Large Language Models (LLMs) and their multimodal extensions are becoming increasingly popular. One common approach to enable multimodality is to cascade domain-specific encoders with an LLM, making the resulting model inherit vulnerabilities from all of its components. In this work, we present the first systematic study of audio backdoor attacks against speech language models. We demonstrate its effectiveness across four speech encoders and three datasets, covering four tasks: automatic speech recognition (ASR), speech emotion recognition, and gender and age prediction. The attack consistently achieves high success rates, ranging from 90.76% to 99.41%. To better understand how backdoors propagate, we conduct a component-wise analysis to identify the most vulnerable stages of the pipeline. Finally, we propose a fine-tuning-based defense that mitigates the threat of poisoned pretrained encoders.

We present GEOPARD, a transformer-based architecture for predicting articulation from a single static snapshot of a 3D shape. The key idea of our method is a pretraining strategy that allows our transformer to learn plausible candidate articulations for 3D shapes based on a geometric-driven search without manual articulation annotation. The search automatically discovers physically valid part motions that do not cause detachments or collisions with other shape parts. Our experiments indicate that this geometric pretraining strategy, along with carefully designed choices in our transformer architecture, yields state-of-the-art results in articulation inference in the PartNet-Mobility dataset.

Monocular facial performance capture in-the-wild is challenging due to varied capture conditions, face shapes, and expressions. Most current methods rely on linear 3D Morphable Models, which represent facial expressions independently of identity at the vertex displacement level. We propose SEREP (Semantic Expression Representation), a model that disentangles expression from identity at the semantic level. We start by learning an expression representation from high-quality 3D data of unpaired facial expressions. Then, we train a model to predict expression from monocular images relying on a novel semi-supervised scheme using low quality synthetic data. In addition, we introduce MultiREX, a benchmark addressing the lack of evaluation resources for the expression capture task. Our experiments show that SEREP outperforms state-of-the-art methods, capturing challenging expressions and transferring them to new identities.

Existing graphical user interfaces for circuit simulators often show small visual summaries of the reduced state of each qubit, showing the probability, phase, purity, and/or Bloch sphere coordinates associated with each qubit. These necessarily provide an incomplete picture of the quantum state of the qubits, and can sometimes be confusing for students or newcomers to quantum computing. We contribute two novel visual approaches to provide more complete information about small circuits. First, to complement information about each qubit, we show the complete state vector, and illustrate the way that amplitudes change from layer-to-layer under the effect of different gates, by using a small set of colors, arrows, and symbols. We call this ``state vector difference highlighting'', and show how it elucidates the effect of Hadamard, X, Y, Z, S, T, Phase, and SWAP gates, where each gate may have an arbitrary combination of control and anticontrol qubits. Second, we display pairwise information about qubits (such as concurrence and correlation) in a triangular ``half-matrix'' visualization. Our open source software implementation, called MuqcsCraft, is available as a live online demonstration that runs in a web browser without installing any additional software, allowing a user to define a circuit through drag-and-drop actions, and then simulate and visualize it.

The proliferation of demanding applications and edge computing establishes the need for an efficient management of the underlying computing infrastructures, urging the providers to rethink their operational methods. In this paper, we propose an Intelligent Proactive Fault Tolerance (IPFT) method that leverages the edge resource usage predictions through Recurrent Neural Networks (RNN). More specifically, we focus on the process-faults, which are related with the inability of the infrastructure to provide Quality of Service (QoS) in acceptable ranges due to the lack of processing power. In order to tackle this challenge we propose a composite deep learning architecture that predicts the resource usage metrics of the edge nodes and triggers proactive node replications and task migration. Taking also into consideration that the edge computing infrastructure is also highly dynamic and heterogeneous, we propose an innovative Hybrid Bayesian Evolution Strategy (HBES) algorithm for automated adaptation of the resource usage models. The proposed resource usage prediction mechanism has been experimentally evaluated and compared with other state of the art methods with significant improvements in terms of Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Additionally, the IPFT mechanism that leverages the resource usage predictions has been evaluated in an extensive simulation in CloudSim Plus and the results show significant improvement compared to the reactive fault tolerance method in terms of reliability and maintainability.

Machine learning and Large language models (LLMs) for vulnerability detection has received significant attention in recent years. Unfortunately, state-of-the-art techniques show that LLMs are unsuccessful in even distinguishing the vulnerable function from its benign counterpart, due to three main problems: Vulnerability detection requires deep analysis, which LLMs often struggle with when making a one-shot prediction. Existing techniques typically perform function-level analysis, whereas effective vulnerability detection requires contextual information beyond the function scope. The focus on binary classification can result in identifying a vulnerability but associating it with the wrong security weaknesses (CWE), which may mislead developers. We propose a novel multi-agent LLM approach to address the challenges of identifying CWEs. This approach consists of three steps: (1) a team of LLM agents performs an exhaustive search for potential CWEs in the function under review, (2) another team of agents identifies relevant external context to support or refute each candidate CWE, and (3) a final agent makes informed acceptance or rejection decisions for each CWE based on the gathered context. A preliminary evaluation of our approach shows promising results. In the PrimeVul dataset, Step 1 correctly identifies the appropriate CWE in 40.9\% of the studied vulnerable functions. We further evaluated the full pipeline on ten synthetic programs and found that incorporating context information significantly reduced false positives from 6 to 9 CWEs to just 1 to 2, while still correctly identifying the true CWE in 9 out of 10 cases.

Artificial intelligence (AI) continues to transform data analysis in many domains. Progress in each domain is driven by a growing body of annotated data, increased computational resources, and technological innovations. In medicine, the sensitivity of the data, the complexity of the tasks, the potentially high stakes, and a requirement of accountability give rise to a particular set of challenges. In this review, we focus on three key methodological approaches that address some of the particular challenges in AI-driven medical decision making. (1) Explainable AI aims to produce a human-interpretable justification for each output. Such models increase confidence if the results appear plausible and match the clinicians expectations. However, the absence of a plausible explanation does not imply an inaccurate model. Especially in highly non-linear, complex models that are tuned to maximize accuracy, such interpretable representations only reflect a small portion of the justification. (2) Domain adaptation and transfer learning enable AI models to be trained and applied across multiple domains. For example, a classification task based on images acquired on different acquisition hardware. (3) Federated learning enables learning large-scale models without exposing sensitive personal health information. Unlike centralized AI learning, where the centralized learning machine has access to the entire training data, the federated learning process iteratively updates models across multiple sites by exchanging only parameter updates, not personal health data. This narrative review covers the basic concepts, highlights relevant corner-stone and state-of-the-art research in the field, and discusses perspectives.

Usually, programming languages have official documentation to guide developers with APIs, methods, and classes. However, researchers identified insufficient or inadequate documentation examples and flaws with the API's complex structure as barriers to learning an API. As a result, developers may consult other sources (StackOverflow, GitHub, etc.) to learn more about an API. Recent research studies have shown that unofficial documentation is a valuable source of information for generating code summaries. We, therefore, have been motivated to leverage such a type of documentation along with deep learning techniques towards generating high-quality summaries for APIs discussed in informal documentation. This paper proposes an automatic approach using the BART algorithm, a state-of-the-art transformer model, to generate summaries for APIs discussed in StackOverflow. We built an oracle of human-generated summaries to evaluate our approach against it using ROUGE and BLEU metrics which are the most widely used evaluation metrics in text summarization. Furthermore, we evaluated our summaries empirically against a previous work in terms of quality. Our findings demonstrate that using deep learning algorithms can improve summaries' quality and outperform the previous work by an average of %57 for Precision, %66 for Recall, and %61 for F-measure, and it runs 4.4 times faster.

Our research investigates the recommendation of code examples to aid software developers, a practice that saves developers significant time by providing ready-to-use code snippets. The focus of our study is Stack Overflow, a commonly used resource for coding discussions and solutions, particularly in the context of the Java programming language. We applied BERT, a powerful Large Language Model (LLM) that enables us to transform code examples into numerical vectors by extracting their semantic information. Once these numerical representations are prepared, we identify Approximate Nearest Neighbors (ANN) using Locality-Sensitive Hashing (LSH). Our research employed two variants of LSH: Random Hyperplane-based LSH and Query-Aware LSH. We rigorously compared these two approaches across four parameters: HitRate, Mean Reciprocal Rank (MRR), Average Execution Time, and Relevance. Our study revealed that the Query-Aware (QA) approach showed superior performance over the Random Hyperplane-based (RH) method. Specifically, it exhibited a notable improvement of 20\% to 35\% in HitRate for query pairs compared to the RH approach. Furthermore, the QA approach proved significantly more time-efficient, with its speed in creating hashing tables and assigning data samples to buckets being at least four times faster. It can return code examples within milliseconds, whereas the RH approach typically requires several seconds to recommend code examples. Due to the superior performance of the QA approach, we tested it against PostFinder and FaCoY, the state-of-the-art baselines. Our QA method showed comparable efficiency proving its potential for effective code recommendation.

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance drops when the trained model is used in new data sets. Domain adaptation (DA) is a machine learning technique that aims to address this problem by reducing the differences between domains. This paper presents simulation-based algorithms of recent DA techniques, mainly related to unsupervised domain adaptation (UDA), where labels are available only in the source domain. Our study compares these techniques with public data sets and diverse characteristics, highlighting their respective strengths and drawbacks. For example, Safe Self-Refinement for Transformer-based DA (SSRT) achieved the highest accuracy (91.6\%) in the office-31 data set during our simulations, however, the accuracy dropped to 72.4\% in the Office-Home data set when using limited batch sizes. In addition to improving the reader's comprehension of recent techniques in DA, our study also highlights challenges and upcoming directions for research in this domain. The codes are available at this https URL

Domain adaptation (DA) techniques have the potential in machine learning to alleviate distribution differences between training and test sets by leveraging information from source domains. In image classification, most advances in DA have been made using natural images rather than medical data, which are harder to work with. Moreover, even for natural images, the use of mainstream datasets can lead to performance bias. {With the aim of better understanding the benefits of DA for both natural and medical images, this study performs 557 simulation studies using seven widely-used DA techniques for image classification in five natural and eight medical datasets that cover various scenarios, such as out-of-distribution, dynamic data streams, and limited training samples.} Our experiments yield detailed results and insightful observations highlighting the performance and medical applicability of these techniques. Notably, our results have shown the outstanding performance of the Deep Subdomain Adaptation Network (DSAN) algorithm. This algorithm achieved feasible classification accuracy (91.2\%) in the COVID-19 dataset using Resnet50 and showed an important accuracy improvement in the dynamic data stream DA scenario (+6.7\%) compared to the baseline. Our results also demonstrate that DSAN exhibits remarkable level of explainability when evaluated on COVID-19 and skin cancer datasets. These results contribute to the understanding of DA techniques and offer valuable insight into the effective adaptation of models to medical data.

Much research in recent years has focused on using empirical machine learning approaches to extract useful insights on the structure-property relationships of superconductor material. Notably, these approaches are bringing extreme benefits when superconductivity data often come from costly and arduously experimental work. However, this assessment cannot be based solely on an open black-box machine learning, which is not fully interpretable, because it can be counter-intuitive to understand why the model may give an appropriate response to a set of input data for superconductivity characteristic analyses, e.g., critical temperature. The purpose of this study is to describe and examine an alternative approach for predicting the superconducting transition temperature $T_c$ from SuperCon database obtained by Japan's National Institute for Materials Science. We address a generative machine-learning framework called Variational Bayesian Neural Network using superconductors chemical elements and formula to predict $T_c$. In such a context, the importance of the paper in focus is twofold. First, to improve the interpretability, we adopt a variational inference to approximate the distribution in latent parameter space for the generative model. It statistically captures the mutual correlation of superconductor compounds and; then, gives the estimation for the $T_c$. Second, a stochastic optimization algorithm, which embraces a statistical inference named Monte Carlo sampler, is utilized to optimally approximate the proposed inference model, ultimately determine and evaluate the predictive performance.

The use of deep learning (DL) in medical image analysis has significantly improved the ability to predict lung cancer. In this study, we introduce a novel deep convolutional neural network (CNN) model, named ResNet+, which is based on the established ResNet framework. This model is specifically designed to improve the prediction of lung cancer and diseases using the images. To address the challenge of missing feature information that occurs during the downsampling process in CNNs, we integrate the ResNet-D module, a variant designed to enhance feature extraction capabilities by modifying the downsampling layers, into the traditional ResNet model. Furthermore, a convolutional attention module was incorporated into the bottleneck layers to enhance model generalization by allowing the network to focus on relevant regions of the input images. We evaluated the proposed model using five public datasets, comprising lung cancer (LC2500 $n$=3183, IQ-OTH/NCCD $n$=1336, and LCC $n$=25000 images) and lung disease (ChestXray $n$=5856, and COVIDx-CT $n$=425024 images). To address class imbalance, we used data augmentation techniques to artificially increase the representation of underrepresented classes in the training dataset. The experimental results show that ResNet+ model demonstrated remarkable accuracy/F1, reaching 98.14/98.14\% on the LC25000 dataset and 99.25/99.13\% on the IQ-OTH/NCCD dataset. Furthermore, the ResNet+ model saved computational cost compared to the original ResNet series in predicting lung cancer images. The proposed model outperformed the baseline models on publicly available datasets, achieving better performance metrics. Our codes are publicly available at this https URL.

Despite the remarkable performance of vision language models (VLMs) such as Contrastive Language Image Pre-training (CLIP), the large size of these models is a considerable obstacle to their use in federated learning (FL) systems where the parameters of local client models need to be transferred to a global server for aggregation. Another challenge in FL is the heterogeneity of data from different clients, which affects the generalization performance of the solution. In addition, natural pre-trained VLMs exhibit poor generalization ability in the medical datasets, suggests there exists a domain gap. To solve these issues, we introduce a novel method for the Federated Adversarial Adaptation (FAA) of CLIP. Our method, named FAA-CLIP, handles the large communication costs of CLIP using a light-weight feature adaptation module (FAM) for aggregation, effectively adapting this VLM to each client's data while greatly reducing the number of parameters to transfer. By keeping CLIP frozen and only updating the FAM parameters, our method is also computationally efficient. Unlike existing approaches, our FAA-CLIP method directly addresses the problem of domain shifts across clients via a domain adaptation (DA) module. This module employs a domain classifier to predict if a given sample is from the local client or the global server, allowing the model to learn domain-invariant representations. Extensive experiments on six different datasets containing both natural and medical images demonstrate that FAA-CLIP can generalize well on both natural and medical datasets compared to recent FL approaches. Our codes are available at this https URL

The development of vision-language models (VLMs) for histo-pathology has shown promising new usages and zero-shot performances. However, current approaches, which decompose large slides into smaller patches, focus solely on inductive classification, i.e., prediction for each patch is made independently of the other patches in the target test data. We extend the capability of these large models by introducing a transductive approach. By using text-based predictions and affinity relationships among patches, our approach leverages the strong zero-shot capabilities of these new VLMs without any additional labels. Our experiments cover four histopathology datasets and five different VLMs. Operating solely in the embedding space (i.e., in a black-box setting), our approach is highly efficient, processing $10^5$ patches in just a few seconds, and shows significant accuracy improvements over inductive zero-shot classification. Code available at this https URL.

In industrial environments, predicting human actions is essential for ensuring safe and effective collaboration between humans and robots. This paper introduces a perception framework that enables mobile robots to understand and share information about human actions in a decentralized way. The framework first allows each robot to build a spatial graph representing its surroundings, which it then shares with other robots. This shared spatial data is combined with temporal information to track human behavior over time. A swarm-inspired decision-making process is used to ensure all robots agree on a unified interpretation of the human's actions. Results show that adding more robots and incorporating longer time sequences improve prediction accuracy. Additionally, the consensus mechanism increases system resilience, making the multi-robot setup more reliable in dynamic industrial settings.

Medical Ultrasound (US) imaging has seen increasing demands over the past years, becoming one of the most preferred imaging modalities in clinical practice due to its affordability, portability, and real-time capabilities. However, it faces several challenges that limit its applicability, such as operator dependency, variability in interpretation, and limited resolution, which are amplified by the low availability of trained experts. This calls for the need of autonomous systems that are capable of reducing the dependency on humans for increased efficiency and throughput. Reinforcement Learning (RL) comes as a rapidly advancing field under Artificial Intelligence (AI) that allows the development of autonomous and intelligent agents that are capable of executing complex tasks through rewarded interactions with their environments. Existing surveys on advancements in the US scanning domain predominantly focus on partially autonomous solutions leveraging AI for scanning guidance, organ identification, plane recognition, and diagnosis. However, none of these surveys explore the intersection between the stages of the US process and the recent advancements in RL solutions. To bridge this gap, this review proposes a comprehensive taxonomy that integrates the stages of the US process with the RL development pipeline. This taxonomy not only highlights recent RL advancements in the US domain but also identifies unresolved challenges crucial for achieving fully autonomous US systems. This work aims to offer a thorough review of current research efforts, highlighting the potential of RL in building autonomous US solutions while identifying limitations and opportunities for further advancements in this field.

The dynamic adaptation of resource levels enables the system to enhance energy efficiency while maintaining the necessary computational resources, particularly in scenarios where workloads fluctuate significantly over time. The proposed approach can play a crucial role in heterogeneous systems where workload characteristics are not uniformly distributed, such as non-pinning tasks. The deployed THEAS algorithm in this research work ensures a balance between performance and power consumption, making it suitable for a wide range of real-time applications. A comparative analysis of the proposed THEAS algorithm with well-known scheduling techniques such as Completely Fair Scheduler (CFS), Energy-Aware Scheduling (EAS), Heterogeneous Scheduling (HeteroSched), and Utility-Based Scheduling is presented in Table III. Each scheme is compared based on adaptability, core selection criteria, performance scaling, cache awareness, overhead, and real-time suitability.