Ondrej Bohdal

I'm a postdoctoral researcher in machine learning at the University of Edinburgh. My research focuses on topics such as multimodal large language models, fairness, uncertainty calibration, 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 / CV

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, hyperparameter optimization (HPO) and neural architecture search (NAS). I work with images (computer vision) and text (natural language processing).

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
Under review, 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

PASHA: Efficient HPO and NAS with Progressive Resource Allocation
Ondrej Bohdal, Lukas Balles, Martin Wistuba, Beyza Ermis, Cédric Archambeau, Giovanni Zappella
ICLR, 2023
paper / code / tutorial / video / slides

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

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

	Postdoctoral Research Associate The University of Edinburgh, Edinburgh, UK May 2023 - Current Research in multimodal large language models, fairness, uncertainty calibration, domain generalization 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 - Current 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 PhD thesis: Meta-Learning Algorithms and Applications (supervised by Prof. Timothy Hospedales) MSc(R) thesis: Multi-Domain Meta-Learning (same supervisor) MSc(R) result: Distinction Fully funded by a highly competitive scholarship from EPSRC - CDT in Data Science Reviewer at top ML and CV conferences, including NeurIPS, ICML, ICLR, CVPR Participated in several ML summer schools: MLSS'22, OxML'22, CIFAR DLRL'21, EEML'21 , OxML'20 EdIntelligence (ML/AI society): mini-conference organizer
	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