All Outputs (3170)

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.

Green AutoML: Energy-Efficient AI Deployment Across the Edge-Fog-Cloud Continuum (2025)
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.

Annotation-guided AoS-to-SoA conversions and GPU offloading with data views in C++ (2025)
Journal Article
Weinzierl, T., & Radtke, P. (2025). Annotation-guided AoS-to-SoA conversions and GPU offloading with data views in C++. Concurrency and Computation: Practice and Experience, 37(21-22), Article e70199. https://doi.org/10.1002/cpe.70199

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

Round-asynchronous amnesiac flooding (2025)
Presentation / Conference Contribution
Alafin, O., Mertzios, G., & Spirakis, P. (2025, September). Round-asynchronous amnesiac flooding. Presented at International Symposium on Algorithmics of Wireless Networks (ALGOWIN 2025), Warsaw, Poland

CPEL: A Causality-Aware, Parameter-Efficient Learning Framework for Adaptation of Large Language Models with Case Studies in Geriatric Care and Beyond (2025)
Journal Article
Xu, J., Gao, J., Liu, X., Yang, G., Liu, J., Long, Y., Huang, Z., & Yang, K. (2025). CPEL: A Causality-Aware, Parameter-Efficient Learning Framework for Adaptation of Large Language Models with Case Studies in Geriatric Care and Beyond. Mathematics, 13(15), Article 2460. https://doi.org/10.3390/math13152460

Adapting Large Language Models (LLMs) to specialized domains like geriatric care remains a significant challenge due to the limited availability of domain-specific data and the difficulty of achieving efficient yet effective fine-tuning. Current meth... Read More about CPEL: A Causality-Aware, Parameter-Efficient Learning Framework for Adaptation of Large Language Models with Case Studies in Geriatric Care and Beyond.

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

Generating large-scale multi-character interactions is a challenging and important task in character animation. Multi-character interactions involve not only natural interactive motions but also characters coordinated with each other for transition.... Read More about Large-Scale Multi-Character Interaction Synthesis.

SCAN: ML-Based Slice Congestion and Admission Network Controller (2025)
Journal Article
Perveen, A., Cebecioglu, B. B., Abozariba, R., Patwary, M., Aneiba, A., Jindal, A., & Al-Kadri, M. O. (online). SCAN: ML-Based Slice Congestion and Admission Network Controller. IEEE Internet of Things Journal, https://doi.org/10.1109/jiot.2025.3592803

Network slicing enables 5G/6G networks to support Ultra-Reliable Low-Latency Communication (ULLC), enhanced Mobile Broadband (eMBB) and Massive Machine-Type Communication (mMTC). However, while this virtual networking technology enhances network effi... Read More about SCAN: ML-Based Slice Congestion and Admission Network Controller.

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. (online). Video Prediction of Dynamic Physical Simulations with Pixel-Space Spatiotemporal Transformers. IEEE Transactions on Neural Networks and Learning Systems, https://doi.org/10.1109/TNNLS.2025.3585949

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.

PRECIOUS: Approximate Real-Time Computing in MLC-MRAM based Heterogeneous CMPs (2025)
Journal Article
Saha, S., Chakraborty, S., Agarwal, S., Sjalander, M., & McDonald-Maier, K. (online). PRECIOUS: Approximate Real-Time Computing in MLC-MRAM based Heterogeneous CMPs. IEEE Transactions on Computers, https://doi.org/10.1109/TC.2025.3590809

Enhancing quality of service (QoS) in approximate-computing (AC) based real-time systems, without violating power limits is becoming increasingly challenging due to contradictory constraints, i.e., power consumption and time criticality, as multicore... Read More about PRECIOUS: Approximate Real-Time Computing in MLC-MRAM based Heterogeneous CMPs.

Real-time and Controllable Reactive Motion Synthesis via Intention Guidance (2025)
Journal Article
Zhang, X., Chang, Z., Men, Q., & Shum, H. P. H. (online). Real-time and Controllable Reactive Motion Synthesis via Intention Guidance. Computer Graphics Forum, https://doi.org/10.1111/cgf.70222

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.

The Proportional Fair Scheduler in Wavelength-Multiplexed Quantum Network (2025)
Presentation / Conference Contribution
Bhambay, S., Koduru Joshi, S., Vasantam, T., & Walton, N. (2025, August). The Proportional Fair Scheduler in Wavelength-Multiplexed Quantum Network. Presented at IEEE Quantum Week — the IEEE International Conference on Quantum Computing and Engineering (QCE) 2025, Albuquerque, New Mexico, USA

On the movement of the honeybee queen in the hive (2025)
Journal Article
Blaha, J., Stefanec, M., Janota, J., Hofstadler, D. N., Rouček, T., Ulrich, J., Fedotoff, L. A., Broughton, G., Vintr, T., Arvin, F., Schmickl, T., & Krajník, T. (2025). On the movement of the honeybee queen in the hive. Scientific Reports, 15, Article 20708. https://doi.org/10.1038/s41598-025-07093-4

A honeybee colony is a complex and dynamic system that emerges out of the interactions of thousands of individuals within a seemingly chaotic and heterogeneous environment. At the figurative core of this system is the honeybee queen, responsible for... Read More about On the movement of the honeybee queen in the hive.

Matching cut and variants on bipartite graphs of bounded radius and diameter (2025)
Journal Article
Lucke, F. (2025). Matching cut and variants on bipartite graphs of bounded radius and diameter. Theoretical Computer Science, 1052, Article 115429. https://doi.org/10.1016/j.tcs.2025.115429

In the MATCHING CUT problem we ask whether a graph G has a matching cut, that is, a matching which is also an edge cut of G. We consider the variants PERFECT MATCHING CUT and DISCONNECTED PERFECT MATCHING where we ask whether there exists a matching... Read More about Matching cut and variants on bipartite graphs of bounded radius and diameter.

Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting (2025)
Presentation / Conference Contribution
Miao, X., Duan, H., Qian, Q., Wang, J., Long, Y., Shao, L., Zhao, D., Xu, R., & Zhang, G. (2025, October). Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting. Presented at International Conference on Computer Vision, ICCV 2025, Honolulu, Hawaii

Recognizing and Realizing Temporal Reachability Graphs (2025)
Presentation / Conference Contribution
Erlebach, T., Michail, O., & Morawietz, N. (2025, September). Recognizing and Realizing Temporal Reachability Graphs. Presented at European Symposium on Algorithms, Warsaw, Poland

Re-clustering for High-performance Metaverse in Vehicular Networks (2025)
Presentation / Conference Contribution
Ahmed, O., Grace, D., Tu, W., & Popoola, K. (2025, August). Re-clustering for High-performance Metaverse in Vehicular Networks. Presented at IEEE MetaCom 2025, Seoul, South Korea

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

Consider a public healthcare system consisting of a hospital, a mobile clinic (MC), and a population of potential patients. The government is concerned about the system’s healthcare spending and the population’s health outcomes. It decides the freque... Read More about Temporal graph realization with bounded stretch.

Designing a generative AI enabled learning environment for mathematics word problem solving in primary schools: Learning performance, attitudes and interaction (2025)
Journal Article
Liu, J., Sun, D., Sun, J., Wang, J., & Yu, P. L. H. (2025). Designing a generative AI enabled learning environment for mathematics word problem solving in primary schools: Learning performance, attitudes and interaction. Computers and Education: Artificial Intelligence, 9, Article 100438. https://doi.org/10.1016/j.caeai.2025.100438

Mathematics word problem solving is a critical component of elementary education, yet many students encounter persistent difficulties in this area due to the combined cognitive demands of linguistic comprehension and mathematical re... Read More about Designing a generative AI enabled learning environment for mathematics word problem solving in primary schools: Learning performance, attitudes and interaction.

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.

Potential-driven Metal Cycling: JADES Census of Gas-phase Metallicity for Galaxies at 1 < z < 7 (2025)
Journal Article
Jia, C., Wang, E., Lyu, C., Ma, C., Song, J., Chen, Y., Wang, K., Yu, H., Chen, Z., Wang, J., Wang, Y., & Kong, X. (2025). Potential-driven Metal Cycling: JADES Census of Gas-phase Metallicity for Galaxies at 1 < z < 7. Astrophysical Journal Letters, 986(2), Article L24. https://doi.org/10.3847/2041-8213/addfd9

The gravitational potential is established as a critical determinant of gas-phase metallicity (12+log(O/H)) in low-redshift galaxies, whereas its influence remains unconfirmed at high redshifts. We investigate the correlation between gas-phase metall... Read More about Potential-driven Metal Cycling: JADES Census of Gas-phase Metallicity for Galaxies at 1 < z < 7.