News

• Our position paper "We Should Distinguish Unlearning from Untraining" (Triantafillou, Humayun, Ribero, Turner, Mozer and Kaissis) is accepted for an oral presentation at NeurIPS'26 (0.5% of papers)
• I served as a Program Chair for CoLLAs'26, together with Martin Mundt.
• I gave a keynote at CoLLAs'24 titled "Are we making progress in machine unlearning?" [slides].
• The recording and slides of our CVPR'24 tutorial on unlearning are now available here.
• We released a preprint describing the metric and findings from the first NeurIPS unlearning competition.
• I co-led the organization of the first NeurIPS competition on unlearning [website], hosted at NeurIPS'23.
• The recording of my NeurIPS 2022 tutorial about the role of meta-learning in few-shot learning is now available.
• I am co-organizing the NeurIPS 2022 workshop on meta-learning.
• I gave an invited talk at the NeurIPS 2021 workshop on meta-learning.
• I defended my PhD thesis in the summer of 2021 and have started working as a Research Scientist in Google Brain, based in London UK.

About me

I'm a senior research scientist at Google DeepMind, based in London UK. My main research interest is around creating methods that allow efficient and effective adaptation of deep neural networks to cope with distribution shifts, rapidly learning new tasks, and supporting efficient unlearning of data points. My research falls in the areas of few-shot learning, meta-learning, domain adaptation and machine unlearning.

Selected publications

We Should Distinguish Unlearning from Untraining
Eleni Triantafillou, Ahmed Imtiaz Humayun, Monica Ribero, Alexander Matt Turner, Micahel Curtis Mozer and Georgios Kaissis. NeurIPS 2026, oral. [paper].

Step-resolved data attribution for looped transofmers
Georgios Kaissis, David Mildenberger, Juan Felipe Gomez, Martin J. Menten and Eleni Triantafillou. ICML 2026. [paper].

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
Kairan Zhao, Eleni Triantafillou and Peter Triantafillou. ICML 2026. [paper].

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
Stefan Schoepf, Michael Curtis Mozer, Nicole Elyse Mitchell, Alexandra Brintrup, Georgios Kaissis, Peter Kairouz and Eleni Triantafillou. ICLR 2026. [paper].

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger, Gintare Karolina Dziugaite, Michael Curtis Mozer and Eleni Triantafillou. NeurIPS 2025. [paper].

Improved Localized Machine Unlearning Through the Lens of Memorization
Reihaneh Torkzadehmahani, Reza Nasirigerdeh, Georgios Kaissis, Daniel Rueckert, Gintare Karolina Dziugaite and Eleni Triantafillou. TMLR 2025. [paper].

Selective Unlearning Via Representation Erasure Using Domain Adversarial Training
Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, James J. Clark, Daniel M. Roy, Gintare Karolina Dziugaite. ICLR 2025. [paper].

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
Jamie Hayes, Ilia Shumailov, Eleni Triantafillou, Amr Khalifa and Nicolas Papernot. SaTML 2025. [paper].

What makes unlearning hard and what to do about it
Kairan Zhao, Meghdad Kurmanji, George-Octavian Barbulescu, Eleni Triantafillou* and Peter Triantafillou*. NeurIPS 2024. [paper].

Machine Unlearning in Learned Databases: An Experimental Analysis
Meghdad Kurmanji, Eleni Triantafillou and Peter Triantafillou. SIGMOD 2024. [paper].

Towards Unbounded Machine Unlearning
Meghdad Kurmanji, Peter Triantafillou, Jamie Hayes and Eleni Triantafillou. NeurIPS 2023. [paper].

In Search for a Generalizable Method for Source Free Domain Adaptation
Malik Boudiaf, Tom Denton, Bart van Merriënboer, Vincent Dumoulin* and Eleni Triantafillou*. ICML 2023. [paper].

Learning a Universal Template for Few-shot Dataset Generalization.
Eleni Triantafillou, Hugo Larochelle, Richard Zemel and Vincent Dumoulin. ICML 2021. [paper].

Meta-dataset: A dataset of datasets for learning to learn from few examples.
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol and Hugo Larochelle. ICLR 2020. [paper].

Meta Learning for Semi-Supervised Few-Shot Classification.
Mengye Ren, Eleni Triantafillou*, Sachin Ravi*, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle and Richard Zemel. ICLR 2018. [paper]

Few-Shot Learning Through an Information Retrieval Lens.
Eleni Triantafillou, Richard Zemel and Raquel Urtasun. NeurIPS 2017. [paper]

Non-Deterministic Planning with Temporally Extended Goals: LTL over finite and infinite traces.
Alberto Camacho, Eleni Triantafillou, Christian Muise, Jorge Baier, and Sheila McIlraith. AAAI, 2017. [paper]

Selected preprints and workshop papers

Position: Capability Control Should be a Separate Goal from Alignment.
Shoaib Ahmed Siddiqui, Eleni Triantafillou, David Krueger, Adrian Weller. 2026. [paper].

Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition.
Eleni Triantafillou, Peter Kairouz, Fabian Pedregosa, Jamie Hayes, Meghdad Kurmanji, Kairan Zhao, Vincent Dumoulin, Julio Jacques Junior, Ioannis Mitliagkas, Jun Wan, Lisheng Sun Hosoya, Sergio Escalera, Gintare Karolina Dziugaite, Peter Triantafillou, Isabelle Guyon. 2024. [paper].

Data Selection for Transfer Unlearning
Nazanin Mohammadi Sepahvand, Vincent Dumoulin, Eleni Triantafillou*, Gintare Karolina Dziugaite∗. 2024. [paper].

Flexible Few-Shot Learning with Contextual Similarity.
Mengye Ren*, Eleni Triantafillou*, Kuan-Chieh Wang*, James Lucas*, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard Zemel. 2020. [paper].

Few-shot Learning for Free by Modelling Global Class Structure.
Xuechen Li*, Will Grathwohl*, Eleni Triantafillou*, David Duvenaud, Richard Zemel. Meta-learning workshop at NeurIPS 2018. [paper].

Towards Generalizable Sentence Embeddings
Eleni Triantafillou, Jamie Ryan Kiros, Raquel Urtasun, Richard Zemel.
1st Workshop on Representation Learning for NLP at ACL 2016. [paper]

A Unifying Framework for Planning with LTL and Regular Expressions
Eleni Triantafillou, Jorge A. Baier, Sheila A. McIlraith.
MOCHAP workshop at ICAPS 2015. [paper]

Community Service

• Program Chair for CoLLAs 2026.
• Area chair for NeurIPS, ICLR, ICML continuously since 2025.
• Associate Program Chair for CoLLAs 2025.
• Action Editor for TMLR since 2024.
• Area chair for AutoML 2022 and 2023.
• Reviewer for NeurIPS: 2018 (top 10%), 2019, 2020 (top 10%), 2021 (top 8%), 2022, 2023, 2024.
• Reviewer for ICML: 2019 (top 5%), 2020, 2021 (expert reviewer), 2022, 2023, 2024.
• Reviewer for ICLR: 2019, 2020, 2021 (outstanding reviewer), 2022, 2023 (notable reviewer), 2024
• Reviewer for CVPR 2021, UAI 2018, IROS 2021, TMLR between 2022-2024 (recognized as expert reviewer)