Addison J. Wu

Hey!

I'm a rising senior (fourth-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 🌉 and have lived in Kingston, Ontario, Canada 🇨🇦 for most of my life.

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

I'm interested in how humans and AI co-adapt, for better or worse. To this end, I work on understanding the effects of data and building evaluations that let us trace how these dynamics unfold.

Outside of research, I like to play Wordle, Globle, Travle, GeoGuessr/Geotastic, and the NYT Mini. I love binge-watching travel YouTubers who go off the beaten path (check out Harry Jaggard, Luke Damant, Britannica, Bald and Bankrupt). I'm working my way toward joining the Travelers' Century Club (currently at 22)!

Publications

Conference/Journal Papers

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

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 [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 [arXiv]; Press coverage: The Information [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]

Workshop Papers

Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
Ryo Mitsuhashi*, Patrick Chen*, Isabelle Tseng*, Jasin Cekinmez*, Addison J. Wu*
Workshop on Combining Benchmarks and Theory @ ICML 2026 [arXiv]

OccludeBench: Can VLMs See the Hint?
Jasin Cekinmez*, Addison J. Wu*, Ryo Mitsuhashi*, Linrong Cai, Xingyu Fu, Zhuang Liu
Computer Vision in the Wild @ CVPR 2026

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]; Press coverage: Hacks/Hackers, The Indian Express

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]

Preprints

Guess the Unified Model: How Much Can We Recover from Generated Images?
Jasin Cekinmez*, Ryo Mitsuhashi*, Addison J. Wu*, Yida Yin
under review, 2026 [arXiv]