Work by Jinzhou Wu

2Work

Selected publications

  1. Chen, B., Fang, S., Ji, J., Zhu, Y., Wen, P., Wu, J., … & Yao, A. (2025). AI Deception: Risks, Dynamics, and Controls. (core contributor)
  2. Sana, S.*, Wu, J.*, & Wells, M. T. (2026). Pluralistic Preference Alignment via Sortition-Weighted RLHF. ICML 2026 Pluralistic Alignment Workshop. (*equal contribution)
  3. Ying, L., Wu, J., Wang, Y. S., … & Tenenbaum, J. B. (2026). CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition.

Google Scholar

Translations

  1. METR (2026). 对 OpenAI / Hugging Face 入侵事件中智能体行为、推理与协作的简要独立调查. Translated by Wang, A., Li, C., & Wu, J. from Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident.
  2. Eicher, J. E., Elasky, E., Howard-Jones, R., et al. (2026). 我们发现了一批来自腾讯的并行智能体. Translated from We found a Tencent agent fleet. (contributor)

Initiatives