Selected work

Representative Papers

PHOENIX: Fine-Tuned SLM-Powered Autonomous Satellite Lifetime Extension via Predictive Self-Healing and Multi-Agent AI Recovery

Aug 07, 2026

This study addresses the premature failure of low Earth orbit CubeSats caused by undetected faults during communication blackout periods. The authors propose a space-ground collaborative autonomous fault-recovery framework: a fine-tuned small language model (SLM) equipped with a memory-augmented mechanism is deployed on an onboard embedded platform (Aethero NxN-ECM) to enable continuous monitoring and autonomous reasoning over sensor data; meanwhile, a ground-based multi-agent system generates repair commands during brief communication windows and leverages a denoising diffusion probabilistic model (DDPM) to synthesize scarce fault data, thereby enhancing training efficacy. This approach represents the first integration of memory-augmented SLMs with multi-agent cooperative recovery, achieving significant improvements in fault detection accuracy and in-orbit recovery efficiency on the ESA 14-year anomaly detection benchmark dataset comprising 76 telemetry channels and 118 annotated faults.

0 citationsRead paper

Custom-made Gauss quadrature: an introduction for statisticians

Jul 15, 2026

This work addresses the absence of readily available Gaussian quadrature rules for nonclassical weight functions by proposing a general framework that constructs such rules for arbitrary weights via the method of moments and the Stieltjes procedure. Innovatively integrating type-generic programming with adaptive high-precision arithmetic, the approach effectively controls round-off errors and, for the first time, systematically introduces tailored Gaussian quadrature methods to the statistics community. Implemented in Julia as the CustomGaussQuadrature package—accessible from R through JuliaConnectoR—the resulting quadrature rules achieve exact integration of polynomials up to degree \(2n-1\) while substantially reducing the number of function evaluations, thereby offering both high accuracy and computational efficiency.

0 citationsRead paper

VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

Jul 07, 2026

This work addresses the challenges of hallucination and overconfidence in vision-language models when applied to digital museums of ancient Greek pottery, where visual evidence is often ambiguous. To mitigate these issues, the authors propose VaseAgent, a lightweight, modular multimodal agent framework that integrates 2D/3D artifact perception, 3D-aware reasoning, and retrieval from external authoritative knowledge sources. The framework innovatively incorporates dual reliability control mechanisms—at both source and response levels—to enable verifiable citations and calibrated uncertainty without requiring model fine-tuning. Furthermore, by adopting a training-free, GRPO-style response selection strategy, VaseAgent significantly enhances citation validity, effectively suppresses hallucinations in knowledge-intensive queries, and generates more neutral and reliable responses when evidential support is insufficient.

0 citationsRead paper

DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors

Jul 01, 2026

Existing approaches struggle to construct spatiotemporally consistent 3D semantic scene graphs due to unstable 3D object representations and frame-by-frame inference. This work proposes a novel framework that first models objects as probabilistic 3D nodes by estimating instance-level geometric 3D Gaussian distributions via depth-guided filtering. It then leverages contextual priors from the V-JEPA 2 world model to aggregate relational evidence across space and time, yielding robust 3D semantic scene graphs. By uniquely integrating depth-aware probabilistic node representations with world-model-derived relational priors, the method substantially mitigates relation sparsity and temporal inconsistency. It achieves state-of-the-art performance on 3DSSG and ReplicaSSG, improving triplet and predicate recall by 77.4% and 23.2%, respectively, while producing structurally coherent outputs suitable for robotic manipulation and augmented reality applications.

0 citationsRead paper

Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation

Jun 30, 2026

This work addresses the challenge of dense semantic segmentation in adverse conditions, where radar data suffer from sparsity, high noise levels, and weak semantic content. To tackle this, the authors propose a unified higher-order structural alignment framework that, for the first time, integrates learnable hypergraphs with unbalanced optimal transport (UOT) into multi-view radar segmentation. This approach explicitly models higher-order dependencies among multi-echo signals across range–azimuth (RA), range–Doppler (RD), and azimuth–Doppler (AD) views and achieves cross-view feature alignment without requiring point-wise correspondences. Coupled with adaptive attention-based fusion and structural consistency regularization, the method significantly enhances robustness. It achieves state-of-the-art performance on the CARRADA and RADIal benchmarks with mIoU scores of 63.8% and 83.4%, respectively—improving upon existing best methods by 1.7 and 2.3 mIoU—and thereby validates the efficacy of higher-order relational modeling.

0 citationsRead paper

Recent publications

Latest Papers

PHOENIX: Fine-Tuned SLM-Powered Autonomous Satellite Lifetime Extension via Predictive Self-Healing and Multi-Agent AI Recovery

Aug 07, 2026

This study addresses the premature failure of low Earth orbit CubeSats caused by undetected faults during communication blackout periods. The authors propose a space-ground collaborative autonomous fault-recovery framework: a fine-tuned small language model (SLM) equipped with a memory-augmented mechanism is deployed on an onboard embedded platform (Aethero NxN-ECM) to enable continuous monitoring and autonomous reasoning over sensor data; meanwhile, a ground-based multi-agent system generates repair commands during brief communication windows and leverages a denoising diffusion probabilistic model (DDPM) to synthesize scarce fault data, thereby enhancing training efficacy. This approach represents the first integration of memory-augmented SLMs with multi-agent cooperative recovery, achieving significant improvements in fault detection accuracy and in-orbit recovery efficiency on the ESA 14-year anomaly detection benchmark dataset comprising 76 telemetry channels and 118 annotated faults.

0 citationsRead paper

Custom-made Gauss quadrature: an introduction for statisticians

Jul 15, 2026

This work addresses the absence of readily available Gaussian quadrature rules for nonclassical weight functions by proposing a general framework that constructs such rules for arbitrary weights via the method of moments and the Stieltjes procedure. Innovatively integrating type-generic programming with adaptive high-precision arithmetic, the approach effectively controls round-off errors and, for the first time, systematically introduces tailored Gaussian quadrature methods to the statistics community. Implemented in Julia as the CustomGaussQuadrature package—accessible from R through JuliaConnectoR—the resulting quadrature rules achieve exact integration of polynomials up to degree \(2n-1\) while substantially reducing the number of function evaluations, thereby offering both high accuracy and computational efficiency.

0 citationsRead paper

VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

Jul 07, 2026

This work addresses the challenges of hallucination and overconfidence in vision-language models when applied to digital museums of ancient Greek pottery, where visual evidence is often ambiguous. To mitigate these issues, the authors propose VaseAgent, a lightweight, modular multimodal agent framework that integrates 2D/3D artifact perception, 3D-aware reasoning, and retrieval from external authoritative knowledge sources. The framework innovatively incorporates dual reliability control mechanisms—at both source and response levels—to enable verifiable citations and calibrated uncertainty without requiring model fine-tuning. Furthermore, by adopting a training-free, GRPO-style response selection strategy, VaseAgent significantly enhances citation validity, effectively suppresses hallucinations in knowledge-intensive queries, and generates more neutral and reliable responses when evidential support is insufficient.

0 citationsRead paper

DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors

Jul 01, 2026

Existing approaches struggle to construct spatiotemporally consistent 3D semantic scene graphs due to unstable 3D object representations and frame-by-frame inference. This work proposes a novel framework that first models objects as probabilistic 3D nodes by estimating instance-level geometric 3D Gaussian distributions via depth-guided filtering. It then leverages contextual priors from the V-JEPA 2 world model to aggregate relational evidence across space and time, yielding robust 3D semantic scene graphs. By uniquely integrating depth-aware probabilistic node representations with world-model-derived relational priors, the method substantially mitigates relation sparsity and temporal inconsistency. It achieves state-of-the-art performance on 3DSSG and ReplicaSSG, improving triplet and predicate recall by 77.4% and 23.2%, respectively, while producing structurally coherent outputs suitable for robotic manipulation and augmented reality applications.

0 citationsRead paper

Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation

Jun 30, 2026

This work addresses the challenge of dense semantic segmentation in adverse conditions, where radar data suffer from sparsity, high noise levels, and weak semantic content. To tackle this, the authors propose a unified higher-order structural alignment framework that, for the first time, integrates learnable hypergraphs with unbalanced optimal transport (UOT) into multi-view radar segmentation. This approach explicitly models higher-order dependencies among multi-echo signals across range–azimuth (RA), range–Doppler (RD), and azimuth–Doppler (AD) views and achieves cross-view feature alignment without requiring point-wise correspondences. Coupled with adaptive attention-based fusion and structural consistency regularization, the method significantly enhances robustness. It achieves state-of-the-art performance on the CARRADA and RADIal benchmarks with mIoU scores of 63.8% and 83.4%, respectively—improving upon existing best methods by 1.7 and 2.3 mIoU—and thereby validates the efficacy of higher-order relational modeling.

0 citationsRead paper