Ondrej Bohdal

I'm a senior machine learning researcher at Samsung Research, where I primarily focus on large language models. Before joining Samsung, I was a postdoctoral researcher at the University of Edinburgh, working on topics such as multimodal large language models, diffusion models, fairness, uncertainty calibration and out-of-distribution generalization.

I did my PhD on Meta-Learning Algorithms and Applications at the University of Edinburgh, advised by Timothy Hospedales. I was a research intern at Samsung AI Center, Cambridge and Amazon Web Services, Berlin, and also did part of my studies at the Alan Turing Institute in London.

Email  /  Google Scholar  /  Twitter  /  Github  /  LinkedIn  /  London, UK

profile photo

Research

I've worked on diverse topics within deep learning, including meta-learning, data efficiency, domain adaptation, out-of-distribution generalization, uncertainty calibration, fairness, multimodal large language models, diffusion models and hyperparameter optimization. I work with images (computer vision) and text (natural language processing).

MemControl: Mitigating Memorization in Medical Diffusion Models via Automated Parameter Selection
Raman Dutt, Ondrej Bohdal, Pedro Sanchez, Sotirios A. Tsaftaris, Timothy Hospedales
WACV, 2025
paper
On the Limitations of General Purpose Domain Generalisation Methods
Henry Gouk, Ondrej Bohdal, Da Li, Timothy Hospedales
Under review, 2024
paper
Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted
Ruchika Chavhan, Ondrej Bohdal, Yongshuo Zong, Da Li, Timothy Hospedales
ICML GenLaw workshop and under review, 2024
paper
VL-ICL Bench: The Devil in the Details of Benchmarking Multimodal In-Context Learning
Yongshuo Zong*, Ondrej Bohdal*, Timothy Hospedales
* Joint first authors
Under review, 2024
paper / project page / code / data
Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
Yongshuo Zong, Ondrej Bohdal, Tingyang Yu, Yongxin Yang, Timothy Hospedales
ICML, 2024
paper / project page / code / data
Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks
Martin Ferianc*, Ondrej Bohdal*, Timothy Hospedales, Miguel Rodrigues           
* Joint first authors
TMLR, 2024
paper / code / video
FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
ICLR, 2024
paper / code
Feed-Forward Latent Domain Adaptation
Ondrej Bohdal, Da Li, Shell Xu Hu, Timothy Hospedales
WACV, 2024
paper / project page / video / slides
Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error
Ondrej Bohdal, Yongxin Yang, Timothy Hospedales
TMLR, 2023
paper / code
Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn
Ondrej Bohdal*, Yinbing Tian*, Yongshuo Zong, Ruchika Chavhan, Da Li, Henry Gouk, Li Guo, Timothy Hospedales
* Joint first authors
CVPR, 2023
paper / project page / code / video / slides / poster
PASHA: Efficient HPO and NAS with Progressive Resource Allocation
Ondrej Bohdal, Lukas Balles, Martin Wistuba, Beyza Ermis, Cédric Archambeau, Giovanni Zappella
ICLR, 2023
HPO: hyperparameter optimization, NAS: neural architecture search
paper / code / tutorial / video / slides / poster
Label Calibration for Semantic Segmentation Under Domain Shift
Ondrej Bohdal, Da Li, Timothy Hospedales
ICLR Trustworthy ML workshop, 2023
paper
Fairness in AI and Its Long-Term Implications on Society
Ondrej Bohdal, Timothy Hospedales, Philip H.S. Torr, Fazl Barez
Stanford Existential Risks Conference, 2023
paper
Feed-Forward Source-Free Domain Adaptation via Class Prototypes
Ondrej Bohdal, Da Li, Timothy Hospedales
ECCV OOD-CV workshop, 2022
paper
EvoGrad: Efficient Gradient‑Based Meta‑Learning and Hyperparameter Optimization
Ondrej Bohdal, Yongxin Yang, Timothy Hospedales
NeurIPS, 2021
paper / code / blog / video / slides / poster
A Channel Coding Benchmark for Meta‑Learning
Rui Li, Ondrej Bohdal, Rajesh Mishra, Hyeji Kim, Da Li, Nicholas Lane, Timothy Hospedales
NeurIPS (datasets and benchmarks track), 2021
paper / code / blog / video
Flexible Dataset Distillation: Learn Labels Instead of Images
Ondrej Bohdal, Yongxin Yang, Timothy Hospedales
NeurIPS MetaLearn workshop, 2020
paper / code / video
Semantic Segmentation of 3D Point Clouds
Data study group at the Alan Turing Institute, 2020
report

Experience

Research

Senior Researcher
Samsung Research, London (Staines-upon-Thames), UK
May 2024 - Current
Research in large language models
Managers: Umberto Michieli and Mete Ozay
Postdoctoral Research Associate
The University of Edinburgh, Edinburgh, UK
May 2023 - May 2024
Research in multimodal large language models, diffusion models, fairness, uncertainty calibration
Supervised by Timothy Hospedales
Research Intern (Part-Time)
Samsung AI Center, Cambridge, UK
Nov 2021 - Apr 2022
Research in source-free domain adaptation
Hosted by Da Li
Enrichment Scheme PhD Student
Alan Turing Institute, London, UK
Jan 2022 - Mar 2022
Enrichment scheme placement at the Alan Turing Institute
Participated in an online Engage @ Turing scheme since 2020
Applied Scientist Intern
Amazon Web Services, Berlin, Germany
Jul 2021 - Oct 2021
Research in hyperparameter optimization and neural architecture search
Hosted by Giovanni Zappella

Teaching

Teaching Fellow
Cambridge Spark, UK
Jul 2020 - Jun 2024
Content development, teaching and technical mentoring
Teaching Support Provider
The University of Edinburgh, Edinburgh, UK
Oct 2018 - May 2023
Introductory Applied Machine Learning: Tutor, lab demonstrator and marker
Machine Learning Practical: Tutor and lab demonstrator

Software Engineering

Software Development Engineer Intern
Amazon, Edinburgh, UK
Apr 2018 - Aug 2018
Technology Summer Analyst
JPMorgan Chase & Co., Glasgow, UK
Jun 2017 - Aug 2017
Software Engineering Intern
Metaswitch (now part of Microsoft), Edinburgh, UK
May 2016 - Aug 2016

Education

PhD & MSc(R) in Data Science
The University of Edinburgh, Edinburgh, UK
Sep 2018 - Feb 2024
BSc (Hons) Artificial Intelligence and Mathematics
The University of Edinburgh, Edinburgh, UK
Sep 2015 - May 2018
  • Final result: First-Class Honours (90%)
  • Awarded Howe Prize for top performance in UG4 Artificial Intelligence and Class Prize for top performance in BSc (Hons) AI and Mathematics
  • Honours project: Penalizing Confident Neural Networks (supervised by Prof. Steve Renals)
  • Tuition fees fully funded by SAAS and also received a scholarship from Jan Hus Educational Foundation
  • Direct entry to the second year
International Baccalaureate Diploma Programme
Jur Hronec Grammar School, Bratislava, Slovakia
Sep 2013 - May 2015
  • Final result: 44/45 (within the best 1% in the world)
  • Courses: Mathematics, Computer Science, Physics, English, Economics, Slovak Literature
  • Extended essay: Prime Generating Polynomials (Mathematics)

Misc

I often competed and won prizes in various hackathons, including Algothon (quant finance hackathon), QuHackEd (quantum computing hackathon), Data Open (datathon organized by Citadel - I even participated in the Championship), Hack the Burgh and many others. An overview of some of the projects I worked on is available on my Devpost profile, and there are also articles about my teams here and here.

During my high school I very successfully participated in many competitions in Mathematics, Physics and Informatics, in particular the subject Olympiads, correspondence seminars and various team competitions. Most notably I represented Slovakia at the Middle European Mathematical Olympiad in Dresden, Germany in 2014.


Design and source code from Jon Barron's website