Publications

For an up-to-date list, see my Google Scholar profile. Below are my publications as listed in my CV*.

*Updated sparingly.

Legend: ★ best paper or thesis award, ◇ cover article and best paper finalist, † equal contribution, * corresponding author.

Journal Articles (36)

K Friston, L Da Costa, A Tschantz, C Heins, C Buckley, T Verbelen, T Parr. Active inference and artificial reasoning. Nature Communications, 2026. arXiv:2512.21129.
V Neacsu, WY So, D Rutar, L Da Costa, RA Adams, K Friston. Reviewing Structure Learning in and Out of the Active Inference Framework. Minds and Machines, 2026.
S Rubin, C Heins, T Mitsui, L Da Costa, K Friston. An elementary form of agency at planetary-scale. Scientific Reports, 2026.
L Da Costa*, AK Seth, K Friston, MJD Ramstead, L Sandved-Smith. A Rosetta Stone hypothesis for neurophenomenology: mathematical predictions from predictive processing. Neuroscience of Consciousness, 2026. arXiv:2409.20318.
N Da Costa, M Pförtner, L Da Costa, P Hennig. Sample Path Regularity of Gaussian Processes from the Covariance Kernel. Analysis and Applications, 2026. arXiv:2312.14886.
L Sandved-Smith†, L Da Costa†. Metacognitive particles, mental action and the sense of agency. Neuroscience of Consciousness, 2025. arXiv:2405.12941.
L Da Costa*, T Gavenčiak, D Hyland, M Samiei, C Dragos-Manta, C Pattisapu, A Razi, K Friston. Possible principles for aligned structure learning agents. Neural Computation, 2025.arXiv:2410.00258.
K Friston, T Parr, C Heins, L Da Costa*, et al. Gradient-free de novo learning. Entropy, 2025.
A Tolchinsky, M Levin, C Fields, L Da Costa, et al. Temporal Depth in a Coherent Self and in Depersonalization: Theoretical Model. Frontiers in Psychology, 2025.
K Friston, C Heins, T Verbelen, L Da Costa, T Salvatori, D Markovic, A Tschantz, M Koudahl, C Buckley, T Parr. From pixels to planning: scale-free active inference. Frontiers in Network Physiology, 2025.
L Da Costa†*, N Da Costa†, C Heins, J Medrano, GA Pavliotis, T Parr, AA Meera, K Friston. A theory of generalised coordinates for stochastic differential equations. Studies in Applied Mathematics, 2025.
K Friston, L Da Costa, A Tschantz, A Kiefer, T Salvatori, V Neacsu, et al. Supervised structure learning. Biological Psychology, 2024.
A Paul, N Sajid, L Da Costa, A Razi. On efficient computation in active inference. Expert Systems with Applications, 2024.
C Heins, B Millidge, L Da Costa, RP Mann, K Friston, ID Couzin. Collective behavior from surprise minimization. PNAS, 2023.
L Da Costa*, L Sandved-Smith. Towards a Bayesian mechanics of metacognitive particles: A commentary on “Path integrals, particular kinds, and strange things” by Friston, Da Costa, Sakthivadivel, Heins, Pavliotis, Ramstead, and Parr. Physics of Life Reviews, 2023.
K Friston, L Da Costa*, DAR Sakthivadivel, C Heins, GA Pavliotis, MJD Ramstead, T Parr. Path integrals, particular kinds, and strange things. Physics of Life Reviews, 2023.
K Friston, L Da Costa*, N Sajid, C Heins, K Ueltzhoeffer, GA Pavliotis, T Parr. The free energy principle made simpler but not too simple. Physics Reports, 2023.
L Da Costa*, GA Pavliotis. The entropy production of stationary diffusions. Journal of Physics A: Mathematical and Theoretical, 2023.
L Da Costa*, N Sajid, T Parr, K Friston, R Smith. Reward Maximisation through Discrete Active inference. Neural Computation, 2023.
MJD Ramstead, DAR Sakthivadivel, C Heins, M Koudahl, B Millidge, L Da Costa, B Klein, K Friston. On Bayesian Mechanics: A Physics of and by Beliefs. Journal of the Royal Society Interface, 2023.
C Heins, L Da Costa. Sparse coupling and Markov blankets: A comment on “How particular is the physics of the Free Energy Principle?” by Aguilera, Millidge, Tschantz and Buckley. Physics of Life Reviews, 2022.
T Champion, L Da Costa, H Bowman, M Grzes. Branching Time Active Inference: the theory and its generality. Neural Networks, 2022.
N Sajid, F Faccio, L Da Costa, T Parr, J Schmidhuber, K Friston. Bayesian brains and the Rényi divergence. Neural Computation, 2022.
◇L Da Costa†*, P Lanillos†, N Sajid, K Friston, S Khan. How active inference could help revolutionise robotics. Entropy, 2022.
L Da Costa*, K Friston, C Heins, GA Pavliotis. Bayesian mechanics for stationary processes. Proceedings of the Royal Society A, 2021.
★K Friston, C Heins, K Ueltzhoeffer, L Da Costa, T Parr. Stochastic Chaos and Markov Blankets. Entropy, 2021.
K Ueltzhoeffer, L Da Costa, D Cialfi, K Friston. A Drive towards Thermodynamic Efficiency for Dissipative Structures in Chemical Reaction Networks. Entropy, 2021.
T Parr, L Da Costa, C Heins, MJD Ramstead, K Friston. Memory and Markov Blankets. Entropy, 2021.
K Friston, L Da Costa, T Parr. Some interesting observations on the free energy principle. Entropy, 2021.
K Ueltzhoeffer, L Da Costa, K Friston. Variational free energy, individual fitness, and population dynamics under acute stress. Comment on “Dynamic and thermodynamic models of adaptation” by Alexander N. Gorban et al. Physics of Life Reviews, 2021.
T Parr, N Sajid, L Da Costa, MB Mirza, K Friston. Generative models for active vision. Frontiers in Neurobotics, 2021.
L Da Costa*, T Parr, B Sengupta, K Friston. Neural dynamics under active inference: plausibility and efficiency of information processing. Entropy, 2021.
K Friston, L Da Costa, D Hafner, C Hesp, T Parr. Sophisticated inference. Neural Computation, 2021.
L Da Costa*, T Parr, N Sajid, S Veselic, V Neacsu, K Friston. Active inference on discrete state-spaces: a synthesis. Journal of Mathematical Psychology, 2020.
S Rubin, T Parr, L Da Costa, K Friston. Future climates: Markov blankets and active inference in the biosphere. Journal of the Royal Society Interface, 2020.
T Parr, L Da Costa, K Friston. Markov blankets, information geometry and stochastic thermodynamics. Philosophical Transactions of the Royal Society A, 2020.

Book Chapters (2)

A Barp†, L Da Costa†, G Franca†, K Friston, M Girolami, MI Jordan, GA Pavliotis. Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents. Geometry and Statistics, Handbook of Statistics Series vol 46 (Eds. F Nielsen, AS Rao, CR Rao), 2022.
N Sajid, L Da Costa, T Parr, K Friston. Active inference, Bayesian optimal design, and expected utility. The Drive for Knowledge (Eds. IC Dezza, E Schulz, CM Wu), 2022.

Conference Papers (1)

V Six†, F Panse†, M Fajeau†, L Da Costa†, M Sharma, A Amayuelas, TZ Xiao, D Hyland, P Hennig, B Schölkopf. Learning POMDP World Models from Observations with Language-Model Priors. Advances in Neural Information Processing Systems (NeurIPS), 2026. arXiv:2605.13740.

Preprints and Submitted Manuscripts (2)

A Tschantz, M Koudahl, H Linander, L Da Costa, C Heins, J Beck, C Buckley. Bayesian Predictive Coding. 2025. arXiv:2503.24016.
N Sajid, E Holmes, L Da Costa, C Price, K Friston. A mixed generative model of auditory word repetition. 2022. bioRxiv.

Peer-Reviewed Workshop Papers (8)

K Zaghw, A Pashea, M Pritsch, W Nuijten, K Friston, L Da Costa. Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification. International Workshop on Active Inference (oral), 2026. arXiv:2608.09512.
L Da Costa, S Namjoshi, MA Ansari, B Schölkopf, Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling. World Modeling Workshop, 2026. arXiv:2511.02091.
M Koudahl, A Tschantz, T Salvatori, H Linander, L Da Costa, J Beck, C Buckley. Bethe Predictive Coding: A Message Passing Realization of Expected Free Energy Minimization. International Workshop on Active Inference, 2025.
L Da Costa*. Toward Universal and Interpretable World Models for Open-ended Learning Agents. NeurIPS 2024 Workshop on Intrinsically Motivated and Open Ended Learning, 2024. arXiv:2409.18676.
T Gavenčiak†, D Hyland†, L Da Costa, MJ Wooldridge, J Kulveit. Path Divergence Objective: Boundedly-Rational Decision Making in Partially Observable Environments. NeurIPS 2024 Workshop on NeuroAI, 2024.
D Hyland†, T Gavenčiak†, L Da Costa, C Heins, V Kovarik, J Gutierrez, MJ Wooldridge, J Kulveit. Free-Energy Equilibria: Toward a Theory of Interactions Between Boundedly-Rational Agents. ICML 2024 Workshop on Models of Human Feedback for AI Alignment, 2024.
N Sajid, P Tigas, Z Fountas, Q Guo, A Zakharov, L Da Costa. Modelling non-reinforced preferences using selective attention. First Conference on Lifelong Learning Agents: Workshop Track, 2022. arXiv:2207.13699.
L Da Costa*, N Sajid, D Zhao, S Tenka. Active inference as a model of agency. RLDM 2022 Workshop on Reinforcement Learning as a Model of Agency, 2022.

Theses (3)

★L Da Costa. Probabilistic Principles for Biophysics and Neuroscience: Entropy production, Bayesian mechanics & the free-energy principle. PhD thesis, Department of Mathematics, Imperial College London, 2024. arXiv:2410.11735.
L Da Costa. Topological Hochschild Homology. Part III essay, Department of Pure Mathematics, University of Cambridge, 2018.
L Da Costa. The Uniformization theorem of Riemann Surfaces. Bachelor thesis, Department of Mathematics, University of Toronto, 2017.