Adjunct professor Shuijan Yu and centre director Robert Jenssen.
Image:
Ali Ramezani-Kebrya/ICLR

Adjunct professor Shuijan Yu and centre director Robert Jenssen.

Visual Intelligence well represented at ICLR 2024

Visual Intelligence was well represented at the conference, and presented some of the centre's latest research on representation learning by deep neural networks.

Visual Intelligence well represented at ICLR 2024

The International Conference on Learning Representation (ICLR) is one of the top conferences within the field of machine learning and often dubbed "the premiere gathering of professionals dedicated to the advancement of the many branches of artificial intelligence and deep learning". This year's conference took place in Vienna, Austria from May 7th to 11th, with around 6000 participants from 79 different countries present.

Visual Intelligence was well represented at the conference, and presented some of the centre's latest research on representation learning by deep neural networks.

For instance, adjunct professor Shujian Yu presented the paper "Cauchy-Schwarz Information Bottleneck for Regression". The paper presents a new way to regularize neural networkrs when used for regression (function estimation). This is based on a new sample estimator for the so-called Cauchy-Schwarz divergence. The paper is a collaboration between researchers at the Free University of Amsterdam and the University of Florida.

Centre director Robert Jenssen presented the paper "MAP IT to Visualize Representations". In this work, Jenssen developed a new way to visualize high-dimensional data by aligning distributions in a novel manner. This is highly relevant for deep learning to gain insight from the learned representations of the neural networks.

Thea Brüsch was a visiting PhD student at the Visual Intelligence centre from January to July 2024. She is a PhD student at the Technical Universityof Denmark. She presented the paper “On convex decision regions in deep network representations” at the ICLR workshop on Representational Alignment.

There were close to 7300 papers submitted to the conference, with about 30% of them being accepted.

Adjunct professor Shujian Yu. Photo: Ali Ramezani-Kebrya.
Centre director Robert Jenssen. Photo: Ali Ramezani-Kebrya.
Thea Brüsch (third from the left) with her collaborators FabianMager, Lenka Tetkova and Tommy Sonne Alstrøm (left to right). Photo: Private.
Visual Intelligence principal investigator Ali Ramezani-Kebrya gets ready to participate in ICLR 2024. Photo: Private.

‍

Latest news

Visual Intelligence Days 2026 was a success!

September 25, 2026

100 researchers, user partners and invited guests gathered in Oslo, Norway for the Visual Intelligence Days: the centre's annual conference for sharing knowledge and updates on the latest research and innovations.

Sciencenorway.no: Four reasons why you should not blindly trust artificial intelligence

September 19, 2026

Why should we think twice before using AI as a therapist, romantic partner, or to help out with homework? AI expert Elisabeth Wetzer explains (Popular science article on sciencenorway.no / forskning.no).

Associate Professor Kristoffer Wickstrøm interviewed by NRK Radio

September 18, 2026

Associate Professor Kristoffer Wickstrøm was interviewed by Norsk rikskringkasting (NRK) about the ongoing debate on whether to halt current and future AI development

Visual Intelligence well represented at Arendalsuka 2026

August 13, 2026

Visual Intelligence gathered experts from Norwegian politics, research council, industry, the public sector, and academia to discuss the value of Norwegian AI competence and Norwegian-developed models.

Two Visual Intelligence-authored papers accepted for MICCAI 2026

June 17, 2026

Visual Intelligence will be well represented at MICCAI 2026, one of the leading AI conferences on medical imaging and computer assisted intervention, with two accepted research papers.

Visual Intelligence represented at the Datacloud Global Congress' Talent in Tech programme

June 8, 2026

PhD Candidates Solveig Thrun and Christian Salomonsen attended the Datacloud Global Congress' Talent in Tech programme, which invited emerging talent to a unique programme designed to inspire, educate, and connect young professionals with senior leaders from global tech giants.

Kyst og Fjord: Råfisklaget tester AI-teknologi for å knipe syndere

June 2, 2026

En ny AI-løsning utviklet ved UiT kan gjøre det enklere å avdekke feilrapportering og ulovlig fiske. Nå skal Norges Råfisklag teste teknologien i praktisk bruk (News article on kystogfjord.no)