Few-shot learning (FSL) is a machine learning paradigm that aims to
generalize models from a small number of labeled examples, typically fewer than
10 per class. FSL is particularly crucial in biomedical, environmental,
materials, and mechanical sc... read more
Large language models (LLMs) show significant potential in healthcare,
prompting numerous benchmarks to evaluate their capabilities. However, concerns
persist regarding the reliability of these benchmarks, which often lack
clinical fidelity, robust... read more
Generating stylized large language model (LLM) responses via representation
editing is a promising way for fine-grained output control. However, there
exists an inherent trade-off: imposing a distinctive style often degrades
truthfulness. Existing ... read more
Mixed-precision quantization (MPQ) is crucial for deploying deep neural
networks on resource-constrained devices, but finding the optimal bit-width for
each layer represents a complex combinatorial optimization problem. Current
state-of-the-art met... read more
The integration of artificial intelligence (AI) and pervasive computing offers new opportunities to sense mental health symptoms and deliver just-in-time adaptive interventions via mobile devices. This pilot study tested personalized versus generaliz... read more
IEEE transactions on pattern analysis and machine intelligence
Aug 6, 2025
Adversarial patches present significant challenges to the robustness of deep learning models, making the development of effective defenses become critical for real-world applications. This paper introduces DIFFender, a novel DIFfusion-based DeFender ... read more
Masked autoencoders (MAEs) have emerged as a powerful approach for
pre-training on unlabelled data, capable of learning robust and informative
feature representations. This is particularly advantageous in diffused lung
disease research, where annot... read more
Visual transformation reasoning (VTR) is a vital cognitive capability that
empowers intelligent agents to understand dynamic scenes, model causal
relationships, and predict future states, and thereby guiding actions and
laying the foundation for ad... read more
In the semantic segmentation of remote sensing images, acquiring complete
ground objects is critical for achieving precise analysis. However, this task
is severely hindered by two major challenges: high intra-class variance and
high inter-class sim... read more
We demonstrate that Principal Component Analysis (PCA), when applied in a
structured manner, either to polar-transformed images or segment-wise to token
sequences, enables extreme compression of neural models without sacrificing
performance. Across... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.