Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
研究通过MedQA数据集分析了人类干预对多智能体医疗系统诊断准确性的影响，正确干预可提高准确性，错误干预则降低性能。
0 citationsRead paper
Selected work
Representative Papers
Collaborative System Failure Prognostics via Federated Longitudinal-Survival Modeling
This study addresses the challenge of system failure prediction in distributed settings, where data privacy and proprietary constraints hinder the integration of multi-source sensor measurements and time-to-failure information. To overcome this limitation, the authors propose a federated vertical-survival modeling framework that, for the first time, incorporates a separable discrete-time hazard function into federated learning. By combining local temporal representation learning on client devices with global collaborative optimization, the method enables cross-institutional reliability modeling and remaining useful life (RUL) estimation without sharing raw data. This approach circumvents the intractability of directly optimizing traditional Cox models under federated settings. Experiments on the four C-MAPSS turbofan engine datasets demonstrate that the proposed method significantly outperforms locally trained models and achieves performance approaching that of centralized training, even under heterogeneous operating conditions and diverse failure modes.
0 citationsRead paper
Dialectica Categories over Heyting Algebras
This study investigates the algebraic structures and logical properties induced by the categorification of the Dialectica interpretation over Heyting algebras. By specializing de Paiva’s categorical framework to the posetal setting, the authors reconstruct the original construction in purely algebraic terms and demonstrate that the resulting embedding of Heyting algebras into residuated lattices admits a definable adjoint. Key contributions include clarifying the distinct behavior of the single Dialectica tensor with respect to contraction in intuitionistic versus classical logic, and proving that, within ZF set theory, the collapse of the propositional Dialectica construction PD(Set) to PD(2) is equivalent to the Axiom of Choice. The work synthesizes methods from category theory, algebraic logic, and axiomatic set theory, thereby extending the algebraic foundations of Dialectica models and deepening their connections to foundational axiomatic systems.
0 citationsRead paper
Can an AI System Be Creative? A Critical Perspective from Art and Engineering
This study addresses whether artificial intelligence possesses transformative creativity. Drawing on Boden’s tripartite framework of creativity—combinational, exploratory, and transformative—the paper systematically examines the limits of AI’s creative capacities through an interdisciplinary lens integrating philosophical inquiry, artistic practice, and AI theory. It argues that AI, lacking serendipity, openness to意外 (unexpected events), and a situated subjective stance, cannot recognize or meaningfully incorporate genuine accidents, thereby restricting its efficacy primarily to combinational creativity and precluding authentic transformative creativity. As a novel contribution, the work proposes and demonstrates a generative model of human–AI collaborative creation, offering a promising new pathway for expanding the creative applications of artificial intelligence.
0 citationsRead paper
Duality theory and representations for distributive quasi relation algebras and DInFL-algebras
This paper addresses the lack of a duality theory for distributive quasi-relation algebras (DQRA) and involutive FL-algebras, as well as the undecidability of representability. It establishes a systematic duality framework: first, a categorical duality between DQRA and dual involutive FL-algebras (DInFL); second, an ordered relational structure—specifically, a partially ordered frame—for completely perfect algebras, and introduces the novel *bi-pointed Priestley topological frame*, enabling duality extension from completely perfect to arbitrary algebras; third, a complete classification of representability for all algebras of order ≤6. Key contributions include: the first full order-theoretic duality characterizations for both classes; proofs that several algebras are representable as term subreducts of representable relation algebras; and a full representability classification for all algebras up to order six—resolving critical gaps in duality theory and finite representability for relation algebras in algebraic logic.
0 citationsRead paper
Recent publications
Latest Papers
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
研究通过MedQA数据集分析了人类干预对多智能体医疗系统诊断准确性的影响，正确干预可提高准确性，错误干预则降低性能。
0 citationsRead paper
Collaborative System Failure Prognostics via Federated Longitudinal-Survival Modeling
This study addresses the challenge of system failure prediction in distributed settings, where data privacy and proprietary constraints hinder the integration of multi-source sensor measurements and time-to-failure information. To overcome this limitation, the authors propose a federated vertical-survival modeling framework that, for the first time, incorporates a separable discrete-time hazard function into federated learning. By combining local temporal representation learning on client devices with global collaborative optimization, the method enables cross-institutional reliability modeling and remaining useful life (RUL) estimation without sharing raw data. This approach circumvents the intractability of directly optimizing traditional Cox models under federated settings. Experiments on the four C-MAPSS turbofan engine datasets demonstrate that the proposed method significantly outperforms locally trained models and achieves performance approaching that of centralized training, even under heterogeneous operating conditions and diverse failure modes.
0 citationsRead paper
Dialectica Categories over Heyting Algebras
This study investigates the algebraic structures and logical properties induced by the categorification of the Dialectica interpretation over Heyting algebras. By specializing de Paiva’s categorical framework to the posetal setting, the authors reconstruct the original construction in purely algebraic terms and demonstrate that the resulting embedding of Heyting algebras into residuated lattices admits a definable adjoint. Key contributions include clarifying the distinct behavior of the single Dialectica tensor with respect to contraction in intuitionistic versus classical logic, and proving that, within ZF set theory, the collapse of the propositional Dialectica construction PD(Set) to PD(2) is equivalent to the Axiom of Choice. The work synthesizes methods from category theory, algebraic logic, and axiomatic set theory, thereby extending the algebraic foundations of Dialectica models and deepening their connections to foundational axiomatic systems.
0 citationsRead paper
Can an AI System Be Creative? A Critical Perspective from Art and Engineering
This study addresses whether artificial intelligence possesses transformative creativity. Drawing on Boden’s tripartite framework of creativity—combinational, exploratory, and transformative—the paper systematically examines the limits of AI’s creative capacities through an interdisciplinary lens integrating philosophical inquiry, artistic practice, and AI theory. It argues that AI, lacking serendipity, openness to意外 (unexpected events), and a situated subjective stance, cannot recognize or meaningfully incorporate genuine accidents, thereby restricting its efficacy primarily to combinational creativity and precluding authentic transformative creativity. As a novel contribution, the work proposes and demonstrates a generative model of human–AI collaborative creation, offering a promising new pathway for expanding the creative applications of artificial intelligence.
0 citationsRead paper
Duality theory and representations for distributive quasi relation algebras and DInFL-algebras
This paper addresses the lack of a duality theory for distributive quasi-relation algebras (DQRA) and involutive FL-algebras, as well as the undecidability of representability. It establishes a systematic duality framework: first, a categorical duality between DQRA and dual involutive FL-algebras (DInFL); second, an ordered relational structure—specifically, a partially ordered frame—for completely perfect algebras, and introduces the novel *bi-pointed Priestley topological frame*, enabling duality extension from completely perfect to arbitrary algebras; third, a complete classification of representability for all algebras of order ≤6. Key contributions include: the first full order-theoretic duality characterizations for both classes; proofs that several algebras are representable as term subreducts of representable relation algebras; and a full representability classification for all algebras up to order six—resolving critical gaps in duality theory and finite representability for relation algebras in algebraic logic.
0 citationsRead paper