Mariya Hendriksen

I am a Research Fellow at the University of Oxford, working with Philip Torr and ʻŌiwi Parker Jones. My broader research interests span multimodal machine learning, with a focus on representation learning, evaluation, and trustworthiness. I am a member of the ELLIS society, an Encode AI for Science Fellow, and an incoming Junior Research Fellow at Kellogg College.

I earned my PhD in Artificial Intelligence at the University of Amsterdam, advised by Maarten de Rijke and Paul Groth, following a MSc in AI from KU Leuven with Marie-Francine Moens. My work has been shaped by research positions across industry, including the Gemini team at Google DeepMind, Microsoft Research, Bloomberg AI, and Amazon Science. Beyond research, I work to make the ML and broader STEM community more inclusive: I served as General Chair for the WiML at ICML 2025, organize the WiML Mentorship Program, serve on the committee of the Piscopia Initiative's Oxford branch, and mentored through the ELLIS Inclusive AI initiative.

Email / Scholar / GitHub / Bsky / X

Updates

(Mar 2026) Presenting 'Adapting Vision-Language Models for Evaluating World Models' at CoAStaL NLP at the University of Copenhagen.
(Nov 2025) Presenting 'Adapting Vision-Language Models for Evaluating World Models' at NeurIPS LAW 2025 as an Oral.
(Sep 2025) Presenting 'Adapting Vision-Language Models for Evaluating World Models' at CMU as a Spotlight.
(Sep 2025) Presenting 'Image-Seeking Intent Prediction for Cross-Device Product Search' at RecSys Gen AI for E-commerce 2025 as an Oral.
(Aug 2025) Started as a Research Fellow at the University of Oxford, working with Philip Torr and Oiwi Parker Jones.
(Apr 2025) Our paper 'Benchmark Granularity and Model Robustness for Image-Text Retrieval' accepted at SIGIR 2025.
(Apr 2025) Serving as the General Chair for the Women in Machine Learning symposium at ICML 2025.
(Sep 2024) Started a research internship at Microsoft Research on the Game Intelligence team.
(Jul 2024) Our paper 'Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning' accepted at TMLR.
(Apr 2024) Started a research internship with the Gemini team.
(Jul 2023) Started a research internship at Bloomberg AI with the Question Answering team.
(Oct 2022) Started a research internship at Amazon Science.

Research

	Adapting Vision-Language Models for Evaluating World Models. Mariya Hendriksen, Tabish Rashid, David Bignell, Raluca Georgescu, Abdelhak Lemkhenter, Katja Hoffman, Sam Devlin, Sarah Parisot Oral at NeurIPS LAW 2025; Under submission arXiv / GitHub We focus on the challenge of automated evaluation for world model rollouts and introduce a structured semantic protocol for this domain. We also propose UNIVERSE, a method for efficient adaptation of VLMs to this scenario.
	Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning. Maurits Bleeker, Mariya Hendriksen, Andrew Yates, Maarten de Rijke TMLR, 2024 arXiv / bibtex / GitHub We propose a framework to examine the shortcut learning problem in the context of Vision-Language contrastive representation learning with multiple captions per image. We show how this problem can be partially mitigated using a form of text reconstruction and implicit feature modification.
	Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control. Thong Nguyen, Mariya Hendriksen, Andrew Yates, Maarten de Rijke ECIR, 2024 arXiv / GitHub We propose a framework for multimodal learned sparse retrieval.
	Scene-Centric vs. Object-Centric Image-Text Cross-Modal Retrieval: A Reproducibility Study. Mariya Hendriksen, Svitlana Vakulenko, Ernst Kuiper, Maarten de Rijke ECIR, 2023 arXiv / GitHub
	Extending CLIP for Category-to-Image Retrieval in E-commerce . Mariya Hendriksen, Maurits Bleeker, Svitlana Vakulenko, Nanne van Noord, Maarten de Rijke ECIR, 2022 arXiv / GitHub
	Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers. Mariya Hendriksen, Ernst Kuiper, Pim Nauts, Sebastian Schelter, Maarten de Rijke SIGIR eCom, 2020 arXiv / related work