Yinan Yu
A central theme in my research is systematically encoding domain-specific knowledge into models to strengthen reasoning and adaptability. Building on this foundation, I advance personalized AI by developing systems that adapt to individual needs and contexts while remaining efficient and scalable. I focus on reducing data requirements, minimizing model size, and designing representation learning methods that support highly personalized data. My work is inherently interdisciplinary, combining insights from computer science, engineering, and domain expertise across healthcare, automotive, finance, sustainability, and other sectors. Through close collaboration with industry partners, I ensure that the systems I design address real-world needs, with robust data governance and deployment practices that make them both scientifically sound and practically valuable.
Visar 50 publikationer
LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks
Mapping sustainability in higher education: a natural language processing analysis of student theses
Polymer: Development Workflows as Software
Automating a Complete Software Test Process Using LLMs: An Automotive Case Study
Deep learning-based Scalable Image-to-3D Facade Parser for generating thermal 3D building models
Semantic-Aware Representation of Multi-Modal Data for Data Ingress: A Literature Review
Sentiment and semantic analysis: Urban quality inference using machine learning algorithms
Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks
climateBUG: A data-driven framework for analyzing bank reporting through a climate lens
Domain generalization through meta-learning: a survey
Building efficient CNNs using Depthwise Convolutional Eigen-Filters (DeCEF)
BAUFER: A Baseline-Enabled Facial Expression Recognition Pipeline Trained With Limited Annotations
AirDnD-Asynchronous In-Range Dynamic and Distributed Network Orchestration Framework
Qually: A Quality Validation Toolbox for Automotive Perception Data Towards Trustworthy AI
Safety-driven data labelling platform to enable safe and responsible AI
AI-baserad segementering av fasader för att optimera renovering i en större skala
Kernel Subspace Learning for Pattern Classification
Adaptive margin slack minimization in RKHS for classification
Microwave technology in medical diagnostics and treatment
Pre-hospital care for stroke and trauma
Detection of wood decay by microwaves
Multiclass Ridge-adjusted Slack Variable Optimization Using Selected Basis for Fast Classification
Feature Reduction Based on Sum-of-SNR (SOSNR) Optimization
Detection of Breathing and Heartbeat by Using a Simple UWB Radar System
Microwave-Based Stroke Diagnosis Making Global Prehospital Thrombolytic Treatment Possible
A Unified Subspace Classification Framework Developed for Diagnostic System Using Microwave Signal
Microwave technology shows potential for detecting traumatic intracranial bleedings
Ridge-Adjusted Slack Variable Optimization for Supervised Classification
Stroke diagnostics with a microwave helmet
Parameter Design Tradeoff Between Prediction Performance and Training Time for Ridge-Svm
Microwave based diagnostics and treatment in practice
Kernel SODA: A Feature Reduction Technique Using Kernel Based Analysis
Several new ultra-wideband antenna systems for radio telescopes and industry sensor imaging process
Compact UWB Indoor and Through-Wall Radar with Precise Ranging and Tracking
Using microwave technology for detecting traumatic intracranial bleedings – tests on a brain phantom
Development of a Compact UWB Radar System for Indoor Ranging and Tracking
Model reduction for inverse scattering problems
The new UWB self-grounded Bow-Tie antennas and the applications in Different Systems
A new UWB radar system using UWB CMOS chip
Ladda ner publikationslistor
Du kan ladda ner denna lista till din dator.
Filtrera och ladda ner publikationslista
Som inloggad användare hittar du ytterligare funktioner i MyResearch.
Du kan även exportera direkt till Zotero eller Mendeley genom webbläsarplugins. Dessa hittar du här:
Zotero Connector
Mendeley Web Importer
Tjänsten SwePub erbjuder uttag av Researchs listor i andra format, till exempel kan du få uttag av publikationer enligt Harvard och Oxford i .RIS, BibTex och RefWorks-format.
Visar 11 forskningsprojekt
AI-baserad telemonitorering och specialiserad hemsjukvård för hjärtsviktspatienter
AutoLang: Anpassning av LLM för programvaruutveckling inom fordonsindustrin
Förbättrad Säkerhet för Vulnerable Road Users (VRU:s) med Nedsatt Rörlighet
Mot radarbaserad gånganalys för äldre med hjälp av maskininlärning
Digitala materialinventeringar för hållbar urban mining
Verification of Machine Learning Algorithms (Vermillion)