OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Eyon Jang
Researcher, MATS
Joined
May 2025
Names
Eyon Jang
(Preferred)
,
Yeonwoo Jang
Emails
****@gmail.com
(Confirmed)
,
****@gmail.com
(Confirmed)
,
****@eyonjang.me
(Confirmed)
Personal Links
Homepage
Google Scholar
LinkedIn
Career & Education History
Researcher
MATS
(matsprogram.org)
2025
–
Present
MS student
Statistics,
University of Oxford
(oxford.ac.uk)
2017
–
2018
Undergrad student
Mathematics,
Imperial College London
(imperial.ac.uk)
2014
–
2017
Advisors, Relations & Conflicts
Coworker
Joschka Braun
2025
–
Present
Coworker
Damon Falck
2025
–
Present
PhD Advisor
David Lindner
2025
–
Present
PhD Advisor
Roland S. Zimmermann
2025
–
Present
PhD Advisor
Scott Emmons
2025
–
Present
Coauthor
Diogo Cruz
2025
–
2026
Coauthor
Ashwin Sreevatsa
2025
–
2025
Coauthor
Shariqah Hossain
2025
–
2025
Expertise
ai safety
,
ai
,
machine learning
,
reinforcement learning
,
ai alignment
,
ai control
,
mechanistic interpretability
,
deceptive alignment
2025
–
Present
Publications
Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation
Spencer Gibson
,
Tyler Crosse
,
Magnus Saebo
,
Achyutha Menon
,
Eyon Jang
,
Diogo Cruz
Pluralistic-Alignment 2026
Readers:
Everyone
Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation
Spencer Gibson
,
Tyler Crosse
,
Magnus Saebo
,
Achyutha Menon
,
Eyon Jang
,
Diogo Cruz
AI4GOOD Workshop 2026 Regular
Readers:
Everyone
Asymmetric Goal Drift in Coding Agents Under Value Conflict
Magnus Saebo
,
Spencer Gibson
,
Tyler Crosse
,
Achyutha Menon
,
Eyon Jang
,
Diogo Cruz
LLA 2026 Poster
Readers:
Everyone
Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals
Achyutha Menon
,
Magnus Saebo
,
Tyler Crosse
,
Spencer Gibson
,
Eyon Jang
,
Diogo Cruz
LLA 2026 Poster
Readers:
Everyone
Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals
Achyutha Menon
,
Magnus Saebo
,
Tyler Crosse
,
Spencer Gibson
,
Eyon Jang
,
Diogo Cruz
ICLR 2026 AIWILD
Readers:
Everyone
Asymmetric Goal Drift in Coding Agents Under Value Conflict
Magnus Saebo
,
Spencer Gibson
,
Tyler Crosse
,
Achyutha Menon
,
Eyon Jang
,
Diogo Cruz
ICLR 2026 AIWILD
Readers:
Everyone
Resisting RL Elicitation of Biosecurity Capabilities: Reasoning Models Exploration Hacking on WMDP
Joschka Braun
,
Yeonwoo Jang
,
Damon Falck
,
Roland S. Zimmermann
,
David Lindner
,
Scott Emmons
BioSafe GenAI 2025 Oral
Readers:
Everyone
Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
Yeonwoo Jang
,
Shariqah Hossain
,
Ashwin Sreevatsa
,
Diogo Cruz
COLM 2025 Workshop SoLaR Poster
Readers:
Everyone
Co-Authors
Achyutha Menon
Ashwin Sreevatsa
Damon Falck
David Lindner
Diogo Cruz
Joschka Braun
Magnus Saebo
Roland S. Zimmermann
Scott Emmons
Shariqah Hossain
Spencer Gibson
Tyler Crosse