Institution profile

Utrecht University

Academic institutioneurope · nl
Official website
Research library690linked papers
Opportunities0open roles
Selected work

Representative Papers

Filtering for Copyright Enforcement in Europe after the Sabam Cases

Apr 08, 2013

This study examines the legal constraints imposed by the Court of Justice of the European Union on internet service providers’ implementation of copyright filtering systems following the Sabam case, with particular attention to the potential infringement of fundamental rights such as privacy and freedom of information. Through doctrinal analysis, a fundamental rights balancing framework, and an assessment of digital copyright governance mechanisms, the research demonstrates that although the Court rejected the mandatory deployment of filtering systems as unlawful, its rulings fall short of adequately safeguarding the substantive essence of these fundamental rights. By redefining the legitimacy boundaries of copyright enforcement from a fundamental rights perspective, this work highlights the limitations of judicial practice in protecting digital rights and offers theoretical insights for refining the EU’s digital copyright governance framework.

18 citationsRead paper

Indoor Drone Localization and Tracking Based on Acoustic Inertial Measurement

Jun 01, 2024IEEE Transactions on Mobile Computing

To address the challenge of precise localization and tracking of indoor drones under GPS-denied and non-line-of-sight (NLoS) conditions, this paper proposes a hardware-agnostic acoustic-inertial fusion method that requires no drone hardware modification or large-scale infrastructure deployment. Innovatively leveraging the drone’s rotor-generated acoustic signatures as motion sources, the approach integrates a distributed microphone array with a customized extended Kalman filter (EKF) and incorporates an interquartile range (IQR)-based robust outlier rejection mechanism. This enables real-time, three-dimensional pose estimation and motion tracking in arbitrarily sized and configured indoor environments. Experimental evaluation in a complex 10 m × 10 m indoor setting demonstrates that the method achieves a 46% reduction in mean localization error compared to a commercial ultra-wideband (UWB) system; moreover, positioning accuracy remains within 0.5 m across a 20 m operational range.

10 citationsRead paper

LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning

Jan 15, 2026

In multimodal implicit reasoning, lightweight student models often rely excessively on linguistic priors while neglecting genuine visual perception, leading to significant divergence in visual attention from their teacher counterparts. To address this, this work proposes a novel paradigm that aligns the "latent visual thinking" of student and teacher models. Specifically, it employs autoregressive reconstruction of the teacher’s visual semantics and attention trajectories to align their dynamic visual reasoning processes prior to text generation. A curriculum-based sensory gating mechanism is further introduced to suppress shortcut learning. This approach represents the first explicit modeling and transfer of the teacher’s dynamic visual attention, achieving up to a 16.9% performance gain on complex reasoning tasks and enabling a 3B-parameter model to surpass both larger open-source models and closed-source systems such as GPT-4o.

2 citationsRead paper

Using street view images and visual LLMs to predict heritage values for governance support: Risks, ethics, and policy implications

Dec 22, 2025arXiv.org

Sweden lacks a national registry of architectural heritage values, which hinders the formulation of effective building retrofit policies. This study addresses this gap by pioneering the integration of multimodal large language models (MLLMs) with street-view imagery to predict heritage values for over 150,000 buildings nationwide—encompassing approximately 5 million square meters of heated floor area—using zero-shot learning. Beyond delivering critical data to inform national retrofitting initiatives, the research systematically examines the ethical implications, transparency, and policy impacts of deploying vision-based large language models in public governance. The findings illuminate both the transformative potential and inherent risks of such AI applications, offering an innovative paradigm for AI-driven cultural heritage management.

2 citationsRead paper

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Dec 03, 2025

Existing evaluation methods inadequately measure large language model (LLM) agents’ cooperative generalization capability in novel, mixed-motive social scenarios. Method: We conduct a systematic zero-shot evaluation on the Concordia multi-agent simulation platform, assessing LLM agents’ ability to recognize and realize mutual benefit across diverse social interaction tasks—including negotiation and collective action—using a novel quantitative framework for general cooperative intelligence. This framework emphasizes high-generalization dimensions such as persuasion and norm enforcement. Contribution/Results: Empirical analysis of NeurIPS 2024 Concordia Competition data reveals substantial limitations in current LLM agents’ cross-context cooperative generalization, particularly in dynamic coordination and implicit norm modeling. Our work establishes a new paradigm for benchmarking and diagnosing cooperative intelligence, advancing both methodological rigor and diagnostic precision in multi-agent cooperation research.

2 citationsRead paper
Recent publications

Latest Papers