Addison J. Wu

Hey!

I'm a junior (third-year) at Princeton University studying computer science and math, grateful to be advised by Tom Griffiths and Zhuang Liu. I was born in the Bay Area 🌉 but have lived in Kingston, Ontario, Canada 🇨🇦 for my entire life.

This summer, I will be joining the Center for AI Safety as a Research Intern.

I'm interested in human-compatible AI, studying how to make foundation models more robust, safe, and adaptable.

Outside of research, I like to play Wordle, Globle, Travle, GeoGuessr/Geotastic, and the NYT Mini. I love binge-watching off-the-beat travel YouTubers (check out Harry Jaggard, Luke Damant, Britannica, Bald and Bankrupt). My life goal is to defeat the Ender Dragon in Minecraft Survival Mode without cheats.

Publications

Peer-Reviewed

Large Language Models Develop Novel Social Biases Through Adaptive Exploration
Addison J. Wu*, Ryan Liu*, Xuechunzi Bai, Thomas L. Griffiths
ICML 2026 Spotlight; SPSP 2026 Invited Symposia Talk [arXiv]

Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
Addison J. Wu*, Ryan Liu*, Shuyue Stella Li, Yulia Tsvetkov, Thomas L. Griffiths
Agents in the Wild @ ICLR 2026 [arXiv]

Query Timing Produces Opposite Positional Biases Between LLMs and Humans
Jasin Cekinmez*, Addison J. Wu*, Thomas L. Griffiths
ICBINB @ ICLR 2026 Entropic Paper Award [Paper]

Are Large Language Models Sensitive to the Motives Behind Communication?
Addison J. Wu*, Ryan Liu*, Kerem Oktar*, Theodore R. Sumers, Thomas L. Griffiths
NeurIPS 2025; PragLM @ COLM 2025 Oral [Project Page] [arXiv]

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
Ryan Liu*, Jiayi Geng*, Addison J. Wu, Ilia Sucholutsky, Tania Lombrozo, Thomas L. Griffiths
ICML 2025; Press coverage: The Information [Project Page] [arXiv] [text]

Toward a Neural Network-Based Approach for Improved Atmospheric Infrasound Source Localization
Addison J. Wu, Arnav Joshi, Jean-Pierre Hickey
IEEE Access, 2025 [Paper]

Preprints

In Plain Sight, Yet Missed: MLLMs Fail to Use Exact Visual Evidence
Jasin Cekinmez*, Addison J. Wu*, Ryo Mitsuhashi*, Linrong Cai*, Xingyu Fu, Zhuang Liu
under review, 2026

Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
Ryo Mitsuhashi*, Patrick Chen*, Isabelle Tseng*, Jasin Cekinmez*, Addison J. Wu*
under review, 2026