Latest AI and machine learning research in schizophrenia for healthcare professionals.
Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or ungrounded in the input image. Recent work suggests that hallucination detection using internal representations is more efficient and accurate than approaches that rely solely on model outputs. However, existing internal-representation-based methods typically rely o...
As vision-language models (VLMs) are increasingly deployed in clinical decision support, more than accuracy is required: knowing when to trust their predictions is equally critical. Yet, a comprehensive and systematic investigation into the overconfidence of these models remains notably scarce in the medical domain. We address this gap through a comprehensive empirical study of confidence calibrat...
Transfer learning (TL) and deep ensemble learning (DE) have recently been shown to outperform simple machine learning in classifying psychiatric disor...
Purpose: Manual verification of AI-based auto-contouring is labor-intensive and prone to fatigue-related errors. This study developed the large langua...
The deployment of large language models (LLMs) for science carries an intrinsic risk: hallucination of citations, fabricated drug approvals or clinica...
Accurate prediction of drug-target binding affinity across multiple pharmacological endpoints remains challenging, as most deep learning methodologies...
Self-supervised Vision Transformers (ViTs) like DINO show an emergent ability to discover objects, typically observed in [CLS] token attention maps of...
Recent work has questioned whether large language models (LLMs) can perform genuine in-context learning (ICL) for scientific experimental design, with...
Accurate uncertainty quantification is crucial for making reliable decisions in various supervised learning scenarios, particularly when dealing with ...
Large vision-language models (LVLMs) tend to hallucinate, especially when visual inputs are corrupted at test time. We show that such corruptions act ...
Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. However, despite this...
Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barr...
Vision-language models (VLMs) adapted to the medical domain have shown strong performance on visual question answering benchmarks, yet their robustnes...
Artistic font generation aims to synthesize stylized glyphs based on a reference style. However, existing approaches suffer from limited style diversi...
Multimodal Large Language Models (MLLMs) suffer from hallucinations. Existing hallucination evaluation benchmarks are often limited by over-simplified...
Background: Conversational AI safety systems are primarily evaluated using message-level content monitoring, which assesses inputs and outputs in isol...
When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts? We introduce the Tri-Layer Diagnostic Framewor...
Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning. Yet they remain ...
Rapid behavioral adaptation requires the brain to solve a fundamental computational dilemma: how to flexibly update learned rules while maintaining st...
We present Omni-I2C, a comprehensive benchmark designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured...