Simplified Cross-Modal Calibration for Heterogeneous Event-RGB Stereo Systems
本文提出了一种无运动的跨模态校准框架，通过时间调制混合ChArUco目标解决事件相机和帧相机之间的外参校准问题。
0 citationsRead paper
Selected work
Representative Papers
Drifting Models for Surrogate Flow Modeling
This work addresses the high computational cost of traditional computational fluid dynamics (CFD), which hinders rapid exploration in indoor environmental optimization. While existing generative surrogate models can capture complex flow fields, they suffer from inefficient iterative sampling. To overcome this limitation, the study introduces, for the first time, a drifting generative framework into fluid dynamics, proposing label-conditional and spatially conditional variants that enable single-pass forward generation in the latent space of a variational autoencoder (VAE). A label-aware masking mechanism is incorporated to enforce boundary condition consistency. The method achieves flow field accuracy and physical fidelity comparable to iterative diffusion models while accelerating inference by two orders of magnitude. Moreover, it generalizes effectively to unseen geometries, establishing an efficient new paradigm for real-time CFD surrogate modeling.
0 citationsRead paper
Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning
This work addresses the pressing need for efficient and reliable uncertainty quantification in deep neural networks deployed in safety-critical systems. To overcome limitations of existing stochastic regularization approaches—particularly the lack of a Bayesian interpretation for Stochastic Depth and insufficient validation in multi-task settings—the authors propose Monte Carlo Stochastic Depth (MCSD), reframing it as a Monte Carlo sampling mechanism to approximate Bayesian inference. The study establishes, for the first time, a theoretical connection between MCSD and variational inference. Comprehensive evaluations on object detectors such as YOLO and RT-DETR using COCO and COCO-O datasets demonstrate that MCSD achieves calibration (measured by ECE) and uncertainty ranking performance (via AUARC) slightly superior to Monte Carlo Dropout, while maintaining high mAP, robustness, and computational efficiency.
0 citationsRead paper
Generative Anonymization in Event Streams
Event-based data in public-space applications are prone to identity leakage, yet existing anonymization methods often disrupt their spatiotemporal structure, degrading downstream task performance. This work proposes the first generative anonymization framework tailored for event streams, introducing an intermediate intensity representation to bridge asynchronous events with spatial generative models. The framework synthesizes realistic but fictitious identities and re-encodes them back into the neuromorphic domain. It effectively prevents recovery of true identities from event-to-video (E2V) reconstructions while preserving the utility of event streams for downstream vision tasks. Additionally, the study constructs and releases the first synchronized real-world event-RGB benchmark dataset to facilitate systematic evaluation of privacy–utility trade-offs.
0 citationsRead paper
Generative AI Usage of University Students: Navigating Between Education and Business
This study addresses the lack of systematic understanding regarding how university students navigating dual academic and professional identities employ generative artificial intelligence (GenAI) in the intersecting contexts of education and work. Drawing on grounded theory, the research constructs the first integrated theoretical model of GenAI use through semi-structured in-depth interviews with 11 distance-learning students. The analysis identifies three core causal conditions and four intervening factors that shape distinct usage strategies. Findings reveal that while GenAI enhances both learning and work efficiency, it simultaneously introduces critical challenges concerning reliability, academic integrity, and ethical risks. These insights offer valuable theoretical and practical implications for human-AI collaboration across boundary-spanning scenarios.
0 citationsRead paper
Recent publications
Latest Papers
Simplified Cross-Modal Calibration for Heterogeneous Event-RGB Stereo Systems
本文提出了一种无运动的跨模态校准框架，通过时间调制混合ChArUco目标解决事件相机和帧相机之间的外参校准问题。
0 citationsRead paper
Drifting Models for Surrogate Flow Modeling
This work addresses the high computational cost of traditional computational fluid dynamics (CFD), which hinders rapid exploration in indoor environmental optimization. While existing generative surrogate models can capture complex flow fields, they suffer from inefficient iterative sampling. To overcome this limitation, the study introduces, for the first time, a drifting generative framework into fluid dynamics, proposing label-conditional and spatially conditional variants that enable single-pass forward generation in the latent space of a variational autoencoder (VAE). A label-aware masking mechanism is incorporated to enforce boundary condition consistency. The method achieves flow field accuracy and physical fidelity comparable to iterative diffusion models while accelerating inference by two orders of magnitude. Moreover, it generalizes effectively to unseen geometries, establishing an efficient new paradigm for real-time CFD surrogate modeling.
0 citationsRead paper
Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning
This work addresses the pressing need for efficient and reliable uncertainty quantification in deep neural networks deployed in safety-critical systems. To overcome limitations of existing stochastic regularization approaches—particularly the lack of a Bayesian interpretation for Stochastic Depth and insufficient validation in multi-task settings—the authors propose Monte Carlo Stochastic Depth (MCSD), reframing it as a Monte Carlo sampling mechanism to approximate Bayesian inference. The study establishes, for the first time, a theoretical connection between MCSD and variational inference. Comprehensive evaluations on object detectors such as YOLO and RT-DETR using COCO and COCO-O datasets demonstrate that MCSD achieves calibration (measured by ECE) and uncertainty ranking performance (via AUARC) slightly superior to Monte Carlo Dropout, while maintaining high mAP, robustness, and computational efficiency.
0 citationsRead paper
Generative Anonymization in Event Streams
Event-based data in public-space applications are prone to identity leakage, yet existing anonymization methods often disrupt their spatiotemporal structure, degrading downstream task performance. This work proposes the first generative anonymization framework tailored for event streams, introducing an intermediate intensity representation to bridge asynchronous events with spatial generative models. The framework synthesizes realistic but fictitious identities and re-encodes them back into the neuromorphic domain. It effectively prevents recovery of true identities from event-to-video (E2V) reconstructions while preserving the utility of event streams for downstream vision tasks. Additionally, the study constructs and releases the first synchronized real-world event-RGB benchmark dataset to facilitate systematic evaluation of privacy–utility trade-offs.
0 citationsRead paper
Generative AI Usage of University Students: Navigating Between Education and Business
This study addresses the lack of systematic understanding regarding how university students navigating dual academic and professional identities employ generative artificial intelligence (GenAI) in the intersecting contexts of education and work. Drawing on grounded theory, the research constructs the first integrated theoretical model of GenAI use through semi-structured in-depth interviews with 11 distance-learning students. The analysis identifies three core causal conditions and four intervening factors that shape distinct usage strategies. Findings reveal that while GenAI enhances both learning and work efficiency, it simultaneously introduces critical challenges concerning reliability, academic integrity, and ethical risks. These insights offer valuable theoretical and practical implications for human-AI collaboration across boundary-spanning scenarios.
0 citationsRead paper