Scientific publications

At Visual Intelligence we work across our innovation areas to extract knowledge from large volumes of visual data more efficiently through automatic and intelligent data analysis. The work to address the core research challenges in deep learning: working with limited training data, utilizing context and dependencies, providing explainability, confidence and uncertainty, are important in all the innovation areas.

Featured papers

AI matches human experts in classifying microscopic organisms

July 16, 2025
By
Iver Martinsen, Steffen Aagaard Sørensen, Samuel Ortega, Fred Godtliebsen, Miguel Tejedor, Eirik Myrvoll-Nilsen

Visual Data Diagnosis and Debiasing with Concept Graphs

September 26, 2024
By
Chakraborty, Rwiddhi; Wang, Yinong; Gao, Jialu; Zheng, Runkai; Zhang, Cheng; De la Torre, Fernando

All publications

Mitigating Embedding Leakage via Latent Disruption with Controlled Reconstruction

By authors:

Zhiyuan Wu, Changkyu Choi, Shujian Yu, Robert Jenssen, Ali Ramezani-Kebrya

Published in:

Transactions on Machine Learning Research (June/2026)

on

August 6, 2026

A variational framework for the complexity of PDE solutions

By authors:

Juan Esteban Suarez Cardona, Holger Boche, Gitta Astrid Hildegard Kutyniok

Published in:

BIT Numerical Mathematics, 66:40, 2026

on

June 16, 2026

Symbolic Recovery of Differential Equations: The Identifiability Problem

By authors:

Philipp Scholl, Aras Bacho, Holger Boche, Gitta Astrid Hildegard Kutyniok

Published in:

Mach Learn 115, 139 (2026)

on

May 29, 2026

An annotated aerial imagery dataset for automated detection of harbour seals in Svalbard, Norway

By authors:

Zoé Lemoine, Puneet Sharma, Kit M. Kovacs, Christian Lydersen, Marie-Anne Blanchet

Published in:

Scientific Data

on

May 20, 2026

Physics-Informed Video Diffusion for Shallow Water Equations

By authors:

Yang Bai, George Eskandar, Ziyuan Liu, Gitta Kutyniok

Published in:

ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026, pp. 13242-13246

on

May 3, 2026

Explaining Latent Representations of Neural Networks with Archetypal Analysis

By authors:

Anna Emilie Jennow Wedenborg, Kristoffer Wickstrøm, Lars Kai Hansen, Morten Mørup, Teresa Dorszewski

Published in:

Proceedings of the 7th Northern Lights Deep Learning Conference (NLDL), PMLR 307:448-468, 2026.

on

May 1, 2026

Concepts' Information Bottleneck Models

By authors:

Karim Galliamov, Syed M Ahsan Kazmi, Adil Mehmood Khan, Adín Ramírez Rivera

Published in:

International Conference on Learning Representations (ICLR), 2026

on

April 23, 2026

Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning

By authors:

Gabriel Yanci Arteaga, Marius Aasan, Rwiddhi Chakraborty, Martine Hjelkrem Tan, Thalles Silva, Michael Kampffmeyer, Adín Ramírez Rivera

Published in:

International Conference on Learning Representations (ICLR) 2026

on

April 11, 2026

Suppressing Non-Semantic Noise in Masked Image Modeling Representations

By authors:

Martine Hjelkrem-Tan, Marius Aasan, Rwiddhi Chakraborty, Gabriel Y. Arteaga, Changkyu Choi, Adín Ramirez Rivera

Published in:

CPVR 2026

on

March 31, 2026

A robust and versatile deep learning model for prediction of the arterial input function in dynamic small animal [18F] FDG PET imaging

By authors:

Christian Salomonsen, Luigi T. Luppino, Fredrik Aspheim, Kristoffer Wickstrøm, Elisabeth Wetzer, Michael Kampffmeyer, Rodrigo Berzaghi, Rune Sundset, Robert Jenssen & Samuel Kuttner

Published in:

EJNMMI Res 16, 65 (2026)

on

March 9, 2026

Other publications

annual reports