Out-of-distribution (OOD) generalization and detection have received significant attention in recent years, focusing primarily on addressing covariate shifts and category shifts in modern machine learning problems, respectively. However, most existin... read more
IEEE transactions on pattern analysis and machine intelligence
May 12, 2026
Despite the remarkable developments of recent large models in Embodied Artificial Intelligence (E-AI), their integration into robotics is hampered by their excessive parameter sizes and computational demands. Towards the Vision-and-Language Navigatio... read more
IEEE transactions on neural networks and learning systems
May 12, 2026
Analog in-memory computing (AIMC) is a promising technology for energy-efficient acceleration of deep learning workloads. While significant advancements have been achieved in accelerating on-chip inference, on-chip training has not received as much a... read more
IEEE transactions on neural networks and learning systems
May 12, 2026
Infrared and visible image fusion (IVIF) has attracted much attention owing to the highly complementary properties of the two image modalities. Due to the lack of ground-truth fused images, the fusion output of current deep-learning-based methods hea... read more
IEEE transactions on neural networks and learning systems
May 12, 2026
Hyperparameters significantly influence the learning process and performance of machine learning algorithms, rendering their effective selection a critical challenge. Meta-learning-based hyperparameter recommendation has shown promise, yet existing m... read more
Critical reviews in clinical laboratory sciences
May 12, 2026
Single-cell mechanical profiling of deformations has become a promising method of identifying a functional biomarker in patients with blood cancers. By quantifying the physical and mechanical properties of individual cells, this method examines the b... read more
OBJECTIVE: This retrospective, case-control study with internal validation evaluates the performance of machine learning (ML) and deep learning (DL) models in classifying pediatric patients at risk for anxiety disorders using structured electronic he... read more
Real-world evidence (RWE) has emerged as an essential complement to randomized controlled trial data, providing insights into the effectiveness, safety, and tolerability of healthcare interventions in routine practice. The increasing digitalization o... read more
Multimodal Sentiment Analysis (MSA) aims to interpret emotions by integrating textual, acoustic, and visual information. However, the heterogeneous quality and weak correlation among nonverbal modalities often lead to unstable alignment and ineffecti... read more
Software-defined wide area networks (SD-WAN), empowered by software-defined networking (SDN) technology, offer unparalleled flexibility and efficiency in wireless communication. However, their integration introduces new security challenges, particula... read more
Stay Ahead of Medical AI
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.