Skip to main content

Research Repository

Advanced Search

All Outputs (1380)

SYCL compute kernels for ExaHyPE (2024)
Presentation / Conference Contribution
Loi, C. M., Bockhorst, H., & Weinzierl, T. (2024, March). SYCL compute kernels for ExaHyPE. Presented at 2024 SIAM Conference on Parallel Processing for Scientific Computing (PP), Baltimore, MD

We discuss three SYCL realisations of a simple Finite Volume scheme over multiple Cartesian patches. The realisation flavours differ in the way how they map the compute steps onto loops and tasks: We compare an implementation that is exclusively usin... Read More about SYCL compute kernels for ExaHyPE.

MxT: Mamba x Transformer for Image Inpainting (2024)
Presentation / Conference Contribution
Chen, S., Atapour-Abarghouei, A., Zhang, H., & Shum, H. P. H. (2024, November). MxT: Mamba x Transformer for Image Inpainting. Presented at BMVC 2024: The 35th British Machine Vision Conference, Glasgow, UK

Image inpainting, or image completion, is a crucial task in computer vision that aims to restore missing or damaged regions of images with semantically coherent content. This technique requires a precise balance of local texture replication and globa... Read More about MxT: Mamba x Transformer for Image Inpainting.

A Leader-Follower Collective Motion in Robotic Swarms (2024)
Presentation / Conference Contribution
Bahaidarah, M., Marjanovic, O., Rekabi-bana, F., & Arvin, F. (2024, August). A Leader-Follower Collective Motion in Robotic Swarms. Presented at TAROS 2024: Towards Autonomous Robotic Systems, London, UK

Collective Motion (CM) is a basic phenomenon observed in nature, such as in birds, insects, and schooling fish. In swarm robotics, virtual links among the swarm members generate attractive and repulsive forces to attain self-organised CM behaviour. H... Read More about A Leader-Follower Collective Motion in Robotic Swarms.

Predator-Prey Q-Learning Based Collaborative Coverage Path Planning for Swarm Robotics (2024)
Presentation / Conference Contribution
Watson, M., Ren, H., Arvin, F., & Hu, J. (2024, August). Predator-Prey Q-Learning Based Collaborative Coverage Path Planning for Swarm Robotics. Presented at 2024 Annual Conference Towards Autonomous Robotic Systems (TAROS), London

Coverage Path Planning (CPP) is an effective approach to let intelligent robots cover an area by finding feasible paths through the environment. In this paper, we focus on using reinforcement learning to learn about a given environment and find the m... Read More about Predator-Prey Q-Learning Based Collaborative Coverage Path Planning for Swarm Robotics.

Reconfigurable routing in data center networks (2024)
Presentation / Conference Contribution
Kutner, D. C., & Stewart, I. A. (2024, September). Reconfigurable routing in data center networks. Presented at 20th International Symposium on Algorithmics of Wireless Networks, ALGOWIN 2024, Egham, UK

A hybrid network is a static (electronic) network that is augmented with optical switches. The Reconfigurable Routing Problem (RRP) in hybrid networks is the problem of finding settings for the optical switches augmenting a static network so as to ac... Read More about Reconfigurable routing in data center networks.

The threshold of existence of δ-temporal cliques in random simple temporal graphs (2024)
Presentation / Conference Contribution
Mertzios, G. B., Nikoletseas, S., Raptopoulos, C., & Spirakis, P. (2024, September). The threshold of existence of δ-temporal cliques in random simple temporal graphs. Presented at The 20th International Symposium on Algorithmics of Wireless Networks (ALGOWIN), Egham, London, United Kingdom

Surprise! Surprise! Learn and Adapt (2024)
Presentation / Conference Contribution
Samin, H., Walton, D., & Bencomo, N. (2025, May). Surprise! Surprise! Learn and Adapt. Presented at 24th International Conference on Autonomous Agents and Multiagent Systems, Detroit, Michigan, USA

Self-adaptive systems (SAS) adjust their behavior at runtime in response to environmental changes, which are often unpredictable at design time. SAS must make decisions under uncertainty, balancing trade-offs between quality attributes (e.g., cost mi... Read More about Surprise! Surprise! Learn and Adapt.

Interactive Digital Storytelling Navigating the Inherent Currents of the Diasporic Mind (2024)
Presentation / Conference Contribution
Nisi, V., Bala, P., Pessoa, M., James, S., & Nunes, N. (2024, December). Interactive Digital Storytelling Navigating the Inherent Currents of the Diasporic Mind. Presented at International Conference on Interactive Digital Storytelling (ICIDS 2024), Barranquilla, Colombia

Due to a recent increase in conflicts, natural disasters, and economic crises, a growing wave of migrant populations has been searching for asylum in Europe. For this population of asylum seekers, the migration process, like currents and rapids, can... Read More about Interactive Digital Storytelling Navigating the Inherent Currents of the Diasporic Mind.

Beyond Syntax: How Do LLMs Understand Code? (2024)
Presentation / Conference Contribution
North, M., Atapour-Abarghouei, A., & Bencomo, N. (2025, April). Beyond Syntax: How Do LLMs Understand Code?. Presented at 2025 IEEE/ACM International Conference on Software Engineering ICSE, Ottawa , Canada

Within software engineering research, Large Language Models (LLMs) are often treated as 'black boxes', with only their inputs and outputs being considered. In this paper, we take a machine interpretability approach to examine how LLMs internally repr... Read More about Beyond Syntax: How Do LLMs Understand Code?.

Block Ciphers in Idealized Models: Automated Proofs and New Security Results (2024)
Presentation / Conference Contribution
Ambrona, M., Farshim, P., & Harasser, P. (2024, October). Block Ciphers in Idealized Models: Automated Proofs and New Security Results. Presented at ACM SIGSAC Conference on Computer and Communications Security 2024, Salt Lake City, USA

We develop and implement AlgoROM, a tool to systematically analyze the security of a wide class of symmetric primitives in idealized models of computation. The schemes that we consider are those that can be expressed over an alphabet consisting of XO... Read More about Block Ciphers in Idealized Models: Automated Proofs and New Security Results.

Neural-code PIFu: High-fidelity Single Image 3D Human Reconstruction via Neural Code Integration (2024)
Presentation / Conference Contribution
Liu, R., Remagnino, P., & Shum, H. P. (2024, December). Neural-code PIFu: High-fidelity Single Image 3D Human Reconstruction via Neural Code Integration. Presented at 2024 International Conference on Pattern Recognition, Kolkata, India

We introduce neural-code PIFu, a novel implicit function for 3D human reconstruction, leveraging neural codebooks, our approach learns recurrent patterns in the feature space and reuses them to improve current features. Many existing methods predict... Read More about Neural-code PIFu: High-fidelity Single Image 3D Human Reconstruction via Neural Code Integration.

Complexity framework for forbidden subgraphs II: Edge subdivision and the "H"-graphs (2024)
Presentation / Conference Contribution
Lozin, V. V., Martin, B., Pandey, S., Paulusma, D., Siggers, M., Smith, S., & van Leeuwen, E. J. (2024, December). Complexity framework for forbidden subgraphs II: Edge subdivision and the "H"-graphs. Presented at ISAAC, ISAAC 2024

For a fixed set H of graphs, a graph G is H-subgraph-free if G does not contain any H ∈ H as a (not necessarily induced) subgraph. A recent framework gives a complete classification on H-subgraph-free graphs (for finite sets H) for problems that are... Read More about Complexity framework for forbidden subgraphs II: Edge subdivision and the "H"-graphs.

From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos (2024)
Presentation / Conference Contribution
Qiao, T., Li, R., Li, F. W. B., & Shum, H. P. H. (2024, December). From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos. Presented at ICPR 2024: International Conference on Pattern Recognition, Kolkata, India

Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human behavior and intentions. While previous work has made significant stride... Read More about From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos.

SK_DU Team: Cross-Encoder based Evidence Retrieval and Question Generation with Improved Prompt for the AVeriTeC Shared Task (2024)
Presentation / Conference Contribution
Malviya, S., & Katsigiannis, S. (2024, November). SK_DU Team: Cross-Encoder based Evidence Retrieval and Question Generation with Improved Prompt for the AVeriTeC Shared Task. Presented at 7th Fact Extraction and VERification Workshop (FEVER), Miami, Florida, USA

As part of the AVeriTeC shared task, we developed a pipelined system comprising robust and finely tuned models. Our system integrates advanced techniques for evidence retrieval and question generation, leveraging cross-encoders and large language mod... Read More about SK_DU Team: Cross-Encoder based Evidence Retrieval and Question Generation with Improved Prompt for the AVeriTeC Shared Task.

AI-Driven Feedback for Enhancing Students' Mathematical Problem-Solving: The ScaffoldiaMyMaths System (2024)
Presentation / Conference Contribution
Sun, D., Wang, J., Yang, L., Chou, K.-L., Song, Z., & Zheng, Z. (2024, November). AI-Driven Feedback for Enhancing Students' Mathematical Problem-Solving: The ScaffoldiaMyMaths System. Poster presented at International Conference on Computers in Education, Philippines

As online learning becomes increasingly prevalent, it is essential to understand students' perspectives and address the challenges they encounter. The developing system, ScaffoldiaMyMaths, aims to support the mathematics learning of underprivileged a... Read More about AI-Driven Feedback for Enhancing Students' Mathematical Problem-Solving: The ScaffoldiaMyMaths System.

Evidence Retrieval for Fact Verification using Multi-stage Reranking (2024)
Presentation / Conference Contribution
Malviya, S., & Katsigiannis, S. (2024, November). Evidence Retrieval for Fact Verification using Multi-stage Reranking. Presented at 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), Miami, FL, USA

Green AutoML: Energy-Efficient AI Deployment Across the Edge-Fog-Cloud Continuum (2024)
Presentation / Conference Contribution
Dua, A., Singh Aujla, G., Jindal, A., & Sun, H. (2024, December). Green AutoML: Energy-Efficient AI Deployment Across the Edge-Fog-Cloud Continuum. Presented at IEEE Global Communications Conference - Workshop on Next-Gen Healthcare Fusion (NgHF): AI-driven Secure Integrated Networks for Healthcare IoT Systems, Cape Town, South Africa

The increasing demand for machine learning (ML) technologies has led to a significant rise in energy consumption and environmental impact, particularly within the context of distributed computing environments like the Edge-Fog-Cloud Continuum. This p... Read More about Green AutoML: Energy-Efficient AI Deployment Across the Edge-Fog-Cloud Continuum.

MAFin: Maximizing Accuracy in FinFET based Approximated Real-Time Computing (2024)
Presentation / Conference Contribution
Chakraborty, S., Saha, S., Sjalander, M., & Mcdonald-Maier, K. (2024, June). MAFin: Maximizing Accuracy in FinFET based Approximated Real-Time Computing. Presented at DAC '24: 61st ACM/IEEE Design Automation Conference, San Francisco CA USA

We propose MAFin that exploits the unique temperature effect inversion (TEI) property of a FinFET based multicore platform, where processing speed increases with temperature, in the context of approximate real-time computing. In approximate real-time... Read More about MAFin: Maximizing Accuracy in FinFET based Approximated Real-Time Computing.

Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images (2024)
Presentation / Conference Contribution
Toso, M., Fiorini, S., James, S., & Del Bue, A. (2025, March). Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images. Presented at International Conference on 3D Vision (3DV), Singapore

World-wide detailed 2D maps require enormous collective efforts. OpenStreetMap is the result of 11 million registered users manually annotating the GPS location of over 1.75 billion entries, including distinctive landmarks and common urban objects. A... Read More about Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images.