On the Design Fundamentals of Diffusion Models: A Survey
(2025)
Journal Article
Chang, Z., Koulieris, G. A., Chang, H. J., & Shum, H. P. H. (in press). On the Design Fundamentals of Diffusion Models: A Survey. Pattern Recognition,
Outputs (3105)
Talking Face Generation with Lip and Identity Priors (2025)
Journal Article
Wu, J., Li, F. W. B., Tam, G. K. L., Yang, B., Nan, F., & Pan, J. (2025). Talking Face Generation with Lip and Identity Priors. Computer Animation and Virtual Worlds, 36(3), Article e70026. https://doi.org/10.1002/cav.70026Speech-driven talking face video generation has attracted growing interest in recent research. While person-specific approaches yield high-fidelity results, they require extensive training data from each individual speaker. In contrast, general-purpo... Read More about Talking Face Generation with Lip and Identity Priors.
Optimal Message-Passing with Noisy Beeps (2025)
Journal Article
Davies-Peck, P. (in press). Optimal Message-Passing with Noisy Beeps. Distributed Computing,Beeping models are models for networks of weak devices, such as sensor networks or biological networks. In these networks, nodes are allowed to communicate only via emitting beeps: unary pulses of energy. Listening nodes have only the capability of c... Read More about Optimal Message-Passing with Noisy Beeps.
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, CanadaSparse 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.
Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos (2025)
Journal Article
Qiao, T., Li, R., Li, F. W. B., Kubotani, Y., Morishima, S., & Shum, H. P. H. (in press). Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos. Expert Systems with Applications, https://doi.org/10.1016/j.eswa.2025.128344
CLN: A multi-task deep neural network for chest X-ray image localisation and classification (2025)
Journal Article
Okolo, G. I., Katsigiannis, S., & Ramzan, N. (online). CLN: A multi-task deep neural network for chest X-ray image localisation and classification. Expert Systems with Applications, Article 128162. https://doi.org/10.1016/j.eswa.2025.128162Chest X-ray (CXR) imaging is a widely used and cost-effective medical imaging technique for detecting various pathologies. However, accurate interpretation of CXR images is a challenging and time-consuming task that requires expert radiologists. Alth... Read More about CLN: A multi-task deep neural network for chest X-ray image localisation and classification.
Service-the-Longest-Queue Among d Choices Policy for Quantum Entanglement Switching (2025)
Presentation / Conference Contribution
Yau, G. X., Vasantam, T., & Vardoyan, G. (2025, March). Service-the-Longest-Queue Among d Choices Policy for Quantum Entanglement Switching. Presented at QCNC2025: International Conference on Quantum Communications, Networking, and Computing, Nara, JapanAn Entanglement Generation Switch (EGS) is a quantum network hub that provides entangled states to a set of connected nodes by enabling them to share a limited number of hub resources. As entanglement requests arrive, they join dedicated queues corre... Read More about Service-the-Longest-Queue Among d Choices Policy for Quantum Entanglement Switching.
SPECTRA: A Markovian Framework for Managing NFR Tradeoffs in Systems with Mixed Observability (2025)
Journal Article
Ignatius, H. T. N., Bahsoon, R., Bencomo, N., & Samin, H. (online). SPECTRA: A Markovian Framework for Managing NFR Tradeoffs in Systems with Mixed Observability. ACM Transactions on Autonomous and Adaptive Systems, https://doi.org/10.1145/3735643Non-Functional Requirements (NFRs) play a critical role in driving self-adaptation in software systems. In Self-Adaptive Systems (SAS), satisfying multiple NFRs simultaneously introduces significant complexity, as these requirements often conflict-im... Read More about SPECTRA: A Markovian Framework for Managing NFR Tradeoffs in Systems with Mixed Observability.
weDecide: Clinical Tool for Shared Decision-Making for Treatment of Menopause Symptoms (2025)
Presentation / Conference Contribution
Bencomo, N., Horrocks, J., Walton, D., & Samin, H. (2025, June). weDecide: Clinical Tool for Shared Decision-Making for Treatment of Menopause Symptoms. Presented at BMS Annual Scientific Conference 2025, Chesford Grange, Kenilworth, UKThis work introduces weDecide, an AI/ML-based clinical tool designed to support personalised and shared decision-making (PSDM) for menopause treatment. The tool combines explainable machine learning models with multi-criteria decision-making methods... Read More about weDecide: Clinical Tool for Shared Decision-Making for Treatment of Menopause Symptoms.
Acyclic, star and injective colouring: A complexity picture for H-free graphs (2025)
Journal Article
Bok, J., Jedličková, N., Martin, B., Ochem, P., Paulusma, D., & Smith, S. (2025). Acyclic, star and injective colouring: A complexity picture for H-free graphs. Journal of Computer and System Sciences, 154, Article 103662. https://doi.org/10.1016/j.jcss.2025.103662A (proper) colouring is acyclic, star, or injective if any two colour classes induce a forest, star forest or disjoint union of vertices and edges, respectively. The corresponding decision problems are Acyclic Colouring, Star Colouring and Injective... Read More about Acyclic, star and injective colouring: A complexity picture for H-free graphs.