{ "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json", "basics": { "name": "Kavindu Ravishan Perera", "label": "Project Researcher, University of Oulu", "image": "https://www.kavinduravishan.com/images/kavindu-ravishan-perera.jpg", "url": "https://www.kavinduravishan.com/", "summary": "Kavindu Ravishan Perera (published as Kavindu Perera) is a Project Researcher at the University of Oulu, where he is starting a PhD in reinforcement learning within the Horizon Europe project ARGENTIC. His work covers conversational AI, retrieval augmented generation, AI agents and human-AI interaction. He built the AI platform behind NeuroClima, an EU climate policy project, and is responsible for development in AIKAA, which brings generative AI to small Finnish companies. His first-author paper on AI-assisted spoken reviews appeared at ACM MUM 2024.", "profiles": [ { "network": "Google Scholar", "url": "https://scholar.google.com/citations?user=X6T7ffIAAAAJ&hl=en" }, { "network": "LinkedIn", "url": "https://www.linkedin.com/in/raviya/" }, { "network": "ORCID", "url": "https://orcid.org/0000-0001-9621-3104" }, { "network": "ResearchGate", "url": "https://www.researchgate.net/profile/Kavindu-Perera-15" }, { "network": "GitHub", "url": "https://github.com/kravishan" }, { "network": "YouTube", "url": "https://www.youtube.com/@kavindu.ravishan.perera" } ] }, "work": [ { "name": "University of Oulu", "position": "Project Researcher", "url": "https://www.oulu.fi/en", "summary": "Builds AI systems for policymakers, researchers and everyday users at the University of Oulu.", "highlights": [ "NeuroClima: Climate and policy knowledge anyone can ask about, in four languages.", "ARGENTIC: Deciding where each AI workload should run, and learning to decide better.", "AIKAA: Generative AI demos for the repetitive work in small Finnish companies." ] } ], "education": [ { "institution": "University of Oulu", "area": "Computer Science and Engineering", "studyType": "Master's degree", "endDate": "2024" }, { "institution": "Riga Technical University", "area": "Engineering Science", "studyType": "Bachelor's degree", "endDate": "2022" }, { "institution": "SLTC Research University", "area": "Electrical and Electronics Engineering" } ], "publications": [ { "name": "From Voice to Value: Leveraging AI to Enhance Spoken Online Reviews on the Go", "publisher": "ACM International Conference on Mobile and Ubiquitous Multimedia (MUM 2024)", "releaseDate": "2024", "url": "https://doi.org/10.1145/3701571.3701593", "summary": "Speak a restaurant review and let an AI help turn it into one you would post. A field study with 14 people and 157 reviews: willingness to share rose 31%, and confidence in writing a good review rose 88%." }, { "name": "Factors of Trust for Successfully Adopting Social Robots on the Campus", "publisher": "Australian Conference on Human-Computer Interaction (OzCHI 2025)", "releaseDate": "2025", "url": "https://doi.org/10.1145/3764687.3764717", "summary": "What students and staff would need before trusting a social robot on campus, from 59 people who met a Pepper robot first. Knowing what the robot does, and who is behind it, came first." }, { "name": "A modular transformer framework for automated detection and structuring of social tipping point evidence in climate-related documents", "publisher": "In preparation", "url": "https://arxiv.org/pdf/2609.12254", "summary": "Finding the moments a public conversation turns, and giving that evidence enough structure that something else can act on it. The classifier behind it also runs inside NeuroClima." }, { "name": "What Does a Faithfulness Score Summarise? Evidence from a Production RAG System Built with Open-Source Technologies", "publisher": "In preparation", "summary": "Reading the explanations behind an LLM judge’s faithfulness scores for 1,197 answers from NeuroClima, and finding what a single number leaves out: about one in seven pieces of evidence the judge relied on was text a model had written, not the source." }, { "name": "AIRA Scholar-KG: A Multi-Source Knowledge Graph and Grounded Conversational Assistant for Academic Research Exploration", "publisher": "In preparation", "summary": "Asking questions of the research literature and getting answers grounded in a knowledge graph assembled from several sources, rather than a single index." }, { "name": "Log2Sign: Automatic signature generation using LLMs with Explainability and Interpretability", "publisher": "In preparation", "summary": "Generating intrusion detection signatures from logs automatically with large language models, while keeping each signature explainable and interpretable." } ], "projects": [ { "name": "NeuroClima", "description": "Over 10,000 climate and policy documents made answerable in four languages, at whichever reading level the person asking needs.", "url": "https://www.kavinduravishan.com/projects/neuroclima/", "type": "EU Horizon project" }, { "name": "ARGENTIC", "description": "My PhD. Every AI workload has to run somewhere, and something has to decide where. This is about making that decision learn.", "url": "https://www.kavinduravishan.com/projects/argentic/", "type": "PhD research" }, { "name": "AIKAA", "description": "Find out which parts of the week a small Finnish company keeps repeating, and build something that takes those parts off them.", "url": "https://www.kavinduravishan.com/projects/aikaa/", "type": "ESF+ project" }, { "name": "Voice to Value", "description": "You talk about an experience. The model turns it into something you would actually post. My master's thesis, and a paper at ACM MUM 2024.", "url": "https://www.kavinduravishan.com/projects/voice-to-value/", "type": "Master’s thesis" }, { "name": "Human robot interaction", "description": "A Pepper robot in the corridors of the University of Oulu, and a study of what people would need before they trusted one on campus. A summer internship.", "url": "https://www.kavinduravishan.com/projects/human-robot-interaction/", "type": "Summer internship" } ], "languages": [ { "language": "English" }, { "language": "Sinhala" } ], "interests": [ { "name": "Research", "keywords": [ "Conversational AI", "AI agents", "Reinforcement learning", "Multi-agent systems", "Natural language processing", "Large language models", "Retrieval augmented generation", "Knowledge graphs", "LLM evaluation", "Human-AI interaction", "Human-computer interaction", "Human-robot interaction", "Voice user interfaces", "MLOps", "Kubernetes" ] } ], "meta": { "canonical": "https://www.kavinduravishan.com/resume.json", "lastModified": "2026-09-25" } }