Selected work

Representative Papers

EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion

Jul 07, 2026

This work addresses the challenge of achieving high-quality video enhancement under extreme low-light conditions while maintaining computational efficiency in resource-constrained settings. To this end, it introduces binary neural networks (BNNs) into RAW-event multimodal fusion for the first time, proposing a modality-specific binary encoder, a lightweight cross-modal fusion module, and an event-guided skip gating mechanism to enable dynamic spatiotemporal optimization. Evaluated on both synthetic and real-world low-light datasets, the proposed method significantly outperforms existing BNN-based approaches, delivering superior enhancement quality while substantially reducing computational overhead. This approach effectively strikes a balance between performance and efficiency, making it particularly suitable for practical deployment in low-power or embedded vision systems.

0 citationsRead paper

A Comparative Evaluation of Prominent Methods in Autonomous Vehicle Certification

Nov 14, 2025

The absence of a systematic framework and standardized methodology for the safety certification of autonomous vehicles hinders regulatory oversight and technical harmonization. Method: This study proposes a structured certification process framework that integrates functional safety (ISO 26262) and safety of the intended functionality (SOTIF, ISO 21448) requirements. It explicitly defines responsibilities, inputs/outputs, and methodological boundaries across key phases—design verification, simulation-based testing, on-road validation, and type approval. Through systematic literature review, multidimensional comparative analysis, and process modeling, the study evaluates the applicability and limitations of mainstream certification approaches, including scenario-driven testing, formal verification, and evidence-based argumentation. Contribution/Results: The framework provides a theoretically grounded and practically implementable foundation for developing an extensible, reproducible, and auditable certification system for autonomous vehicles, thereby advancing the realization of the “vision zero” goal in intelligent transportation systems.

0 citationsRead paper

Recent publications

Latest Papers

EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion

Jul 07, 2026

This work addresses the challenge of achieving high-quality video enhancement under extreme low-light conditions while maintaining computational efficiency in resource-constrained settings. To this end, it introduces binary neural networks (BNNs) into RAW-event multimodal fusion for the first time, proposing a modality-specific binary encoder, a lightweight cross-modal fusion module, and an event-guided skip gating mechanism to enable dynamic spatiotemporal optimization. Evaluated on both synthetic and real-world low-light datasets, the proposed method significantly outperforms existing BNN-based approaches, delivering superior enhancement quality while substantially reducing computational overhead. This approach effectively strikes a balance between performance and efficiency, making it particularly suitable for practical deployment in low-power or embedded vision systems.

0 citationsRead paper

A Comparative Evaluation of Prominent Methods in Autonomous Vehicle Certification

Nov 14, 2025

The absence of a systematic framework and standardized methodology for the safety certification of autonomous vehicles hinders regulatory oversight and technical harmonization. Method: This study proposes a structured certification process framework that integrates functional safety (ISO 26262) and safety of the intended functionality (SOTIF, ISO 21448) requirements. It explicitly defines responsibilities, inputs/outputs, and methodological boundaries across key phases—design verification, simulation-based testing, on-road validation, and type approval. Through systematic literature review, multidimensional comparative analysis, and process modeling, the study evaluates the applicability and limitations of mainstream certification approaches, including scenario-driven testing, formal verification, and evidence-based argumentation. Contribution/Results: The framework provides a theoretically grounded and practically implementable foundation for developing an extensible, reproducible, and auditable certification system for autonomous vehicles, thereby advancing the realization of the “vision zero” goal in intelligent transportation systems.

0 citationsRead paper