Xiaowen Dong

Associate Professor, University of Oxford

Joined

March 2018

Names

Xiaowen Dong

Emails

****@eng.ox.ac.uk (Confirmed)

****@robots.ox.ac.uk (Confirmed)

****@mit.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Associate Professor

University of Oxford (ox.ac.uk)

2021 – Present

Assistant Professor

University of Oxford (ox.ac.uk)

2017 – 2021

Postdoc

Massachusetts Institute of Technology (mit.edu)

2014 – 2017

PhD student

EPFL - EPF Lausanne (epfl.ch)

2009 – 2014

Advisors, Relations & Conflicts

Postdoc Advisor

Alex Pentland

2014 – 2017

PhD Advisor

Pascal Frossard

2009 – 2014

PhD Advisor

Pierre Vandergheynst

2009 – 2014

Expertise

graph signal processing

Present

graph representation learning

Present

Publications

Can Graph Foundation Models Generalize Over Architecture?
Benjamin Gutteridge, Michael M. Bronstein, Xiaowen Dong
- ICLR 2026 Workshop GRaM Poster
- Readers: Everyone
k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS
Jonas De Schouwer, Haitz Sáez de Ocáriz Borde, Xiaowen Dong
- ICLR 2026 Workshop GRaM Poster
- Readers: Everyone
Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning
Haitz Sáez de Ocáriz Borde, Artem Lukoianov, Anastasis Kratsios, Michael M. Bronstein, Xiaowen Dong
- ICLR 2026 Workshop GRaM Poster
- Readers: Everyone
A Survey on Over-smoothing and Over-squashing: Unified Propagation Perspectives on Graph Neural Networks and Transformers
Alvaro Arroyo, Federico Barbero, Hugh Blayney, Michael M. Bronstein, Xiaowen Dong, Pietro Lio, Razvan Pascanu, Pierre Vandergheynst
- Accepted by TMLR
- Readers: Everyone
Bridging Graph Neural Networks and Large Language Models: A Survey and Unified Perspective
Alvaro Arroyo, Federico Barbero, Hugh Blayney, Michael M. Bronstein, Xiaowen Dong, Pietro Lio, Razvan Pascanu, Pierre Vandergheynst
- OpenReview Preprint
- Readers: Everyone
Spectral Clustering for Directed Graphs via Likelihood Estimation on Stochastic Block Models
Ning Zhang, Xiaowen Dong, Mihai Cucuringu
- AISTATS 2026 Poster
- Readers: Everyone
Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription
Benjamin Gutteridge, Matthew Thomas Jackson, Toni Kukurin, Xiaowen Dong
- Submitted to ICLR 2026
- Readers: Everyone
Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
Enrique Queipo-de-Llano, Alvaro Arroyo, Federico Barbero, Xiaowen Dong, Michael M. Bronstein, Yann LeCun, Ravid Shwartz-Ziv
- ICLR 2026 Poster
- Readers: Everyone
gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity
Hugh Blayney, Alvaro Arroyo, Xiaowen Dong, Michael M. Bronstein
- ICLR 2026 Poster
- Readers: Everyone
Bures-Wasserstein Flow Matching for Graph Generation
Keyue Jiang, Jiahao Cui, Xiaowen Dong, Laura Toni
- ICLR 2026 Poster
- Readers: Everyone

View all 171 publications

Co-Authors

View all 161 co-authors