A5101417955- Topic Modeling
- AI in cancer detection
- Advanced Neural Network Applications
- Natural Language Processing Techniques
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Domain Adaptation and Few-Shot Learning
- Digital Imaging for Blood Diseases
- Advanced Image and Video Retrieval Techniques
- Authorship Attribution and Profiling
- COVID-19 diagnosis using AI
- Neural Networks and Applications
- Multimodal Machine Learning Applications
- Underwater Vehicles and Communication Systems
- Image Retrieval and Classification Techniques
- Machine Learning and Data Classification
- Advanced Vision and Imaging
- Protein Structure and Dynamics
- Robotics and Sensor-Based Localization
- Colorectal Cancer Screening and Detection
- Computational Drug Discovery Methods
- Generative Adversarial Networks and Image Synthesis
- Sentiment Analysis and Opinion Mining
- Image Enhancement Techniques
- Vehicle License Plate Recognition
Kunming University of Science and Technology
2025
Chinese Academy of Sciences
2006-2024
China Mobile (China)
2024
Tokyo University of Science
2024
Peking University
2017-2024
Shenyang Institute of Automation
2017-2024
Harbin Institute of Technology
2024
Group Sense (China)
2019-2023
Ocean University of China
2023
Newcastle University
2021-2023
Generalized nucleus segmentation techniques can contribute greatly to reducing the time develop and validate visual biomarkers for new digital pathology datasets. We summarize results of MoNuSeg 2018 Challenge whose objective was generalizable nuclei in pathology. The challenge an official satellite event MICCAI conference which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set 30 images seven organs annotations...
Abstract Motivation Accurate prediction of cancer drug response (CDR) is challenging due to the uncertainty efficacy and heterogeneity patients. Strong evidences have implicated high dependence CDR on tumor genomic transcriptomic profiles individual Precise identification crucial in both guiding anti-cancer design understanding biology. Results In this study, we present DeepCDR which integrates multi-omics cells explores intrinsic chemical structures drugs for predicting CDR. Specifically, a...
Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Roy Ka-Wei Lee, Ee-Peng Lim. Proceedings of the 61st Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2023.
The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development numerous cost-effective accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e.g., ChatDoctor) or instruction Alpaca). Among various fine-tuning methods, adapter-based parameter-efficient (PEFT) is undoubtedly one most attractive topics, as it only requires a few external parameters instead entire while achieving comparable even better performance. To...
Designing protein mutants with both high stability and activity is a critical yet challenging task in engineering. Here, we introduce PRIME, deep learning model, which can suggest improved without any prior experimental mutagenesis data for the specified protein. Leveraging temperature-aware language modeling, PRIME demonstrated superior predictive ability compared to current state-of-the-art models on public dataset across 283 assays. Furthermore, validated PRIME’s predictions five...
Automatic and accurate 3D cardiac image segmentation plays a crucial role in disease diagnosis treatment. Even though CNN based techniques have achieved great success medical segmentation, the expensive annotation, large memory consumption, insufficient generalization ability still pose challenges to their application clinical practice, especially case of from high-resolution large-dimension volumetric imaging. In this paper, we propose few-shot learning framework by combining ideas...
We report on in situ low-temperature (4 K) scanning tunneling microscope measurements of atomic and electronic structures the cleaved surfaces an alkali-based kagome metal RbV3Sb5 single crystals. find that dominant pristine surface exhibits Rb-1×1 structure, which a unique unidirectional √3a0 charge order is discovered. As sample temperature slightly rises, Rb-√3×1 Rb-√3×√3 reconstructions form due to desorption Rb atoms. Our conductance mapping results demonstrate not only gives rise hole...
The stylistic properties of text have intrigued computational linguistics researchers in recent years. Specifically, investigated the style transfer task (TST), which aims to change while retaining its independent content style. Over last few years, many novel TST algorithms been developed, industry has leveraged these enable exciting applications. field research developed because this symbiosis. This article provide a comprehensive review efforts on transfer. More concretely, we create...
Clinical research on smart health has an increasing demand for intelligent and clinic-oriented medical image computing algorithms platforms that support various applications. To this end, we have developed SenseCare platform, which is designed to facilitate translational diagnosis treatment planning in clinical scenarios. enable with Artificial Intelligence (AI), provides a range of AI toolkits different tasks, including segmentation, registration, lesion landmark detection from modalities...
Rare earth is an important strategic resource and a key mineral for global competition. As the depletion of primary rare-earth resources increases, great number secondary resources, such as waste phosphor powder collected from fluorescent lamps, cathode-ray tubes, other luminescent materials, continue to be generated accumulated. How achieve low-carbon extraction green efficient utilization these has become urgent problem solved. In recent years, preliminary enrichment methods, flotation,...
Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step demonstrations which enable LLMs explicitly generate steps and improve their task accuracy. eliminate the manual effort, Zero-shot-CoT concatenates target problem statement with "Let's think step by step" as an input prompt LLMs. Despite success of...