Qianpu Chen

Hidden hateful illusions can be detected with over 93% accuracy using a novel adaptive retrieval approach, revealing the limitations of current moderation systems.

Forget complex communication protocols – this trust-based algorithm lets agents learn to cooperate in competitive environments with minimal overhead.

Face pareidolia reveals that a vision model's behavior under ambiguity is governed more by representational choices than score thresholds, and that low uncertainty can signal either safe suppression or extreme over-interpretation.