Archives AI News

arXiv:2509.00069v1 Announce Type: new Abstract: Conversational AI and Large Language Models (LLMs) have become powerful tools across domains, including cybersecurity, where they help detect threats early and improve response times. However, challenges such as false positives and complex model management still limit trust. Although Explainable AI (XAI) aims to make AI decisions more transparent, many security analysts remain uncertain about its usefulness. This study presents a framework that detects anomalies and provides high-quality explanations through visual tools BERTViz and Captum, combined with natural language reports based on attention outputs. This reduces manual effort and speeds up remediation. Our comparative analysis showed that RoBERTa offers high accuracy (99.6 %) and strong anomaly detection, outperforming Falcon-7B and DeBERTa, as well as exhibiting better flexibility than large-scale Mistral-7B on the HDFS dataset from LogHub. User feedback confirms the chatbot's ease of use and improved understanding of anomalies, demonstrating the ability of the developed framework to strengthen cybersecurity workflows.

arXiv:2509.02474v1 Announce Type: cross Abstract: Following rapid advancements in text and image generation, research has increasingly shifted towards 3D generation. Unlike the well-established pixel-based representation in images, 3D representations remain diverse and fragmented, encompassing a wide variety of approaches such as voxel grids, neural radiance fields, signed distance functions, point clouds, or octrees, each offering distinct advantages and limitations. In this work, we present a unified evaluation framework designed to assess the performance of 3D representations in reconstruction and generation. We compare these representations based on multiple criteria: quality, computational efficiency, and generalization performance. Beyond standard model benchmarking, our experiments aim to derive best practices over all steps involved in the 3D generation pipeline, including preprocessing, mesh reconstruction, compression with autoencoders, and generation. Our findings highlight that reconstruction errors significantly impact overall performance, underscoring the need to evaluate generation and reconstruction jointly. We provide insights that can inform the selection of suitable 3D models for various applications, facilitating the development of more robust and application-specific solutions in 3D generation. The code for our framework is available at https://github.com/isl-org/unifi3d.

arXiv:2509.00071v1 Announce Type: new Abstract: In recent years, AI-assisted IC design methods have demonstrated great potential, but the availability of circuit design data is extremely limited, especially in the public domain. The lack of circuit data has become the primary bottleneck in developing AI-assisted IC design methods. In this work, we make the first attempt, SynCircuit, to generate new synthetic circuits with valid functionalities in the HDL format. SynCircuit automatically generates synthetic data using a framework with three innovative steps: 1) We propose a customized diffusion-based generative model to resolve the Directed Cyclic Graph (DCG) generation task, which has not been well explored in the AI community. 2) To ensure our circuit is valid, we enforce the circuit constraints by refining the initial graph generation outputs. 3) The Monte Carlo tree search (MCTS) method further optimizes the logic redundancy in the generated graph. Experimental results demonstrate that our proposed SynCircuit can generate more realistic synthetic circuits and enhance ML model performance in downstream circuit design tasks.

arXiv:2408.16653v2 Announce Type: replace Abstract: Recent works on the parallel complexity of Boosting have established strong lower bounds on the tradeoff between the number of training rounds $p$ and the total parallel work per round $t$. These works have also presented highly non-trivial parallel algorithms that shed light on different regions of this tradeoff. Despite these advancements, a significant gap persists between the theoretical lower bounds and the performance of these algorithms across much of the tradeoff space. In this work, we essentially close this gap by providing both improved lower bounds on the parallel complexity of weak-to-strong learners, and a parallel Boosting algorithm whose performance matches these bounds across the entire $p$ vs.~$t$ compromise spectrum, up to logarithmic factors. Ultimately, this work settles the true parallel complexity of Boosting algorithms that are nearly sample-optimal.

arXiv:2509.00073v1 Announce Type: new Abstract: Generative Artificial Intelligence (GenAI), particularly Large Language Models (LLMs), offer powerful capabilities for interpreting the complex data landscape in healthcare. In this paper, we present a comprehensive overview of the capabilities, requirements and applications of GenAI for deriving clinical insights and improving clinical efficiency. We first provide some background on the forms and sources of patient data, namely real-time Remote Patient Monitoring (RPM) streams and traditional Electronic Health Records (EHRs). The sheer volume and heterogeneity of this combined data present significant challenges to clinicians and contribute to information overload. In addition, we explore the potential of LLM-powered applications for improving clinical efficiency. These applications can enhance navigation of longitudinal patient data and provide actionable clinical decision support through natural language dialogue. We discuss the opportunities this presents for streamlining clinician workflows and personalizing care, alongside critical challenges such as data integration complexity, ensuring data quality and RPM data reliability, maintaining patient privacy, validating AI outputs for clinical safety, mitigating bias, and ensuring clinical acceptance. We believe this work represents the first summarization of GenAI techniques for managing clinician data overload due to combined RPM / EHR data complexities.

arXiv:2502.20293v3 Announce Type: replace Abstract: Instance selection (IS) addresses the critical challenge of reducing dataset size while keeping informative characteristics, becoming increasingly important as datasets grow to millions of instances. Current IS methods often struggle with capturing complex relationships in high-dimensional spaces and scale with large datasets. This paper introduces a graph attention-based instance selection (GAIS) method that uses attention mechanisms to identify informative instances through their structural relationships in graph representations. We present two approaches for scalable graph construction: a distance-based mini-batch sampling technique that achieves dataset-size-independent complexity through strategic batch processing, and a hierarchical hashing approach that enables efficient similarity computation through random projections. The mini-batch approach keeps class distributions through stratified sampling, while the hierarchical hashing method captures relationships at multiple granularities through single-level, multi-level, and multi-view variants. Experiments across 39 datasets show that GAIS achieves reduction rates above 96% while maintaining or improving model performance relative to state-of-the-art IS methods. The findings show that the distance-based mini-batch approach offers an optimal efficiency for large-scale datasets, while multi-view variants excel on complex, high-dimensional data, demonstrating that attention-based importance scoring can effectively identify instances important for maintaining decision boundaries while avoiding computationally prohibitive pairwise comparisons.

arXiv:2509.00076v1 Announce Type: new Abstract: There is increased interest in applying Artificial Intelligence and Machine Learning (AI/ML) within the nuclear industry and nuclear engineering community. Effective implementation of AI/ML could offer benefits to the nuclear domain, including enhanced identification of anomalies, anticipation of system failures, and operational schedule optimization. However, limited work has been done to investigate the feasibility and applicability of AI/ML tools in a functioning nuclear reactor. Here, we go beyond the development of a single model and introduce a multi-layered AI/ML architecture that integrates both information technology and operational technology data streams to identify, characterize, and differentiate (i) among diverse cybersecurity events and (ii) between cyber events and other operational anomalies. Leveraging Purdue Universitys research reactor, PUR-1, we demonstrate this architecture through a representative use case that includes multiple concurrent false data injections and denial-of-service attacks of increasing complexity under realistic reactor conditions. The use case includes 14 system states (1 normal, 13 abnormal) and over 13.8 million multi-variate operational and information technology data points. The study demonstrated the capability of AI/ML to distinguish between normal, abnormal, and cybersecurity-related events, even under challenging conditions such as denial-of-service attacks. Combining operational and information technology data improved classification accuracy but posed challenges related to synchronization and collection during certain cyber events. While results indicate significant promise for AI/ML in nuclear cybersecurity, the findings also highlight the need for further refinement in handling complex event differentiation and multi-class architectures.

arXiv:2507.03843v2 Announce Type: replace Abstract: Cost models in healthcare research must balance interpretability, accuracy, and parameter consistency. However, interpretable models often struggle to achieve both accuracy and consistency. Ordinary least squares (OLS) models for high-dimensional regression can be accurate but fail to produce stable regression coefficients over time when using highly granular ICD-10 diagnostic codes as predictors. This instability arises because many ICD-10 codes are infrequent in healthcare datasets. While regularization methods such as Ridge can address this issue, they risk discarding important predictors. Here, we demonstrate that reducing the granularity of ICD-10 codes is an effective regularization strategy within OLS while preserving the representation of all diagnostic code categories. By truncating ICD-10 codes from seven characters to six or fewer, we reduce the dimensionality of the regression problem while maintaining model interpretability and consistency. Mathematically, the merging of predictors in OLS leads to increased trace of the Hessian matrix, which reduces the variance of coefficient estimation. Our findings explain why broader diagnostic groupings like DRGs and HCC codes are favored over highly granular ICD-10 codes in real-world risk adjustment and cost models.

arXiv:2509.00083v1 Announce Type: new Abstract: Modern generative models risk overfitting and unintentionally memorizing rare training examples, which can be extracted by adversaries or inflate benchmark performance. We propose Generative Data Cartography (GenDataCarto), a data-centric framework that assigns each pretraining sample a difficulty score (early-epoch loss) and a memorization score (frequency of ``forget events''), then partitions examples into four quadrants to guide targeted pruning and up-/down-weighting. We prove that our memorization score lower-bounds classical influence under smoothness assumptions and that down-weighting high-memorization hotspots provably decreases the generalization gap via uniform stability bounds. Empirically, GenDataCarto reduces synthetic canary extraction success by over 40% at just 10% data pruning, while increasing validation perplexity by less than 0.5%. These results demonstrate that principled data interventions can dramatically mitigate leakage with minimal cost to generative performance.

arXiv:2305.04228v4 Announce Type: replace-cross Abstract: Code classification is a difficult issue in program understanding and automatic coding. Due to the elusive syntax and complicated semantics in programs, most existing studies use techniques based on abstract syntax tree (AST) and graph neural networks (GNN) to create code representations for code classification. These techniques utilize the structure and semantic information of the code, but they only take into account pairwise associations and neglect the high-order data correlations that already exist between nodes of the same field or called attribute in the AST, which may result in the loss of code structural information. On the other hand, while a general hypergraph can encode high-order data correlations, it is homogeneous and undirected which will result in a lack of semantic and structural information such as node types, edge types, and directions between child nodes and parent nodes when modeling AST. In this study, we propose a heterogeneous directed hypergraph (HDHG) to represent AST and a heterogeneous directed hypergraph neural network (HDHGN) to process the graph for code classification. Our method improves code understanding and can represent high-order data correlations beyond paired interactions. We assess our heterogeneous directed hypergraph neural network (HDHGN) on public datasets of Python and Java programs. Our method outperforms previous AST-based and GNN-based methods, which demonstrates the capability of our model.