Selected work

Representative Papers

ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation

Apr 24, 2026

This work addresses the lack of explicit, auditable conflict resolution mechanisms in existing multi-agent requirement negotiation approaches, which hinders compliance with transparency demands in highly regulated contexts. The paper introduces Dung’s abstract argumentation framework into requirements engineering for the first time, modeling proposals, critiques, and refinements as argument nodes, with attack relations capturing conflicts. Acceptable argument sets are derived using grounded and preferred semantics, integrated within a structured negotiation process that combines KAOS goal modeling and multi-layer validation. The approach provides argument-level traceability and enables automatic generation of standards-compliant artifacts. Empirical results demonstrate significantly superior traceability over baselines, higher decision rationality (4.32 vs. 3.07, p<0.001), 94.9% BERTScore semantic retention, and improved compliance coverage at 84.7% compared to baseline ranges of 47.6%–47.8%.

0 citationsRead paper

BasketLiDAR: The First LiDAR-Camera Multimodal Dataset for Professional Basketball MOT

Aug 21, 2025

To address the accuracy and real-time performance bottlenecks in multi-object tracking (MOT) for basketball—caused by high-density occlusion and complex, rapid motion—this paper introduces the first synchronized LiDAR–multi-view camera multimodal basketball dataset and proposes a novel 3D spatially aware tracking framework. It pioneers the integration of LiDAR into sports MOT, enabling centimeter-accurate 3D pose annotation and cross-modal identity-consistent alignment. We design a lightweight, real-time pure-LiDAR tracking pipeline alongside a deeply fused LiDAR–camera tracking strategy. Evaluated on 4,445 frames from real matches, our method achieves real-time inference (≥30 FPS) and improves MOTA by 12.7% under severe occlusion, significantly outperforming state-of-the-art vision-only approaches. This work establishes a new paradigm for robust, real-time 3D MOT in highly dynamic sports scenarios.

0 citationsRead paper

An Asymptotic Equation Linking WAIC and WBIC in Singular Models

May 20, 2025

In singular statistical models—such as those with latent variables or hierarchical structures—classical information criteria (AIC/BIC) fail due to the breakdown of normal approximations to the likelihood and posterior. Although WAIC and WBIC were proposed for Bayesian model selection in such settings, they require computationally expensive multi-temperature posterior sampling. Method: Leveraging singular learning theory, we conduct rigorous Bayesian asymptotic analysis combined with temperature-scaled posterior modeling. Contribution/Results: We establish, for the first time, an asymptotic equivalence relation between WAIC and WBIC in singular models. This theoretical result implies that WAIC can be unbiasedly estimated using only the single-temperature posterior samples required for WBIC—eliminating the need for additional sampling. Our analysis not only uncovers a fundamental structural connection between WAIC and WBIC but also yields a computationally efficient, theoretically grounded approach to model selection in singular settings.

0 citationsRead paper

Recent publications

Latest Papers

ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation

Apr 24, 2026

This work addresses the lack of explicit, auditable conflict resolution mechanisms in existing multi-agent requirement negotiation approaches, which hinders compliance with transparency demands in highly regulated contexts. The paper introduces Dung’s abstract argumentation framework into requirements engineering for the first time, modeling proposals, critiques, and refinements as argument nodes, with attack relations capturing conflicts. Acceptable argument sets are derived using grounded and preferred semantics, integrated within a structured negotiation process that combines KAOS goal modeling and multi-layer validation. The approach provides argument-level traceability and enables automatic generation of standards-compliant artifacts. Empirical results demonstrate significantly superior traceability over baselines, higher decision rationality (4.32 vs. 3.07, p<0.001), 94.9% BERTScore semantic retention, and improved compliance coverage at 84.7% compared to baseline ranges of 47.6%–47.8%.

0 citationsRead paper

BasketLiDAR: The First LiDAR-Camera Multimodal Dataset for Professional Basketball MOT

Aug 21, 2025

To address the accuracy and real-time performance bottlenecks in multi-object tracking (MOT) for basketball—caused by high-density occlusion and complex, rapid motion—this paper introduces the first synchronized LiDAR–multi-view camera multimodal basketball dataset and proposes a novel 3D spatially aware tracking framework. It pioneers the integration of LiDAR into sports MOT, enabling centimeter-accurate 3D pose annotation and cross-modal identity-consistent alignment. We design a lightweight, real-time pure-LiDAR tracking pipeline alongside a deeply fused LiDAR–camera tracking strategy. Evaluated on 4,445 frames from real matches, our method achieves real-time inference (≥30 FPS) and improves MOTA by 12.7% under severe occlusion, significantly outperforming state-of-the-art vision-only approaches. This work establishes a new paradigm for robust, real-time 3D MOT in highly dynamic sports scenarios.

0 citationsRead paper

An Asymptotic Equation Linking WAIC and WBIC in Singular Models

May 20, 2025

In singular statistical models—such as those with latent variables or hierarchical structures—classical information criteria (AIC/BIC) fail due to the breakdown of normal approximations to the likelihood and posterior. Although WAIC and WBIC were proposed for Bayesian model selection in such settings, they require computationally expensive multi-temperature posterior sampling. Method: Leveraging singular learning theory, we conduct rigorous Bayesian asymptotic analysis combined with temperature-scaled posterior modeling. Contribution/Results: We establish, for the first time, an asymptotic equivalence relation between WAIC and WBIC in singular models. This theoretical result implies that WAIC can be unbiasedly estimated using only the single-temperature posterior samples required for WBIC—eliminating the need for additional sampling. Our analysis not only uncovers a fundamental structural connection between WAIC and WBIC but also yields a computationally efficient, theoretically grounded approach to model selection in singular settings.

0 citationsRead paper