Skip to main content

Research Repository

Advanced Search

Real-time and Controllable Reactive Motion Synthesis via Intention Guidance (2025)
Journal Article
Zhang, X., Chang, Z., Men, Q., & Shum, H. P. H. (in press). Real-time and Controllable Reactive Motion Synthesis via Intention Guidance. Computer Graphics Forum,

We propose a real-time method for reactive motion synthesis based on the known trajectory of input character, predicting instant reactions using only historical, user-controlled motions. Our method handles the uncertainty of future movements by intro... Read More about Real-time and Controllable Reactive Motion Synthesis via Intention Guidance.

Annotation-guided AoS-to-SoA conversions and GPU offloading with data views in C++ (2025)
Journal Article
Weinzierl, T., & Radtke, P. (in press). Annotation-guided AoS-to-SoA conversions and GPU offloading with data views in C++. Concurrency and Computation: Practice and Experience,

The C++ programming language provides classes and structs as fundamental modeling entities. Consequently, C++ code tends to favour array-of-structs (AoS) for encoding data sequences, even thoughstructure-of-arrays (SoA) yields better performance for... Read More about Annotation-guided AoS-to-SoA conversions and GPU offloading with data views in C++.

Video Prediction of Dynamic Physical Simulations with Pixel-Space Spatiotemporal Transformers (2025)
Journal Article
Slack, D. L., Hudson, G. T., Winterbottom, T., & Al Moubayed, N. (in press). Video Prediction of Dynamic Physical Simulations with Pixel-Space Spatiotemporal Transformers. IEEE Transactions on Neural Networks and Learning Systems,

Inspired by the performance and scalability of autoregressive large language models, transformer-based models have seen recent success in the visual domain. This study investigates a transformer adaptation for video prediction with a simple end-to-en... Read More about Video Prediction of Dynamic Physical Simulations with Pixel-Space Spatiotemporal Transformers.

Temporal graph realization with bounded stretch (2025)
Presentation / Conference Contribution
Mertzios, G., Molter, H., Morawietz, N., & Spirakis, P. (2025, August). Temporal graph realization with bounded stretch. Presented at Proceedings of the 50th International Symposium on Mathematical Foundations of Computer Science (MFCS 2025), Warsaw, Poland

DiDGen: Diffusion-based Dual-task Synthesis for Dermoscopic Data Generation (2025)
Presentation / Conference Contribution
Shentu, J., Watson, M., & Al Moubayed, N. (2025, September). DiDGen: Diffusion-based Dual-task Synthesis for Dermoscopic Data Generation. Presented at 28th International Conference on Medical Image Computing and Computer Assisted Intervention, Daejeon, South Korea

Computer-aided diagnosis (CAD) systems for skin lesion analysis reduce costs and workload associated with the manual inspection of skin diseases. Nevertheless, the performance of deep learning (DL)-based CAD systems is constrained by the limited avai... Read More about DiDGen: Diffusion-based Dual-task Synthesis for Dermoscopic Data Generation.

Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations (2025)
Presentation / Conference Contribution
Xiao, C., Chan, H. P., Zhang, H., Aljunied, M., Bing, L., Al Moubayed, N., & Rong, Y. (2025, July). Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations. Presented at Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria

While understanding the knowledge boundaries of LLMs is crucial to prevent hallucination, research on the knowledge boundaries of LLMs has predominantly focused on English. In this work, we present the first study to analyze how LLMs recognize knowle... Read More about Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations.

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models (2025)
Presentation / Conference Contribution
Leask, P., & Al Moubayed, N. (2025, July). Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models. Presented at International Conference on Machine Learning (ICML 2025), Vancouver, Canada

Sparse Autoencoders (SAEs) are a popular method for decomposing Large Language Model (LLM) activations into interpretable latents, however they have a substantial training cost and SAEs learned on different models are not directly comparable. Motivat... Read More about Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models.

Large-Scale Multi-Character Interaction Synthesis (2025)
Presentation / Conference Contribution
Chang, Z., Wang, H., Koulieris, G. A., & Shum, H. P. (2025, August). Large-Scale Multi-Character Interaction Synthesis. Presented at ACM SIGGRAPH 2025, Vancouver, Canada

Realizing temporal transportation trees (2025)
Presentation / Conference Contribution
Mertzios, G., Molter, H., Morawietz, N., & Spirakis, P. (2025, June). Realizing temporal transportation trees. Presented at 51st International Workshop on Graph-Theoretic Concepts in Computer Science (WG 2025), Otzenhausen, Germany

Optimal Scheduling in a Quantum Switch: Capacity and Throughput Optimality (2025)
Journal Article
Bhambay, S., Vasantam, T., & Walton, N. (in press). Optimal Scheduling in a Quantum Switch: Capacity and Throughput Optimality. ACM SIGMETRICS Performance Evaluation Review,

With a growing number of quantum networks in operation, there is a pressing need for performance analysis of quantum switching technologies. A quantum switch establishes, distributes, and maintains entanglements across a network. In contrast to a cla... Read More about Optimal Scheduling in a Quantum Switch: Capacity and Throughput Optimality.

Human Intracranial EEG Biometric Identification (2025)
Presentation / Conference Contribution
Belay, B., & Katsigiannis, S. (2025, July). Human Intracranial EEG Biometric Identification. Presented at International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE EMBC), Copenhagen, Denmark

Sparse Autoencoders Do Not Find Canonical Units of Analysis (2025)
Presentation / Conference Contribution
Leask, P., Bussmann, B., Pearce, M., Bloom, J., Tigges, C., Al Moubayed, N., Sharkey, L., & Nanda, N. (2025, April). Sparse Autoencoders Do Not Find Canonical Units of Analysis. Presented at ICLR2025: The Thirteenth International Conference on Learning Representations, Singapore

A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse autoencoders (SAEs) are a popular method for finding these features in... Read More about Sparse Autoencoders Do Not Find Canonical Units of Analysis.

Semi-supervised Object-Wise Anomaly Detection for Firearm and Firearm Component Detection in X-ray Security Imagery (2025)
Presentation / Conference Contribution
Gaus, Y. F. A., Isaac-Medina, B. K. S., Bhowmik, N., Lam, Y. T., & Breckon, T. P. (2025, June). Semi-supervised Object-Wise Anomaly Detection for Firearm and Firearm Component Detection in X-ray Security Imagery. Presented at 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, Tennessee, USA

FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment (2025)
Presentation / Conference Contribution
Han, R., Zhou, K., Atapour-Abarghouei, A., Liang, X., & Shum, H. P. H. (2025, June). FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment. Presented at Proceedings of the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025, Music City Center, Nashville TN

Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep learning approaches often operate as black boxes and are vulnerable to s... Read More about FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment.

Decentralized Autonomous Navigation of Large-Scale Robotic Swarms with Control Barrier Functions (2025)
Presentation / Conference Contribution
Pan, H., Wang, H., Arvin, F., & Hu, J. (2025, July). Decentralized Autonomous Navigation of Large-Scale Robotic Swarms with Control Barrier Functions. Presented at 2025 IFAC Symposium on Robotics, Paris, France

This paper addresses the shape formation problem for large-scale robotic swarms by proposing an optimization-based cooperative navigation method. First, the physical space is partitioned into multiple disjoint bins, and the stochastic evolution of ro... Read More about Decentralized Autonomous Navigation of Large-Scale Robotic Swarms with Control Barrier Functions.