Ivona Najdenkoska

I'm a PhD student at the University of Amsterdam, working with Marcel Worring and Yuki Asano. I work on vision and language learning at the Informatics Institute, where I'm part of MultiX Amsterdam and AIMLab groups.

In 2023 I spent time as a Research Scientist Intern in Meta GenAI, working on image generation and in-context learning.

I obtained my master degree in Artificial Inteligence at the KU Leuven. Before that, I spent some time as a Software Engineer in Netcetera and I was an undergraduate student in Computer Science and Engineering at the FCSE at University ”Ss. Cyril and Methodius” in Skopje.

Email  /  Twitter  /  Google Scholar  /  Github  /  LinkedIn

profile photo
  • [Apr 2024] I will be a TA for the Foundation Models (FoMo) course at UvA.
  • [Dec 2023] The preprint of my internship work at Meta is available on arXiv.
  • [June 2023] I started a new position as a Research Scientist Intern at Meta AI in Menlo Park, California 🇺🇸
  • [Mar 2023] I will be a TA for Deep Learning 2, Vison-Language learning module.
  • [Jan 2023] Our paper on multimodal few-shot learning is accepted to ICLR 2023 🎉
  • [Dec 2022] I presented my work in the 6th Workshop on Meta-Learning at NeurIPS 2022
  • [Nov 2022] I taught a guest lecture on Attention & Transformers, as part of the Deep Learning 1 course at UvA
  • [Sept 2022] Our paper is runner-up for the MEDIA Best Paper Award at MICCAI 2022

My research is at the intersection of vision and language learning - with focus on designing efficient approaches for multimodal understanding and generative tasks. I'm interested in better understanding what large-scale models learn, and how to exploit that through in-context learning and prompting. Some of my work also includes automated linguistic interpretation of images, as well as its applications in the medical domain.

Context Diffusion: In-Context Aware Image Generation
Ivona Najdenkoska, Animesh Sinha, Abhimanyu Dubey, Dhruv Mahajan, Vignesh Ramanathan, Filip Radenovic
In arXiv 2023  
paper | project page

We present Context Diffusion, an in-context-aware image generation framework capable of learning from a variable number of visual context examples and prompts.

Self-Supervised Open-Ended Classification with Small Visual Language Models
Mohammad M. Derakshani*, Ivona Najdenkoska*, Cees Snoek, Marcel Worring, Yuki M. Asano
In arXiv 2023  

We present Self-Context Adaptation (SeCAt), a selfsupervised approach that unlocks few-shot open-ended classification with small visual language models.

Meta Learning To Bridge Vision and Language Models for Multimodal Few-Shot Learning
Ivona Najdenkoska, Xiantong Zhen, Marcel Worring
In ICLR 2023  
paper | code

We propose a method for bridging large-scale vision and language models to perform multimodal few-shot learning. The model meta-learns visual prefixes from frozen visual backbone, which are used as prompts to a large langauge model.

Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
Tom van Sonsbeek*, Mohammad M. Derakshani*, Ivona Najdenkoska*, Cees Snoek, Marcel Worring
In MICCAI 2023, Oral
paper | code

We introduce a novel method for open-ended VQA suited for small, domain-specific, medical datasets. We employ parameter-efficient strategies for efficient tuning of the LMs.

Meta-Learning Makes a Better Multimodal Few-Shot Learner
Ivona Najdenkoska, Xiantong Zhen, Marcel Worring
In 6th Workshop on Meta-Learning at NeurIPS 2022  

We define a meta-learning approach for multimodal few-shot learning, to leverage its strong ability of accruing knowledge across tasks (predecessor of the ICLR 2023 work).

Uncertainty-aware Report Generation for Chest X-rays by Variational Topic Inference
Ivona Najdenkoska, Xiantong Zhen, Marcel Worring, Ling Shao
In Medical Image Analysis 2022, Best Paper Honorable Mention
paper | code

We present a probabilistic latent variable model for chest X-Ray report generation. We extend the VTI model by providing a fully Transformer-based definition and explore the trade-off between an LSTM- or Transformer-based decoder for generation of medical text.

LifeLonger: A Benchmark for Continual Disease Classification
Mohammad M. Derakshani*, Ivona Najdenkoska*, Tom van Sonsbeek*, Xiantong Zhen, Dwarikanath Mahapatra, Marcel Worring, Cees Snoek
In MICCAI 2022
paper | code | project page

We introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection, by applying existing state-of-the-art continual learning methods.

Learning to Automatically Generate Accurate ECG Captions
Mathieu G. G. Bartels, Ivona Najdenkoska, Rutger van de Leur, Arjan Sammani, Karim Taha, David M. Knigge, Pieter Doevendans, Marcel Worring, Rene van Es
In MIDL 2022

We introduce a label-guided Transformer model, and show that it is possible to automatically generate relevant and readable ECG descriptions with a data-driven captioning model.

Variational Topic Inference for Chest X-Ray Report Generation
Ivona Najdenkoska, Xiantong Zhen, Marcel Worring, Ling Shao
In MICCAI 2021, Oral + Travel Award
paper | code

We propose Variational Topic Inference (VTI), a probabilistic latent variable model for automatic report generation. We introduce a set of topics as latent variables to guide sentence generation by aligning image and language modalities in the latent space.

Academic experience
University of Amsterdam | Teaching Assistant in Master of AI | Feb 2021 - present
- Foundation Models (2024), Deep Learning 1 (2021, 2022), Deep Learning 2 (2023); Multimedia Analytics (2022); Information Visualization (2021).
- Guest lecturer for Deep Learning 1 (2021, 2022)
- Supervision of Master in AI students during their thesis projects.
Work experience
Netcetera | Software Engineer | Sept 2017 - Sept 2018
Netcetera | Software Engineering Intern | Apr 2017 - Jul 2017
Haselt | Software Engineering Intern | Jun 2016 - Sept 2016
  • Reviewer for: CVPR, NeurIPS, ICLR, ICML, ICMR, Computer Vision & Image Understanding Journal, IEEE Transactions on Medical Imaging, Journal of Biomedical and Health Informatics.
  • Invited talk @ Amsterdam Medical Data Science (AMDS) meetup | July 2022, Amsterdam.
  • Participant @ DeepLearn Summer School, organized by IRDTA, | July 2022, Gran Canaria.
  • Participant @ Oxford Machine Learning Summer School, organized by AI for Global Goals | August 2021, Oxford - virtual.
Website template here.