Hi! I'm a third-year PhD student in machine learning & computer vision at Queen Mary University of London (QMUL), working with Ioannis Patras, Mihalis A. Nicolaou, and Yannis Panagakis. From August I am joining UW Madison as a Visiting Scholar with Grigorios Chrysos. Previously, I was fortunate enough to intern at both Huawei Noah's Ark Lab London and The Cyprus Institute.

My PhD research focuses on interpretable and controllable models. I'm interested in both discovering interpretable mechanisms in existing models and designing new layers/architectures that better exhibit such properties from the outset.

News

• [2024.06] One paper (extending our ICLR'23 work) accepted at TPAMI
• [2023.09] One paper (on semantic subspaces in vision-language models) accepted at NeurIPS'23
• [2023.07] Started as a PhD Research Intern with Jiankang Deng at Huawei R&D UK
• [2023.01] One paper (on parts/appearance decomposition in GANs) accepted at ICLR'23
• [2021.09] Started as a PhD student at QMUL

Selected publications

• "Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization"
  J. Oldfield, M. Georgopoulos, G. G. Chrysos, C. Tzelepis, Y. Panagakis, M. A. Nicolaou, J. Deng, I. Patras
  ArXiv, 2024
  [pdf | code | project page]
• "Parts of Speech–Grounded Subspaces in Vision-Language Models"
  J. Oldfield, C. Tzelepis, Y. Panagakis, M. A. Nicolaou, I. Patras
  NeurIPS, 2023
  [pdf | code | project page]
• "PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs"
  J. Oldfield, C. Tzelepis, Y. Panagakis, M. A. Nicolaou, I. Patras
  ICLR, 2023
  [pdf | code | project page]
• "Tensor methods in computer vision and deep learning"
  Y. Panagakis, J. Kossaifi, G. G. Chrysos, J. Oldfield, M. A. Nicolaou, A. Anandkumar, S. Zafeiriou
  Proceedings of the IEEE, 2021
  [pdf | code]

Experience

• [2023.07–2024.01] Research Intern (Huawei Noah's Ark Lab)
• [2019.11–2020.09] Machine Learning Research Intern (The Cyprus Institute)

Invited talks

• [2024.06] Tensor Decompositions in Large Scale Deep Learning (Archimedes Research Unit)

Teaching

• [2024–2024] (QMUL; TA) Deep Learning and Computer Vision (ECS795P)
• [2021–2022] (QMUL; TA) Machine Learning (ECS708)
• [2021–2021] (QMUL; TA) Artificial Intelligence (ECS629)

Awards

• [2021] Full EPSRC Studentship (QMUL): 3.5 years' PhD funding
• [2018] Academic Excellence (£50; HEAR): Ranked #1 in CS department for undergrad