Latest AI and machine learning research in schizophrenia for healthcare professionals.
Multimodal large language models (MLLMs) struggle with hallucinations, particularly with fine-grained queries, a challenge underrepresented by existing benchmarks that focus on coarse image-related questions. We introduce FIne-grained NEgative queRies (FINER), alongside two benchmarks: FINER-CompreCap and FINER-DOCCI. Using FINER, we analyze hallucinations across four settings: multi-object, multi...
Vision-Language Models (VLMs) offer significant potential in computational pathology by enabling interpretable image analysis, automated reporting, and scalable decision support. However, their widespread clinical adoption remains limited due to the absence of reliable, automated evaluation metrics capable of identifying subtle failures such as hallucinations. To address this gap, we propose PathG...
Large vision-language models (LVLMs) have become increasingly strong but remain prone to hallucinations in multimodal tasks, which significantly narro...
Objective. We establish a principled method for inferring mental health related psychometric variables from neural and behavioral data using the Impli...
Scanning Probe Microscopy or SPM offers nanoscale resolution but is frequently marred by structured artefacts such as line scan dropout, gain induced ...
Hallucination detection in captions (HalDec) assesses a vision-language model's ability to correctly align image content with text by identifying erro...
Twelve-lead electrocardiography (ECG) is essential for cardiovascular diagnosis, but its long-term acquisition in daily life is constrained by complex...
Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their tr...
Current training-free methods tackle MLLM hallucination with separate strategies: either enhancing visual signals or suppressing text inertia. However...
While large vision-language models (LVLMs) achieve strong performance on multimodal tasks, they frequently generate hallucinations -- unfaithful outpu...
Maintaining background consistency while enhancing foreground quality remains a core challenge in video editing. Injecting full-image information ofte...
Quantitative systems pharmacology (QSP) models require calibration data from published literature, yet manual curation produces inconsistent documenta...
With the rapid advancement of AIGC technology, developing identification methods to address the security challenges posed by deepfakes has become urge...
Accurate tumor analysis is central to clinical radiology and precision oncology, where early detection, reliable lesion characterization, and patholog...
Generative real-world image super-resolution (Real-ISR) can synthesize visually convincing details from severely degraded low-resolution (LR) inputs, ...
Digital subtraction angiography (DSA) is a key imaging technique for the auxiliary diagnosis and treatment of cerebrovascular diseases. Recent advance...
Hallucination has been a significant impediment to the development and application of current Large Vision-Language Models (LVLMs). To mitigate halluc...
Deep learning (DL) methods are currently being explored to restore images from sparse-view-, limited-data-, and undersampled-based acquisitions in med...
Animals integrate information over time and maintain persistent internal representations of cues to guide decision-making. How the underlying behavior...
Background: The rapid growth of public single-cell and spatial transcriptomics repositories has shifted the main bottleneck for atlas-scale integratio...