David Williams-King

Researcher, Mila - Quebec Artificial Intelligence Institute

Joined

August 2024

Names

David Williams-King (Preferred)

Emails

****@mila.quebec (Confirmed)

****@gmail.com (Confirmed)

****@columbia.edu (Confirmed)

****@cs.columbia.edu (Confirmed)

Personal Links

Google Scholar

DBLP

Semantic Scholar

Career & Education History

Researcher

Mila - Quebec Artificial Intelligence Institute (mila.quebec)

2024 – Present

PhD student

Computer Science, Columbia University (columbia.edu)

2014 – 2020

MS student

Computer Science, University of British Columbia (ubc.ca)

2012 – 2014

Advisors, Relations & Conflicts

PhD Advisor

Junfeng Yang

2014 – 2020

Expertise

AI safety

2023 – Present

cybersecurity

2014 – Present

speech recognition

2015 – 2020

Publications

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
Linh Le, David Williams-King, Mohamed Amine Merzouk, Aton Kamanda, Adam Oberman
- ICLR 2026 Trustworthy AI
- Readers: Everyone
House, G.P.T.: Diagnosing Pathological Chain-of-Thought in Reasoning Models
Manqing Liu, David Williams-King, Ida Caspary, Linh Le, Hannes Whittingham, Cameron Tice, Puria Radmard, Edward James Young
- Submitted to ICLR 2026
- Readers: Everyone
Latent Personality Alignment: Improving harmlessness without mentioning harms
Linh Le, David Williams-King, Mohamed Amine Merzouk, Aton Kamanda, Adam Oberman
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
Yoshua Bengio, Michael K. Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, Sören Mindermann, Adam Oberman, Jesse Richardson, Oliver Ethan Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King
- arXiv
- Readers: Everyone
Representation Engineering for Large-Language Models: Survey and Research Challenges
Lukasz Bartoszcze, Sarthak Munshi, Bryan Sukidi, Jennifer Yen, Zejia Yang, David Williams-King, Linh Le, Kosi Asuzu, Carsten Maple
- CoRR 2025
- Readers: Everyone
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
Yoshua Bengio, Michael K. Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, Sören Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King
- CoRR 2025
- Readers: Everyone
Time-Series Grid Encoding of Eye-Tracking Data for Explainable AI in Dyslexia Detection
Linh Le, Quoc Toan Nguyen, Nghia Duong-Trung, David Williams-King
- ETRA 2025
- Readers: Everyone
Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
David Williams-King, Linh Le, Adam Oberman, Yoshua Bengio
- CoRR 2025
- Readers: Everyone
Learning Disorder Detection Using Eye Tracking: Are Large Language Models Better Than Machine Learning?
Quoc-Toan Nguyen, Hy Nguyen, Quang Hieu Tang, Tien Truong, Van-Tuan Pham, Linh Le, David Williams-King
- ETRA 2025
- Readers: Everyone
Emotion Recognition Using Text Embedding Models: Wearable and Wireless EEG Without Fixed EEG Channel Configurations
Quoc-Toan Nguyen, Huiru Zheng, Tahia Tazin, Linh Le, Tuan L. Vo, Nhu-Tri Tran, David Williams-King, Benjamin Tag
- UMAP (Adjunct Publication) 2025
- Readers: Everyone

View all 26 publications

Co-Authors

View all 86 co-authors