arXiv subjects

Yong Chu

Publications and source records attributed to Yong Chu.

4 recordsLinked to original sources

arXiv2026

From Event Logs to Governed Action: A BlueSky Agenda for Agentic Process Mining

Process mining has long turned event logs into process knowledge: discovered models, conformance evidence, bottleneck diagnoses, and runtime predictions. Agentic AI changes the target. Process-aware agents will not only ask what happened. They will ask whether a proposed action should be taken, given the available evidence, privacy budget, organizational authority, and downstream risk. This BlueSky paper proposes event-to-action process mining: a process-mining agenda for transforming heterogeneous operational event data into governed action. The goal is not another dashboard, a generic enterprise simulator, or a language interface over logs. We argue that the community needs four mineable artifacts: event-object representations, action evidence packages, governance contracts, and benchmarks where act, defer, ask, and refuse are all valid outputs. This agenda is timely because agentic business process management (BPM), LLM-assisted process mining, object-centric event standards, causal process monitoring, and privacy-preserving learning are maturing separately. Bringing them together defines a data-mining target inside process mining: mining logged organizational behavior for accountable action, not only retrospective insight.

cs.AI↗

arXiv2026

Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization

Accurate and robust wireless localization is a critical enabler for emerging 5G/6G applications, including autonomous driving, extended reality, and smart manufacturing. Despite its importance, achieving precise localization across diverse environments remains challenging due to the complex nature of wireless signals and their sensitivity to environmental changes. Existing data-driven approaches often suffer from limited generalization capability, requiring extensive labeled data and struggling to adapt to new scenarios. To address these limitations, we propose SigMap, a multimodal foundation model that introduces two key innovations: (1) A cycle-adaptive masking strategy that dynamically adjusts masking patterns based on channel periodicity characteristics to learn robust wireless representations; (2) A novel "map-as-prompt" framework that integrates 3D geographic information through lightweight soft prompts for effective cross-scenario adaptation. Extensive experiments demonstrate that our model achieves state-of-the-art performance across multiple localization tasks while exhibiting strong zero-shot generalization in unseen environments, significantly outperforming both supervised and self-supervised baselines by considerable margins.

eess.SP↗

arXiv2024

Intelligent Cross-Organizational Process Mining: A Survey and New Perspectives

Process mining, as a high-level field in data mining, plays a crucial role in enhancing operational efficiency and decision-making across organizations. In this survey paper, we delve into the growing significance and ongoing trends in the field of process mining, advocating a specific viewpoint on its contents, application, and development in modern businesses and process management, particularly in cross-organizational settings. We first summarize the framework of process mining, common industrial applications, and the latest advances combined with artificial intelligence, such as workflow optimization, compliance checking, and performance analysis. Then, we propose a holistic framework for intelligent process analysis and outline initial methodologies in cross-organizational settings, highlighting both challenges and opportunities. This particular perspective aims to revolutionize process mining by leveraging artificial intelligence to offer sophisticated solutions for complex, multi-organizational data analysis. By integrating advanced machine learning techniques, we can enhance predictive capabilities, streamline processes, and facilitate real-time decision-making. Furthermore, we pinpoint avenues for future investigations within the research community, encouraging the exploration of innovative algorithms, data integration strategies, and privacy-preserving methods to fully harness the potential of process mining in diverse, interconnected business environments.

cs.AI↗

arXiv2020

Ptychographic X-ray Speckle Tracking with Multi Layer Laue Lens Systems

The ever-increasing brightness of synchrotron radiation sources demands improved x-ray optics to utilise their capability for imaging and probing biological cells, nano-devices, and functional matter on the nanometre scale with chemical sensitivity. Hard x-rays are ideal for high-resolution imaging and spectroscopic applications due to their short wavelength, high penetrating power, and chemical sensitivity. The penetrating power that makes x-rays useful for imaging also makes focusing them technologically challenging. Recent developments in layer deposition techniques that have enabled the fabrication of a series of highly focusing x-ray lenses, known as wedged multi layer Laue lenses. Improvements to the lens design and fabrication technique demands an accurate, robust, in-situ and at-wavelength characterisation method. To this end, we have developed a modified form of the speckle-tracking wavefront metrology method, the ptychographic x-ray speckle tracking method, which is capable of operating with highly divergent wavefields. A useful by-product of this method, is that it also provides high-resolution and aberration-free projection images of extended specimens. We report on three separate experiments using this method, where we have resolved ray path angles to within 4 nano-radians with an imaging resolution of 45nm (full-period). This method does not require a high degree of coherence, making it suitable for lab based x-ray sources. Likewise it is robust to errors in the registered sample positions making it suitable for x-ray free-electron laser facilities, where beam pointing fluctuations can be problematic for wavefront metrology.

physics.optics↗