70 hasil
Menampilkan 1–20 · 0,12 detik · RSS
npj Artificial Intelligence
Scopus
ISSN 3005-1460 · Nature Portfolio · 70 artikel di indeks
-
Artikel Jurnal
A multimodal framework to identify molecular mechanisms driving patient group-associated morphology through the integration of spatial transcriptomics and whole slide imaging
Abstract Spatial organization of the disease microenvironment informs patient prognosis. Key modalities for studying spatial biology include H&E images (WSIs) for tissue structure and spatial transcriptomics (ST) for transcriptome-level programs. Spatial analysis aims to (1) identify markers linked…
-
Artikel Jurnal
A novel deep learning based automatic ultrasonic posterior cruciate ligament clinical assessment tool
Abstract Posterior cruciate ligament (PCL) injuries often present subtle clinical signs and can be overlooked during standard diagnostic procedures, leading to missed or delayed treatment. Although magnetic resonance imaging (MRI) is highly accurate for acute injuries, it is expensive…
-
Artikel Jurnal
An agentic AI framework for ingestion and standardization of single-cell RNA-seq data analysis
Abstract The proliferation of publicly available single-cell RNA sequencing (scRNA-seq) data has created significant opportunities in biomedical research. However, the reuse of these resources is constrained by a series of preparatory steps, including metadata extraction from primary literature…
-
Artikel Jurnal
A self-correcting multi-agent LLM framework for language-based physics simulation and explanation
Abstract Physics-based simulations are essential in science and engineering, yet creating them typically requires expert knowledge of numerical solvers and governing equations. Large language models (LLMs) offer new possibilities for natural language-based simulation, but they often fail when…
-
Artikel Jurnal
SME-TEAM: leveraging trust and ethics for secure and responsible use of AI and LLMs in SMEs
Abstract Artificial Intelligence (AI) and Large Language Models (LLMs) are revolutionizing today’s business practices; however, their adoption within small and medium-sized enterprises (SMEs) raises serious trust, ethical, and technical issues. In this perspective paper, we introduce a structured…
-
Artikel Jurnal
Interpretable Kolmogorov-Arnold networks for enzyme commission number prediction
Abstract Accurate prediction of enzyme commission (EC) numbers remains a significant challenge in bioinformatics, limiting our understanding of enzyme functions and their roles in biological processes. This paper presents the integration and evaluation of Kolmogorov-Arnold networks (KANs), a new…
-
Artikel Jurnal
CAMP: continuous and adaptive learning model in pathology
Abstract Conventional computational pathology treats diagnostic tasks as independent and individual image classification problems, leading to inefficiencies and high costs. To address this, we introduce CAMP (Continuous and Adaptive learning Model in Pathology), a unified and universal framework…
-
Artikel Jurnal
Large language models reflect the ideology of their creators
Abstract Large language models (LLMs) already play an influential role in how humans access information. However, their behavior varies depending on their design, training, and use. We prompt a diverse panel of 19 popular LLMs to describe 3,991 prominent persons with political relevance, and then…
-
Artikel Jurnal
Learning design-score manifold to guide diffusion models for offline optimization
Abstract Optimizing complex systems—from discovering therapeutic drugs to designing high-performance materials—remains a fundamental challenge across science and engineering, as the underlying rules are often unknown and costly to evaluate. Offline optimization aims to optimize designs for target…
-
Artikel Jurnal
Nexus scissor: enhance open-access language model safety by connection pruning
Abstract Large language models (LLMs) are vulnerable to adversarial attacks that bypass safety measures and induce the model to generate harmful content. Securing open-access LLMs against these adversarial attacks is especially challenging due to their offline, unregulated, and often secretive…
-
Artikel Jurnal
Uncertainty-aware genomic deep learning with knowledge distillation
Abstract Deep neural networks (DNNs) have advanced predictive modeling for regulatory genomics, but challenges remain in ensuring the reliability of their predictions and understanding the key factors behind their decision making. Here we introduce DEGU (Distilling Ensembles for Genomic…
-
Artikel Jurnal
Towards parameter identification in pipeline hydraulics: integrating data-driven discovery and knowledge embedding
Abstract An effective parameter identification method is critical in hydraulic transient simulation for pipeline condition assessment. Existing studies neglect the hydraulic spatiotemporal dynamic characteristics and multi-frequency updating characteristics of simulation parameters, resulting in…
-
Artikel Jurnal
Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction
Abstract Human motion intent prediction (HMIP) combines data sources, feature extraction, modeling and prediction algorithms, etc., which is the key for providing artificial intelligent assistance and protection from intelligent wearable systems. HMIP has been intensively explored. A timely and…
-
Artikel Jurnal
AI agent in healthcare: applications, evaluations, and future directions
Abstract With the rapid advancement of large language model (LLM) technologies, AI agents have rapidly emerged in healthcare. This review traces the historical evolution and core characteristics of AI agents, and systematically examines their applications in assisted diagnosis, clinical decision…
-
Artikel Jurnal
3D Magic Mirror: clothing reconstruction from a single image via a causal perspective
Abstract This paper aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometric shape and texture of human clothing from a single image. Compared with existing methods, we observe that three primary challenges remain: (1) 3D ground-truth meshes of clothing are…
-
Artikel Jurnal
Classroom AI: large language models as grade-specific teachers
Abstract Large Language Models (LLMs) offer a promising solution to complement traditional teaching and address global teacher shortages that affect hundreds of millions of children, but they fail to provide grade-appropriate responses for students at different educational levels. We introduce a…
-
Artikel Jurnal
A variational framework for residual-based adaptivity in neural PDE solvers and operator learning
Abstract Residual-based adaptive strategies are widely used in scientific machine learning yet remain largely heuristic. We introduce a variational framework that formalizes these methods through convex transformations of the residual, where different transformations correspond to distinct…
-
Artikel Jurnal
POLYT5: an encoder-decoder foundation chemical language model for generative polymer design
Abstract Traditional machine learning has advanced polymer discovery, yet direct generation of chemically valid and synthesizable polymers without exhaustive enumeration remains a challenge. Here we present POLYT5, an encoder-decoder chemical language model based on the T5 architecture, trained to…
-
Artikel Jurnal
Phase transitions in large language model compression
Abstract This perspective argues that Large Language Models exhibit Model Phase Transitions: performance collapses beyond critical compression thresholds. We analyze structural, numerical, and algebraic redundancy across pruning, quantization, and low-rank decomposition techniques. These sources…
-
Artikel Jurnal
AIFS-CRPS: ensemble forecasting using a model trained with a loss function based on the continuous ranked probability score
Abstract Ensemble weather forecasts provide a probabilistic description of the future state of the atmosphere and give users flow-dependent estimates of forecast uncertainty. Here, we introduce AIFS-CRPS, an ensemble variant of the machine-learned Artificial Intelligence Forecasting System (AIFS)…