Eleni Triantafillou

Researcher@Google·英国·OpenReview

研究方向

few-shot learning · transfer learning · self-supervised learning · domain generalization · domain adaptation · meta-learning · natural language processing · sentence representation learning

5.0

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data

ICLR 2026Poster

通讯

3.5

Should We Forget About Certified Unlearning? Evaluating the Pitfalls of Noisy Methods

ICLR 2026Rejected

二作

3.3

REPO: Detoxifying LLMs via Representation Erasure-based Preference Optimization

ICLR 2026Rejected

二作

7.3

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

NeurIPS 2025Poster

通讯

5.7

Selective Unlearning via Representation Erasure Using Domain Adversarial Training

ICLR 2025Poster

二作

5.0

合作者 (20)

Gintare Karolina Dziugaite

5 篇

Daniel M. Roy

3 篇

Nazanin Mohammadi Sepahvand

Nicole Elyse Mitchell

Eleni Triantafillou

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data

Should We Forget About Certified Unlearning? Evaluating the Pitfalls of Noisy Methods

REPO: Detoxifying LLMs via Representation Erasure-based Preference Optimization

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Selective Unlearning via Representation Erasure Using Domain Adversarial Training

Leveraging Per-Instance Privacy for Machine Unlearning

Improved Localized Machine Unlearning Through the Lens of Memorization

EEVEE and GATE: Finding the right benchmarks and how to run them seamlessly