← Back to home
Publications
A full list. For the most-cited and most-recent picks, see selected publications on the home page or my Google Scholar profile.
Pre-prints
- T. Delgado, H. Hazard, M. Benfeghoul, J. Wang, Z. Fountas, “LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time”, arXiv, 2026. (arXiv, website, code, Hugging Face, models)
- H. Zhao, Z. Fountas, J. Wang, “Can Large Language Model Agents Learn by Watching Tutorial Videos?”, arXiv, 2026. (arXiv, Hugging Face)
- L. Pacchiardi, P. Paskov, S. Ó hÉigeartaigh, F. Martínez‑Plumed, K. M. Collins, F. Barez, J. Prunty, M. G. Mecattaf, Z. Fountas, R. Uuk, S. Koyejo, C. Ududec, J. Hernández‑Orallo, “Continual Learning Requires Evaluating Trajectories”, preprint (Zenodo / PhilArchive), 2026. (DOI, website)
- Z. Fountas, A. Oomerjee, H. Bou‑Ammar, J. Wang, N. Burgess, “Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation”, arXiv, 2026. (arXiv, website)
- P. Urbina‑Rodriguez, Z. Fountas, F. E. Rosas, J. Wang, A. I. Luppi, H. Bou‑Ammar, M. Shanahan, P. A. M. Mediano, “A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning”, arXiv, 2026. (arXiv)
- J. Ma, J. Wang, Z. Fountas, “Emergent Bayesian Behaviour and Optimal Cue Combination in LLMs”, arXiv, 2025. (arXiv)
- H. Hazard, Z. Fountas, M. A. Benfeghoul, A. Oomerjee, J. Wang, H. Bou‑Ammar, “SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning”, arXiv, 2025. (arXiv)
- F. Wieser, M. A. Benfeghoul, H. Bou‑Ammar, J. Wang, Z. Fountas, “Subjective Depth and Timescale Transformers: Learning Where and When to Compute”, arXiv, 2025. (arXiv)
- M. A. Benfeghoul, T. Delgado, A. Oomerjee, H. Bou‑Ammar, J. Wang, Z. Fountas, “Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods”, arXiv, 2025. (arXiv)
- M. A. Benfeghoul, U. Zahid, Q. Guo, Z. Fountas, “When in Doubt, Think Slow: Iterative Reasoning with Latent Imagination”, arXiv, 2024. (arXiv)
- U. Zahid, Q. Guo, K. Friston, Z. Fountas, “Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlo”, arXiv, 2023. (arXiv)
- A. Zakharov, Q. Guo, Z. Fountas, “Long-horizon Video Prediction Using a Dynamic Latent Hierarchy”, arXiv, 2022. (arXiv)
- A. Mariola, Z. Fountas, L. Barnett, W. Roseboom, “Event Segmentation in Continuous, Naturalistic Videos from Model-Based, Data-Driven, and Human Perspectives”, PsyArXiv, 2022. (DOI)
- O. Miksik, I. Munasinghe, J. Asensio-Cubero, S. Reddy Bethi, S.-T. Huang, S. Zylfo, X. Liu, T. Nica, A. Mitrocsak, S. Mezza, R. Beard, R. Shi, R. Ng, P. Mediano, Z. Fountas, S.-H. Lee, J. Medvesek, H. Zhuang, Y. Rogers, P. Swietojanski, “Building Proactive Voice Assistants: When and How (not) to Interact”, arXiv, 2020. (arXiv)
- Z. Fountas, M. Shanahan, “Assessing Selectivity in the Basal Ganglia: The ‘Gearbox’ Hypothesis”, bioRxiv, 2017. (bioRxiv)
Journal articles
- U. Zahid, Q. Guo, Z. Fountas, “Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluation”, Neural Computation 35(12): 1881–1909, 2023. (DOI, arXiv)
- M. T. Sherman, Z. Fountas, A. K. Seth, W. Roseboom, “Trial-by-trial Predictions of Subjective Time from Human Brain Activity”, PLoS Computational Biology 18(7): e1010223, 2022. (DOI)
- Z. Fountas, A. Sylaidi, K. Nikiforou, A. K. Seth, M. Shanahan, W. Roseboom, “A Predictive Processing Model of Episodic Memory and Time Perception”, Neural Computation 34(7): 1501–1544, 2022. (DOI, bioRxiv, code)
- T. Wilschut, F. Sense, M. van der Velde, Z. Fountas, S. C. Maaß, H. van Rijn, “Benefits of Adaptive Learning Transfer from Typing-Based Learning to Speech-Based Learning”, Frontiers in Artificial Intelligence 4: 780131, 2021. (DOI)
- A. Löffler, A. Sylaidi, Z. Fountas, P. Haggard, “A Hierarchical Attractor Network Model of Perceptual versus Intentional Decision Updates”, Nature Communications 12: 2020, 2021. (DOI, code)
- N. Sajid, E. Holmes, T. M. Hope, Z. Fountas, C. J. Price, K. J. Friston, “Simulating Lesion-Dependent Functional Recovery Mechanisms”, Scientific Reports 11: 7475, 2021. (DOI)
- M. Suárez‑Pinilla, K. Nikiforou, Z. Fountas, A. K. Seth, W. Roseboom, “Perceptual Content, Not Physiological Signals, Determines Perceived Duration When Viewing Dynamic, Natural Scenes”, Collabra: Psychology 5(1): 55, 2019. (DOI)
- W. Roseboom, Z. Fountas, K. Nikiforou, D. Bhowmik, M. Shanahan, A. K. Seth, “Activity in Perceptual Classification Networks as a Basis for Human Subjective Time Perception”, Nature Communications 10: 267, 2019. (DOI, code, dataset)
- Z. Fountas, M. Shanahan, “The Role of Cortical Oscillations in a Spiking Neural Network Model of the Basal Ganglia”, PLOS ONE 12(12): e0189109, 2017. (DOI)
- D. Gamez, Z. Fountas, A. K. Fidjeland, “A Neurally Controlled Computer Game Avatar with Human-like Behavior”, IEEE Transactions on Computational Intelligence and AI in Games 5(1), 2013. (DOI)
Book chapters
- R. Vertegaal, T. Merritt, S. Greenberg, A. P. Tarun, Z. Li, Z. Fountas, “Interactive Inference”, in J. A. Jacko (ed.), Human Computer Interaction Handbook: Fundamentals, Evolving Technologies, and Emerging Applications, 4th ed., CRC Press, pp. 1408–1426, 2026. Preprint title: “Interactive Inference: A Neuromorphic Theory of Human-Computer Interaction”. (DOI, arXiv)
- Z. Fountas, A. Zakharov, “Bayesian Sense of Time in Biological and Artificial Brains”, in R. Lestienne & P. Harris (eds.), Time and Science, Vol. 2: Life Sciences, World Scientific, pp. 237–265, 2023. (DOI, arXiv)
Conference and workshop papers
- A. Oomerjee, Z. Fountas, H. Bou‑Ammar, J. Wang, “Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning”, ICLR 2026. (arXiv, OpenReview)
- M. A. Benfeghoul, H. Bou‑Ammar, J. Wang, Z. Fountas, “Hierarchical Episodic Memory in LLMs via Multi-Scale Event Organization”, Workshop on New Frontiers in Associative Memories, ICLR 2025. (OpenReview)
- Z. Fountas, M. A. Benfeghoul, A. Oomerjee, F. Christopoulou, G. Lampouras, H. Bou‑Ammar, J. Wang, “Human-inspired Episodic Memory for Infinite Context LLMs”, ICLR 2025. (arXiv, OpenReview, website, code)
- U. Zahid, Q. Guo, Z. Fountas, “Sample as You Infer: Predictive Coding with Langevin Dynamics”, ICML 2024, PMLR 235: 58105–58121. (arXiv, OpenReview)
- J. Coda‑Forno, C. Yu, Q. Guo, Z. Fountas, N. Burgess, “Leveraging Episodic Memory to Improve World Models for Reinforcement Learning”, Workshop on Memory in Artificial and Real Intelligence (MemARI), NeurIPS 2022. (OpenReview)
- N. Sajid, P. Tigas, Z. Fountas, Q. Guo, A. Zakharov, L. Da Costa, “Modelling Non-Reinforced Preferences Using Selective Attention”, Workshop track, CoLLAs 2022. (arXiv)
- W. Roseboom, A. K. Seth, M. T. Sherman, Z. Fountas, “The Perception of Time in Humans, Brains and Machines”, 13th Symposium of the BIAL Foundation (Behind and Beyond the Brain), Porto, 2022. (PsyArXiv)
- A. Zakharov, Q. Guo, Z. Fountas, “Variational Predictive Routing with Nested Subjective Timescales”, ICLR 2022. (arXiv, OpenReview, website)
- N. Sajid, P. Tigas, A. Zakharov, Z. Fountas, K. Friston, “Exploration and Preference Satisfaction Trade-off in Reward-free Learning”, Unsupervised Reinforcement Learning Workshop, ICML 2021. (OpenReview)
- A. Zakharov, M. Crosby, Z. Fountas, “Episodic Memory for Learning Subjective-Timescale Models”, Unsupervised Reinforcement Learning Workshop, ICML 2021. (OpenReview)
- T. Wilschut, M. van der Velde, F. Sense, Z. Fountas, H. van Rijn, “Translating a Typing-Based Adaptive Learning Model to Speech-Based L2 Vocabulary Learning”, ACM UMAP 2021, pp. 245–250. (DOI)
- Z. Fountas, N. Sajid, P. A. M. Mediano, K. Friston, “Deep Active Inference Agents Using Monte-Carlo Methods”, NeurIPS 2020. (proceedings, code, talk)
- C. Bao, Z. Fountas, T. Olugbade, N. Bianchi‑Berthouze, “Multimodal Data Fusion based on the Global Workspace Theory”, ACM ICMI 2020. (DOI, arXiv)
- J. Yamada, J. Shawe‑Taylor, Z. Fountas, “Evolution of a Complex Predator-Prey Ecosystem on Large-scale Multi-Agent Deep Reinforcement Learning”, IJCNN 2020. (arXiv)
- M. T. Sherman, Z. Fountas, A. K. Seth, W. Roseboom, “The Accumulation of Salient Changes in Visual Cortex Predicts Subjective Time”, CCN 2019, Berlin. (pdf, archived)
- Z. Fountas, K. Nikiforou, D. Bhowmik, M. Shanahan, W. Roseboom, A. K. Seth, “Clockless Biologically-Plausible Architecture for Temporal Perception Using Convolutional Neural Networks”, CCN 2017. (pdf)
- J. C. Farah, C. Kaplanis, C. Snowden, L. Milic, Z. Fountas, P. A. M. Mediano, “Implementation of Attentional Bistability in a Computational Model of the Dragonfly Visual System”, CCN 2017. (pdf)
- Z. Fountas, M. Shanahan, “GPU-based Fast Parameter Optimization for Phenomenological Spiking Neural Models”, IJCNN 2015, Killarney. (DOI)
- Z. Fountas, M. Shanahan, “Phase Offset Between Slow Oscillatory Cortical Inputs Influences Competition in a Model of the Basal Ganglia”, IJCNN 2014, Beijing, pp. 2407–2414. (DOI, pdf)
- Z. Fountas, M. Shanahan, “A Cognitive Neural Architecture as a Robot Controller”, in Biomimetic and Biohybrid Systems (Living Machines 2013), Springer, pp. 371–373, 2013. (DOI)
- Z. Fountas, D. Gamez, A. K. Fidjeland, “A Neuronal Global Workspace for Human-like Control of a Computer Game Character”, IEEE CIG 2011, Seoul, pp. 350–357. (DOI, pdf)
Patent applications
- R. P. H. Vertegaal, D. Holman, Z. Fountas, A. P. Tarun, “Methods and systems for management of device notifications based on proxemic probability density function”, US patent application 2025/0036493 A1, filed 2023, published 2025. (Google Patents)
- Q. Guo, Z. Fountas, A. Zakharov, “Encoding and decoding method, device and related equipment”, Chinese patent application CN115908593A, filed 2021, published 2023. (Google Patents)
Posters and early student papers
- D. Gamez, Z. Fountas, M. Shanahan, A. K. Fidjeland, “A Cognitive System with a Neurally-Implemented Global Workspace”, poster, CogSys 2012. (pdf)
- P.A.N.D.O.R.A. robotics team (incl. Z. Fountas), “Ρομποτική Πλατφόρμα Διάσωσης” (A rescue robotics platform: construction and use at RoboCup Rescue 2008), 3rd National Convention of Electrical and Computer Engineering Students (ΣΦΗΜΜΥ 3), Thessaloniki, 2009. Best paper, demo session. In Greek. (pdf)
- IEEE Robotics Chapter Team of AUTH (incl. Z. Fountas), “Ρομποτικός βραχίονας 4 βαθμών ελευθερίας” (A four-degree-of-freedom robotic arm for locating and moving objects), 2nd National Convention of Electrical and Computer Engineering Students (ΣΦΗΜΜΥ 2), Athens, 2008. Best paper, demo session. In Greek. (pdf)
- P.A.N.D.O.R.A. robotics team (incl. Z. Fountas), “RoboCupRescue 2008 — Robot League Team P.A.N.D.O.R.A. (Greece)”, 1st National Convention of Robotics, 2008. In Greek. (pdf)
Theses & technical reports
- “Action Selection in the Rhythmic Brain: The Role of the Basal Ganglia and Tremor”, PhD thesis, Imperial College London, 2016. (Spiral)
- “Spiking Neural Networks for Human-like Avatar Control in a Simulated Environment”, MSc thesis, Imperial College London, 2011. (pdf)
- “RoboCupRescue 2009 — Robot League Team P.A.N.D.O.R.A. (Greece)”, RoboCup World Championship and Symposium, Graz, 2009. (pdf)
- “RoboCupRescue 2008 — Robot League Team P.A.N.D.O.R.A. (Greece)”, RoboCup World Championship and Symposium, Suzhou, 2008. (pdf)