence (dynamic) graph structure learning from nodal (e.g., sensor) observations becomes a critical first step. In this paper, we develop a novel algorithm for online graph learning using observation streams, assumed to be smooth on the latent graph. Unlike batch algorithms for topology identification from smooth signals, our modus operandi is to process graph signals sequentially and thus keep memory and computational costs in check. To solve the resulting smoothness-regularized, time-varying inverse problem, we develop online and lightweight iterations built upon the proximal variant of the alternating direction method of multipliers (ADMM), well known for its fast convergence in batch settings. The proximal term in the topology updates seamlessly implements a temporal-variation regularization, and we argue the online procedure exhibits sublinear static regret under some simplifying assumptions. Reproducible experiments with synthetic and real graphs demonstrate the effectiveness of our method in adapting to streaming signals and tracking slowly-varying network connectivity. The proposed approach also exhibits better tracking performance (in terms of suboptimality), when compared to state-of-the-art online graph learning baselines.

Automatic disease diagnosis has become increasingly valuable in clinical practice. The advent of large language models (LLMs) has catalyzed a paradigm shift in artificial intelligence, with growing evidence supporting the efficacy of LLMs in diagnostic tasks. Despite the increasing attention in this field, a holistic view is still lacking. Many critical aspects remain unclear, such as the diseases and clinical data to which LLMs have been applied, the LLM techniques employed, and the evaluation methods used. In this article, we perform a comprehensive review of LLM-based methods for disease diagnosis. Our review examines the existing literature across various dimensions, including disease types and associated clinical specialties, clinical data, LLM techniques, and evaluation methods. Additionally, we offer recommendations for applying and evaluating LLMs for diagnostic tasks. Furthermore, we assess the limitations of current research and discuss future directions. To our knowledge, this is the first comprehensive review for LLM-based disease diagnosis.

Multibeam echo-sounder (MBES) is the de-facto sensor for bathymetry mapping. In recent years, cheaper MBES sensors and global mapping initiatives have led to exponential growth of available data. However, raw MBES data contains 1-25% of noise that requires semi-automatic filtering using tools such as Combined Uncertainty and Bathymetric Estimator (CUBE). In this work, we draw inspirations from the 3D point cloud community and adapted a score-based point cloud denoising network for MBES outlier detection and denoising. We trained and evaluated this network on real MBES survey data. The proposed method was found to outperform classical methods, and can be readily integrated into existing MBES standard workflow. To facilitate future research, the code and pretrained model are available online.

Generative AI has shown its values for many software engineering tasks. Still in its infancy, large language model (LLM)-based proof generation lags behind LLM-based code generation. In this paper, we present AutoVerus. AutoVerus uses LLM to automatically generate correctness proof for Rust code. AutoVerus is designed to match the unique features of Verus, a verification tool that can prove the correctness of Rust code using proofs and specifications also written in Rust. AutoVerus consists of a network of LLM agents that are crafted and orchestrated to mimic human experts' three phases of proof construction: preliminary proof generation, proof refinement guided by generic tips, and proof debugging guided by verification errors. To thoroughly evaluate AutoVerus and help foster future research in this direction, we have built a benchmark suite of 150 non-trivial proof tasks, based on existing code-generation benchmarks and verification benchmarks. Our evaluation shows that AutoVerus can automatically generate correct proof for more than 90% of them, with more than half of them tackled in less than 30 seconds or 3 LLM calls.

Ultrasound is a hand-held, low-cost, non-invasive medical imaging modality which plays a vital role in diagnosing various diseases. Despite this, many rural and remote communities do not have access to ultrasound scans due to the lack of local experts trained to perform them. To address this challenge, we built a mixed reality and haptics-based tele-ultrasound system to enable an expert to precisely guide a novice remotely in carrying out an ultrasound exam. The precision and flexibility of our solution makes it more practical than existing tele-ultrasound solutions. We tested the system in Skidegate on the islands of Haida Gwaii, BC, Canada, with the experts positioned 754 km away at the University of British Columbia, Vancouver, Canada. We performed 11 scans with 10 novices and 2 experts. The experts were tasked with acquiring 5 target images and measurements in the epigastric region. The novices of various backgrounds and ages were all inexperienced in mixed reality and were not required to have prior ultrasound experience. The captured images were evaluated by two radiologists who were not present for the tests. These results are discussed along with new insights into the human computer interaction in such a system. We show that human teleoperation is feasible and can achieve high performance for completing remote ultrasound procedures, even at a large distance and with completely novice followers.

Soccer attracts the attention of many researchers and professionals in the sports industry. Therefore, the incorporation of science into the sport is constantly growing, with increasing investments in performance analysis and sports prediction industries. This study aims to (i) highlight the use of complex networks as an alternative tool for predicting soccer match outcomes, and (ii) show how the combination of structural analysis of passing networks with match statistical data can provide deeper insights into the game patterns and strategies used by teams. In order to do so, complex network metrics and match statistics were used to build machine learning models that predict the wins and losses of soccer teams in different leagues. The results showed that models based on passing networks were as effective as ``traditional'' models, which use general match statistics. Another finding was that by combining both approaches, more accurate models were obtained than when they were used separately, demonstrating that the fusion of such approaches can offer a deeper understanding of game patterns, allowing the comprehension of tactics employed by teams relationships between players, their positions, and interactions during matches. It is worth mentioning that both network metrics and match statistics were important and impactful for the mixed model. Furthermore, the use of networks with a lower granularity of temporal evolution (such as creating a network for each half of the match) performed better than a single network for the entire game.

After 25 years as a pediatric infectious diseases specialist, Asunción Mejías is too familiar with the deadly unpredictability of respiratory syncytial virus (RSV), an infection that hospitalizes up to 80,000 children under the age of 5 every year in the US. "It's a disease which can change very quickly," says Mejías, who works at St. Jude Children's Research Hospital in Memphis, Tennessee. "I've always told my colleagues that for every two children that are admitted, one can go to the ICU in the next three hours and the other one may go home the next day. RSV infections are very common, to the point that nearly every child will have one before they turn 2 years old. Most children experience symptoms similar to a cold, like coughing and sneezing, but some can develop severe lung disease: RSV is responsible for more than 100,000 infant deaths globally every year, nearly half of which are in babies under 6 months of age.

Many users are confronted multiple times daily with the choice of whether to take the stairs or the elevator. Whereas taking the stairs could be beneficial for cardiovascular health and wellness, taking the elevator might be more convenient but it also consumes energy. By precisely tracking and boosting users' stairs and elevator usage through their wearable, users might gain health insights and motivation, encouraging a healthy lifestyle and lowering the risk of sedentary-related health problems. This research describes a new exploratory dataset, to examine the patterns and behaviors related to using stairs and lifts. We collected data from 20 participants while climbing and descending stairs and taking a lift in a variety of scenarios. The aim is to provide insights and demonstrate the practicality of using wearable sensor data for such a scenario. Our collected dataset was used to train and test a Random Forest machine learning model, and the results show that our method is highly accurate at classifying stair and lift operations with an accuracy of 87.61% and a multi-class weighted F1-score of 87.56% over 8-second time windows. Furthermore, we investigate the effect of various types of sensors and data attributes on the model's performance. Our findings show that combining inertial and pressure sensors yields a viable solution for real-time activity detection.