Phil Blunsom

Chief Scientist, Cohere

Joined

September 2016

Names

Phil Blunsom (Preferred)

Emails

****@google.com (Confirmed)

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

****@deepmind.com (Confirmed)

****@cohere.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Chief Scientist

Cohere (cohere.com)

2022 – Present

Associate Professor

Department of Computer Science, University of Oxford (cs.ox.ac.uk)

2009 – 2024

Research Scientist

Google (google.com)

2014 – 2021

Research Scientist

DeepMind (deepmind.com)

2014 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

Natural Language Processing

Machine Learning

Present

Publications

Aya Vision: Advancing the Frontier of Multilingual Multimodality
Saurabh Dash, Yiyang Nan, John Dang, Arash Ahmadian, Shivalika Singh, Madeline Smith, Bharat Venkitesh, Vladyslav Shmyhlo, Viraat Aryabumi, Walter Beller-Morales, Jeremy Pekmez, Jason Ozuzu, Pierre Harvey Richemond, Acyr Locatelli, Nicholas Frosst, Phil Blunsom, Aidan Gomez, Ivan Zhang, Marzieh Fadaee, Manoj Govindassamy et al. (5 additional authors not shown)
- Submitted to ICLR 2026
- Readers: Everyone
Rope to Nope and Back Again: A New Hybrid Attention Strategy
Bowen Yang, Bharat Venkitesh, Dwaraknath Gnaneshwar, Hangyu Lin, David Cairuz, Phil Blunsom, Acyr Locatelli
- NeurIPS 2025 poster
- Readers: Everyone
Aya Vision: Advancing the Frontier of Multilingual Multimodality
Saurabh Dash, Yiyang Nan, John Dang, Arash Ahmadian, Shivalika Singh, Madeline Smith, Bharat Venkitesh, Vladyslav Shmyhlo, Viraat Aryabumi, Walter Beller-Morales, Jeremy Pekmez, Jason Ozuzu, Pierre Harvey Richemond, Acyr Locatelli, Nicholas Frosst, Phil Blunsom, Aidan Gomez, Ivan Zhang, Marzieh Fadaee, Manoj Govindassamy et al. (5 additional authors not shown)
- Submitted to NeurIPS 2025
- Readers: Everyone
Uncertainty-Aware Step-wise Verification with Generative Reward Models
Zihuiwen Ye, Luckeciano Carvalho Melo, Younesse Kaddar, Phil Blunsom, Sam Staton, Yarin Gal
- QUESTION Poster
- Readers: Everyone
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
Qizhen Zhang, Nikolas Gritsch, Dwaraknath Gnaneshwar, Simon Guo, David Cairuz, Bharat Venkitesh, Jakob Nicolaus Foerster, Phil Blunsom, Sebastian Ruder, Ahmet Üstün, Acyr Locatelli
- ES-FoMo-II 2024 Poster
- Readers: Everyone
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
Qizhen Zhang, Nikolas Gritsch, Dwaraknath Gnaneshwar, Simon Guo, David Cairuz, Bharat Venkitesh, Jakob Nicolaus Foerster, Phil Blunsom, Sebastian Ruder, Ahmet Üstün, Acyr Locatelli
- NeurIPS 2024 poster
- Readers: Everyone
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
Satwik Bhattamishra, Michael Hahn, Phil Blunsom, Varun Kanade
- NeurIPS 2024 poster
- Readers: Everyone
The Next Symbol Prediction Problem: PAC-learning and its relation to Language Models
Satwik Bhattamishra, Phil Blunsom, Varun Kanade
- NeurIPS 2023 Workshop M3L Withdrawn Submission
- Readers: Everyone
Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
Satwik Bhattamishra, Arkil Patel, Phil Blunsom, Varun Kanade
- R0-FoMo Spotlight
- Readers: Everyone
Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
Satwik Bhattamishra, Arkil Patel, Phil Blunsom, Varun Kanade
- ICLR 2024 oral
- Readers: Everyone

View all 135 publications

Co-Authors

View all 208 co-authors