Zeming Liang

MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision Support

Lihui Luo, Joongwon Chae, Ziyan Chen, Yang Liu et autres

Traditional Chinese Medicine (TCM) diagnosis, particularly through tongue inspection, faces persistent challenges in subjectivity and reproducibility. The application of multimodal artificial intelligence to TCM clinical tasks, such as syndrome differentiation and prescription generation, is significantly hampered by the semantic gap between visual …

StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection

Joongwon Chae, Lihui Luo, Yang Liu, Runming Wang et autres

Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD). However, because it relies on a single extreme response, it discards most information about how anomaly evidence is distributed and structured …

GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detection

Joongwon Chae, Lihui Luo, Yang Liu, Runming Wang et autres

Feature-based anomaly detection is widely adopted in industrial inspection due to the strong representational power of large pre-trained vision encoders. While most existing methods focus on improving within-category anomaly scoring, practical deployments increasingly require task-agnostic operation under continual category expansion, where the …

Document Similarity Enhanced IPS Estimation for Unbiased Learning to Rank

Zeming Liang, Graham McDonald, Iadh Ounis

Learning to Rank (LTR) models learn from historical user interactions, such as user clicks. However, there is an inherent bias in the clicks of users due to position bias, i.e., users are more likely to click highly-ranked documents than low-ranked documents. To …

gb (code pays fourni par la source)

The Development Process and Characteristics of Antibodies in Antibody-drug Conjugate

Zeming Liang

More than 100 years ago, Paul Ehrlich, the father of immunology, first proposed the concept of “magic bullets”, i.e., the concept of selectively delivering toxic drugs to target cells while avoiding damage to normal cells in the human body. ADCs, as a …

cn (code pays fourni par la source)

An Expert-Driven Machine Learning for Medical Imaging-Based Diagnosis of Lesions

Zeming Liang, Licheng R. Kuo, Marc J. Pomeroy, Su-Youne Chang et autres

This paper describes an expert-driven, instead of data-driven, machine learning (EdML) to characterize in vivo tissues for medical imaging-based diagnosis of lesions. The presented EdML mimics experts’ performance by incorporating experts’ prior knowledge into analysis of data to accomplish a task that …

us (code pays fourni par la source)

Polar AUV Challenges and Applications: A Review

Shuangshuang Fan, Neil Bose, Zeming Liang

This study presents a comprehensive review of the development and progression of autonomous underwater vehicles (AUVs) in polar regions, aiming to synthesize past experiences and provide guidance for future advancements and applications. We extensively explore the history of notable polar AUV deployments …

cn, ca (code pays fourni par la source)