Recent Submissions

  • Leveraging Foundation Model Adapters to Enable Robust and Semantic Underwater Exploration 

    Choi, Changkyu; Subramaniam, Arangan; Handegard, Nils Olav; Ramezani-Kebrya, Ali; Jenssen, Robert (Chapter, 2023)
    This position paper presents a framework for intelligent underwater exploration by marrying foundation models (FMs) with multi‑frequency echosounder data. Echosounder data capture backscattered acoustic signals across a ...
  • Reproducible preservation of databases through executable specifications 

    Rummelhoff, Ivar; Kristoffersen, Thor O.; Østvold, Bjarte Mayanja (Journal article; Peer reviewed, 2025)
    We propose a new preservation method for relational data and a corresponding tool. The method involves writing a specification that can later be executed by the tool without user interaction, transforming the input files ...
  • A Spitting Image: Modular Superpixel Tokenization in Vision Transformers 

    Aasan, Marius; Kolbjørnsen, Odd; Solberg, Anne H Schistad; Ramírez Rivera, Adín (Journal article; Peer reviewed, 2025)
    Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples ...
  • Integrating and assessing machine learning acoustic target classification models for fish survey estimations 

    Handegard, Nils Olav; Holmin, Arne Johannes; Pala, Ahmet; Utseth, Ingrid; Johnsen, Espen (Journal article; Peer reviewed, 2025)
    Scientific acoustic-trawl surveys collect data that are used to track fish and zooplankton populations over time. Most rely on manual annotation during acoustic target classification, but automated methods have been proposed. ...
  • SIMULA 67. Common Base Language 

    Dahl, Ole-Johan; Myhrhaug, Bjørn; Nygaard, Kristen (Report at the Norwegian Computing Center;, Research report, 1984)
    This document contains the definition of the programming language SIMULA 76, excluding the Algol language. The language definition is supervized by the SIMULA Standards Group. This document is a revised version of the ...
  • Opplevd smittepress av lakselus for laksesmolt og sjøaure 

    Aldrin, Magne Tommy; Huseby, Ragnar Bang; Jansen, Peder A (NR-notat;, Research report, 2025)
    Arbeidet som beskrives her er utført av Norsk Regnesentral, i samarbeid med Aqualife R&D, og er en del av er del av prosjektet “Opplevd smittepress for lakse smolt og sjøaure i Nordfjord, Sogn, Bjørnafjorden og Hardanger ...
  • Widespread Risk of Extreme Precipitation and Flooding 

    Nordtorp, Henrik; Roksvåg, Thea Julie Thømt; Thorarinsdottir, Thordis Linda (NR-notat;, Research report, 2024)
    Developing a thorough understanding of the prevalence of natural disasters such as floods and extreme precipitation events is of high importance for the society. In this report, it is attempted to investigate and quantify ...
  • Bærekraftig og inkluderende reiseliv - sluttrapport 

    Torrado, Juan Carlos; Fuglerud, Kristin Skeide; Haugan, Anne-Bjørg; Dale, Marianne; Wiborg, Berit Lilly; Andersen, Rita (Report at the Norwegian Computing Center;, Research report, 2025)
  • MAP IT to Visualize Representations 

    Jenssen, Robert (Journal article, 2024)
    MAP IT visualizes representations by taking a fundamentally different approach to dimensionality reduction. MAP IT aligns distributions over discrete marginal probabilities in the input space versus the target space, thus ...
  • Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks 

    Møller, Bjørn; Igel, Christian; Wickstrøm, Kristoffer Knutsen; Sporring, Jon; Jenssen, Robert; Ibragimov, Bulat (Journal article; Peer reviewed, 2024)
    Unsupervised representation learning has become an important ingredient of today’s deep learning systems. However, only a few methods exist that explain a learned vector embedding in the sense of providing information about ...
  • Tilgjengelige informasjonskapsler 

    Simon-Liedtke, Joschua Thomas; Halbach, Till; Kjellstrand, Sara; Hammarberg, Malin; Laurin, Susanna (NR-rapport;, Research report, 2025)
    Prosjektet «Tilgjengelige informasjonskapsler» undersøker universell utforming av cookie-bannere og brukernes oppfatning av disse, med fokus på personer med funksjonsnedsettelser. Vi har gjennomført en litteraturstudie, ...
  • Rensefiskbetingelser: Betingelser som fremmer lusespising hos rensefisk Faglig sluttrapport for FHF-prosjekt Rensefiskbetingelser (P.nr.: 901766) 

    Jansen, Peder A; Lindhom, Andreas; Danielsen, Ole Roald; Rafoss, Trond; Engebretsen, Solveig; Aldrin, Magne Tommy; Stige, Leif Christian (NR-notat;, Research report, 2024)
  • DIB-X: Formulating Explainability Principles for a Self-Explainable Model Through Information Theoretic Learning 

    Choi, Changkyu; Yu, Shujian; Kampffmeyer, Michael Christian; Salberg, Arnt-Børre; Handegard, Nils Olav; Jenssen, Robert (Peer reviewed; Journal article, 2024)
    The recent development of self-explainable deep learning approaches has focused on integrating well-defined explainability principles into learning process, with the goal of achieving these principles through optimization. ...
  • Diffusion Models with Cross-Modal Data for Super-Resolution of Sentinel-2 To 2.5 Meter Resolution 

    Sarmad, Muhammad; Kampffmeyer, Michael Christian; Salberg, Arnt-Børre (Peer reviewed; Journal article, 2024)
    Diffusion models have obtained photo-realistic results on various super-resolution tasks. However, existing approaches typically require the availability of high-resolution and paired training data, which often is not ...
  • Beyond output-mask comparison: A self-supervised inspired object scoring system for building change detection 

    Jensen, Are Charles (Journal article; Peer reviewed, 2024)
    Updating urban-area maps is crucial for urban planning and development. Traditional methods of updating urban-area maps based on aerial photography are labor-intensive and struggle to keep pace with rapid urban development. ...
  • The aerosol pathway is crucial for observationally constraining climate sensitivity and anthropogenic forcing 

    Skeie, Ragnhild Bieltvedt; Aldrin, Magne Tommy; Berntsen, Terje Koren; Holden, Marit; Huseby, Ragnar Bang; Myhre, Gunnar; Storelvmo, Trude (Journal article; Peer reviewed, 2024)
    Climate sensitivity and aerosol forcing are two of the most central, but uncertain, quantities in climate science that are crucial for assessing historical climate as well as future climate projections. Here, we use a ...
  • Pilotprosjekt PO6: Scenariosimulering av lakselus i Midt-Norge 

    Engebretsen, Solveig; Aldrin, Magne Tommy; Klakegg, Barbo; Grøntvedt, Randi Nygaard; Jensen, Stig Rune; Nøst, Ole Anders; Selnæs, John (NR-notat;, Research report, 2025)
    I dette notatet vurderer vi ulike tiltak mot lakselus i produksjonsområde 6 ved hjelp av scenariosimulering fra en lusemodell. Vi tilpasser lusemodellen til historiske data fra BarentsWatch. I modellen inngår smitte mellom ...
  • Enhancing Naturalness in LLM-Generated Utterances through Disfluency Insertion 

    Zohaib Hassan, Syed; Lison, Pierre; Halvorsen, Pål (Journal article, 2024)
    Disfluencies are a natural feature of spontaneous human speech but are typically absent from the outputs of Large Language Models (LLMs). This absence can diminish the perceived naturalness of synthesized speech, which is ...
  • A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interaction 

    Walker, Nicholas Thomas; Ultes, Stefan; Lison, Pierre (Journal article, 2023)
    Knowledge graphs are often used to represent structured information in a flexible and efficient manner, but their use in situated dialogue remains under-explored. This paper presents a novel conversational model for ...
  • Incremental Dialogue Management: Survey, Discussion, and Implications for HRI 

    Kennington, Casey; Lison, Pierre; Schlangen, David (Journal article, 2025)
    Efforts towards endowing robots with the ability to speak have benefited from recent advancements in NLP, in particular large language models. However, as powerful as current models have become, they still operate on ...

View more