2931 papers
This paper proposes and evaluates a scoring-based approach that automatically classifies business processes into structuredness categories (structured, semi-structured, loosely structured, and unstructured) by analyzing fine-grained temporal and existential activity relationships within event logs to address the lack of automated support in process mining.
MonitorVLM-v2 is a deployed framework that transforms open-ended vision-language reasoning into efficient, single-step symbolic predictions via symbolic policy optimization and entropy-driven triage, achieving a 19.45-fold speed increase and significantly higher violation detection rates in real-time industrial safety monitoring compared to manual inspection.
RGBA-Net is a lightweight, state-of-the-art RGB-D salient object detection framework that employs an asymmetric dual-stream encoder, a depth reliability gate, and a boundary-aware fusion module to achieve high accuracy with only 3.49 million parameters while effectively mitigating depth noise and complexity.
This paper introduces Azra, a Vision-Language Model framework for Ottoman Turkish handwritten text recognition that achieves state-of-the-art performance through LoRA fine-tuning on curated data and demonstrates that autonomous data bootstrapping can effectively match curated approaches while significantly reducing annotation costs.
This paper presents the design and implementation of a stable, modular tourism management system based on the SSH framework that integrates an optimized hybrid recommendation algorithm to achieve high accuracy, low latency under heavy loads, and strong user satisfaction.
This paper proposes an Integrated Offline–Online Evaluation Framework (IOEF) that links technical retrieval metrics with educational outcome evidence from existing literature to demonstrate that effective AI adoption in higher education requires balancing information-retrieval performance with instructional design rather than relying on retrieval benchmarks alone.
This study demonstrates that in controlled synthetic environments, the surface distance between key fields significantly impacts the routing accuracy of small character-level Transformers, validating the use of such unit tests to distinguish between genuine lookup mechanisms and surface-level cue exploitation before deploying automated educational systems.
This paper presents a coordinate-based surface intersection method that represents intersection curves as sequences of residual-audited contact frames containing semantic and geometric metadata, demonstrating superior numerical precision and robust Boolean closure compared to OpenCASCADE Technology across a diverse suite of primitive and complex surface intersection cases.
This study demonstrates that while global diversity in educational item banks is insufficient to ensure robust language parsing, local allocation strategies significantly impact performance, whereas global graph connectivity provides no additional benefit once components have sufficient within-cell exposure.
DeepGaitLab is an open-source, markerless 3D motion tracking framework trained on synthetic data that delivers high-accuracy, calibration-free gait analysis across diverse camera configurations and clinical populations, effectively bridging the gap between research-grade biomechanics and scalable clinical deployment.