We'd love to hear your feedback, questions, or suggestions!
Thank you! Your message has been received.
We collect aggregate usage information (number of visits, etc.) and we use cookies to support functionality such as voting. We also log IP addresses for debugging and to monitor usage of AI-backed endpoints. In addition, we retain any data you voluntarily submit via the Contact form. See the Data Handling section for full details on what we store and how long we keep it.
KUnnect is built exclusively on publicly available researcher profiles from CURIS, the University of Copenhagen's official research information system. No restricted databases, logins, or private records were accessed.
We do not store what you search for or the abstracts/papers you submit. Queries and text inputs are processed in real time and immediately discarded — nothing you enter is retained after your session ends, other than what you voluntarily submit in the contact form. We do keep logs of IP addresses for debugging purposes.
All computation runs on a server hosted in Denmark by Scannet. We are considering options of hosting it in servers managed by KU-IT in the future.
The language models used for embedding and generating recommendations run locally on that server. No data is sent to external AI providers such as OpenAI or Anthropic.
Please provide a reason for downvoting this recommendation.
Discover KU researchers who share your scientific interests. Database includes researchers with three or more publications on CURIS since 2021.
Loading results...
KUnnect turns public publication records into meaning-based profiles, then matches researchers working on similar ground. Here is the path from raw data to a recommendation.
KUnnect is built on publicly available researcher profiles from CURIS, the University of Copenhagen's official research information system. The dataset covers approximately 6,300 researchers whose profiles were publicly indexed in CURIS as of January 2026 and who had at least three publications recorded since 2021. Only publicly accessible pages were used; no login or restricted database was involved.
Each researcher is tracked through a unique profile identifier, so author names are never guessed or confused between people who share a similar name. Their publications are linked back to that single identity before any analysis begins.
KUnnect uses a technique called semantic embedding to capture the meaning of each researcher's work, going beyond titles to the content of the research itself. A language model called Nomic AI reads each publication abstract and converts it into a list of 768 numbers encoding the meaning of the text. Trained on vast scientific literature, the model knows that "myocardial infarction" and "heart attack" refer to the same concept, and that a paper on Arctic ice cores is closer in meaning to one on permafrost than to one on corporate tax law. Each researcher's publication fingerprints are then averaged into a single profile representing the overall territory of their work.
When you search for a researcher, KUnnect first identifies their existing co-authors from papers published since 2021. KUnnect then searches the full pool of 6,300 researchers for those whose topic profile is closest to the queried researcher's, surfacing people covering similar scientific ground who have not recently collaborated. Researchers who collaborated with them prior to 2021 are not excluded and may appear as potential matches.
A language model then reads a selection of papers from both sides and writes a short explanation of the potential overlap — the recommendation text you see in your results.
You can also search by research theme rather than by name. The system finds publications close to that theme, identifies the researchers behind them, and summarises the landscape. Alternatively, you can upload a PDF or paste an abstract: your own text is embedded using the same model and used directly as the search query.
The Research Map groups all 6,300 researchers into clusters based on the similarity of their publication profiles. The same semantic embeddings used for collaborator matching are clustered so that researchers working on related topics are grouped together. Each cluster is then classified within the OpenAlex academic taxonomy: a language model reads the cluster's label and description and maps it to the best-matching field and topic from OpenAlex's hierarchy of roughly 4,500 topics across 26 fields. The result is an interactive overview of the research landscape at the University of Copenhagen, where you can explore clusters and see which researchers belong to each area.
Recommendations reflect topical similarity based on published abstracts. They are a starting point for your own judgement, not a guarantee of a productive match. Researchers with a very broad set of interests may be harder to represent accurately, since averaging across many different topics can blur their profile. As the content is AI-generated, it may include errors and misrepresentations.