TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
本文提出TetrisCNN,一种具有不同形状滤波器的卷积架构,用于从实验量子模拟器数据中检测物质相,并通过可解释的潜在表示揭示其属性。
本文提出TetrisCNN,一种具有不同形状滤波器的卷积架构,用于从实验量子模拟器数据中检测物质相,并通过可解释的潜在表示揭示其属性。
研究重新思考了教师-学生框架在测试时适应中的应用,通过使用不更新权重的顽固教师来解决长期稳定性问题,从而提高性能和鲁棒性。
针对病理图像中模型对数据缺陷的脆弱性问题,提出使用'Destroy Me'框架合成真实瑕疵并增强数据鲁棒性,提高诊断准确性。
研究探讨了大型语言模型在神经发育障碍评估中的人类还原论偏差和决策不一致问题,通过比较人类专家与语言模型的决策一致性、认知启发式易感性等方法。
This study addresses the current lack of longitudinal empirical research evaluating whether large language models (LLMs) exacerbate the risk of AI-induced psychosis in scenarios involving the progressive escalation of delusional content. Employing a 30-day longitudinal qualitative design, the authors conducted a multidimensional analysis of 449 model-day interactions across 15 mainstream LLMs simulating the evolution of psychotic thought processes, integrating human ratings from four trained annotators with computational metrics such as entrainment and modality. The work introduces and validates four distinct LLM response trajectories: premature medicalization and disengagement, unprotected recognition, delayed unstable recognition, and delusion co-construction. Furthermore, it proposes a three-dimensional operational framework—timing of recognition, stability, and intervention accuracy—to quantify the risk of AI psychosis exacerbation, revealing that most models exhibit varying degrees of potential risk.
本文提出TetrisCNN,一种具有不同形状滤波器的卷积架构,用于从实验量子模拟器数据中检测物质相,并通过可解释的潜在表示揭示其属性。
研究重新思考了教师-学生框架在测试时适应中的应用,通过使用不更新权重的顽固教师来解决长期稳定性问题,从而提高性能和鲁棒性。
针对病理图像中模型对数据缺陷的脆弱性问题,提出使用'Destroy Me'框架合成真实瑕疵并增强数据鲁棒性,提高诊断准确性。
研究探讨了大型语言模型在神经发育障碍评估中的人类还原论偏差和决策不一致问题,通过比较人类专家与语言模型的决策一致性、认知启发式易感性等方法。
This study addresses the current lack of longitudinal empirical research evaluating whether large language models (LLMs) exacerbate the risk of AI-induced psychosis in scenarios involving the progressive escalation of delusional content. Employing a 30-day longitudinal qualitative design, the authors conducted a multidimensional analysis of 449 model-day interactions across 15 mainstream LLMs simulating the evolution of psychotic thought processes, integrating human ratings from four trained annotators with computational metrics such as entrainment and modality. The work introduces and validates four distinct LLM response trajectories: premature medicalization and disengagement, unprotected recognition, delayed unstable recognition, and delusion co-construction. Furthermore, it proposes a three-dimensional operational framework—timing of recognition, stability, and intervention accuracy—to quantify the risk of AI psychosis exacerbation, revealing that most models exhibit varying degrees of potential risk.