Zhen Bai — accepted AI-conference papers

2026

Beetrap-MC: A Minecraft-Based AI Literacy Tool for Teaching Filter Bubbles to Middle School Students

Erfan Farhadi, Kenneth Fei, Yifan Jiang, Zhen Bai

AAAI 2026technical

Recommendation systems shape much of what people, including youth, encounter online, influencing their exposure to information and ideas. Understanding their workings and potential downsides, such as filter bubbles, is increasingly important. At the same time, Minecraft remains one of the most popul

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning

Chen Qian, Dongrui Liu, Haochen Wen, Zhen Bai, Yong Liu, Jing Shao

NeurIPS 2025poster

Large reasoning models (LRMs) have demonstrated impressive capabilities in complex problem-solving, yet their internal reasoning mechanisms remain poorly understood. In this paper, we investigate the reasoning trajectories of LRMs from an information-theoretic perspective. By tracking how mutual in…

Cited by 0 Source ↗code ↗Scholar ↗