Institution profile

Tampere University

Academic institutioneurope · fi
Official website
Research library281linked papers
Opportunities0open roles
Selected work

Representative Papers

UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding

Jun 20, 2023International Workshop on Quality of Multimedia Experience

The MPEG Visual Volumetric Video Coding (V3C) standard lacks a standardized, publicly available test benchmark for evaluating compression algorithms. Method: This paper introduces the first open-source, voxelized point cloud video dataset specifically designed for V3C standardization. It comprises 12 diverse 10-second sequences at 25 fps, covering complex motion, texture variation, geometric deformation, and occlusion. Each sequence provides high-precision geometry (9–12 bits), 8-bit RGB color, and surface normal vectors. A novel voxelization framework is proposed, incorporating normal vector embedding, multi-bit-depth geometric quantization, and standardized sequence organization, distributed under a non-commercial license. Contribution/Results: The dataset fills a critical gap in public V3C compression evaluation infrastructure and has been officially adopted by MPEG as a standard test set, thereby accelerating international standardization and practical deployment of point cloud compression technologies.

9 citationsRead paper

Understanding the Issues, Their Causes and Solutions in Microservices Systems: An Empirical Study

Feb 03, 2023arXiv.org

Microservice system developers lack empirical evidence regarding the types, root causes, and remediation strategies of recurring issues. Method: We adopt a mixed-methods approach—quantitatively analyzing 2,641 open-source issues, qualitatively interviewing 15 practitioners, and conducting a global survey with 150 practitioners. Contribution/Results: We introduce the first comprehensive, domain-specific three-level taxonomy (“Issue–Cause–Solution”) for microservices. We identify five high-frequency issue domains—including technical debt, CI/CD pipeline failures, and exception handling—and three predominant root causes, notably generic programming errors. From our analysis, we distill 177 actionable, context-aware remediation strategies. This work establishes an empirical foundation for microservice fault diagnosis and mitigation, delivers practical guidance for industry practitioners, and pinpoints critical research directions for next-generation microservice engineering.

6 citations2 influentialRead paper

Mapping Trustworthiness in Large Language Models: A Bibliometric Analysis Bridging Theory to Practice

Feb 27, 2025arXiv.org

The conceptual ambiguity of trustworthiness in large language models (LLMs) and the disconnect between theoretical foundations and practical implementation hinder rigorous evaluation and deployment. Method: We conduct a bibliometric analysis and systematic literature review of 2,006 publications (2019–2025), establishing, for the first time, a bidirectional “theory–practice” mapping framework. Contribution/Results: First, we synthesize a tripartite theoretical framework—comprising competence, benevolence, and integrity—from 68 core studies. Second, we map these constructs to 20 actionable, lifecycle-spanning trust-enhancement techniques across training, inference, and deployment, forming a structured technical taxonomy. Third, by innovatively integrating organizational trust theory with LLM engineering practice, we propose an empirically grounded methodology for trustworthiness assessment and enhancement. This work provides a systematic foundation for transparent, accountable, and ethically aligned LLM development and deployment.

2 citations1 influentialRead paper

A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism

Jul 22, 2024arXiv.org

Neural architecture search (NAS) suffers from high evaluation overhead and model redundancy due to single-objective optimization (e.g., accuracy only). To address this, we propose an efficient multi-objective NAS framework. Our method introduces: (1) a novel lightweight surrogate model based on pairwise comparison that predicts relative architectural rankings instead of absolute accuracy—substantially reducing evaluation cost; and (2) a master–auxiliary dual-population co-evolutionary mechanism that enhances population diversity while ensuring convergence. Evaluated on CIFAR-10/100 and ImageNet, our approach completes search in just 0.17 GPU-days on a single GPU. On ImageNet, it discovers a compact architecture achieving 78.91% Top-1 accuracy with only 570M MAdds. Compared to state-of-the-art methods, our framework improves search efficiency by multiple orders of magnitude and significantly strengthens multi-objective optimization across accuracy, parameter count, and computational cost.

2 citationsRead paper

NMPC-Augmented Visual Navigation and Safe Learning Control for Large-Scale Mobile Robots

Jan 02, 2026arXiv.org

This work addresses the challenges of pose drift and control instability in large-scale mobile robots operating on loose, slippery terrain due to insufficient traction. To this end, a four-module cooperative framework is proposed, integrating stereo-vision-based pose estimation, high-order nonlinear model predictive control (NMPC), a deep neural network-based low-level controller, and a logarithmic barrier-based safety monitoring mechanism. The approach uniquely combines high-order NMPC with a learning-based low-level controller and introduces a logarithmic safety barrier, achieving system-wide safety and exponential stability of actuators through synchronized multi-rate heterogeneous module coordination. Experimental validation on a 6,000-kg dual electro-hydrostatic actuation platform demonstrates that the method enables low-latency, high-precision pose tracking and full-stack safety guarantees under severe slippage conditions.

1 citationsRead paper
Recent publications

Latest Papers