|
Ondrej Bohdal
I'm a senior artificial intelligence researcher at Samsung
Research, where I focus on post-training, agentic AI and model efficiency. 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  / 
LinkedIn  / 
Github  / 
London, UK
Research Overview
/
Publications
/
Background
|
|
Research Topics
|
|
I've worked on topics within deep learning, including generative AI (large language models and diffusion models), post-training, agentic AI, agentic memory, model merging, model efficiency, meta-learning, data efficiency, out-of-distribution generalization, uncertainty calibration, fairness. I work with text (natural language processing) and images (computer vision).
|
Selected Publications
|
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli
ACL (oral), 2026
paper
/
project page
/
code
/
blog
|
CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models
Peyman Hosseini, Ondrej Bohdal, Taha Ceritli, Ignacio Castro, Matthew Purver, Mete Ozay, Umberto Michieli
TACL, 2026
paper
/
blog
|
Efficient Compositional Multi-tasking for On-device Large Language Models
Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli
EMNLP, 2025
paper
/
project page
/
code
/
blog
|
LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image
Generation
Donald Shenaj, Ondrej Bohdal, Mete Ozay, Pietro Zanuttigh, Umberto Michieli
ICCV, 2025
Short version won the best paper award at the ICCV 2025 Personalization in Generative AI Workshop!
paper
/
project page
/
code
/
blog
|
VL-ICL Bench: The Devil in the Details of Benchmarking Multimodal In-Context Learning
Yongshuo Zong*, Ondrej Bohdal*, Timothy Hospedales
* Joint first authors
ICLR, 2025
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
|
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
|
|