Lennert De Smet

PhD at the DTAI research group of the KU Leuven.

About Me


Having studied and enjoyed many different forms of mathematics, from statistics and analysis to formal logic and abstract algebra, my lifelong interest in modelling intelligence naturally pulled me to the field of AI. In pursuit of this passion, I am now a fourth year PhD student at the DTAI research group of the KU Leuven under the supervision of professor Luc De Raedt. My research interests are mainly related to neurosymbolic AI (NeSy). More specifically, they are located at the intersection of statistics, logic and optimisation. Currently, my research is focused on improving the scalability of probabilistic NeSy methods, both for exact and approximate inference and learning.

Publications


Conference Papers

De Smet, L., Zuidberg Dos Martires, P., Manhaeve, R., Marra, G., Kimmig, A., De Raedt, L. (2023). Neural Probilistic Logic Programming in Discrete-Continuous Domains. In Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI).

De Smet, L., Sansone, E., Zuidberg Dos Martires, P. (2023). Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS).

Verreet, V., De Smet, L., De Raedt, L., Sansone, E. (2024). EXPLAIN, AGREE, LEARN: Scaling Learning for Neural Probabilistic Logic. ECAI 2024.

De Smet, L., Zuidberg Dos Martires, P. (2024). A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetic. In Proceedings of the 38th International Conference on Neural Information Processing Systems (NeurIPS).

Workshop Papers

De Smet, L., Manhaeve, R., Marra, G., Zuidberg Dos Martires, P. (2022). Tensorised Probabilistic Inference for Neural Probabilistic Logic Programming. In the 5th Workshop on Tractable Probabilistic Modeling (TPM).

Verreet, V., De Smet, L., Manhaeve, R., Delobelle, P., Bekker, J., (2023). Inferring Missing CV Skills using PU Learning and Variational Inference. In the ECML-PKDD 2023 International workshop on AI for Human Resources and Public Employment Services.

De Smet, L., Venturato, G., Marra, G., De Raedt, L., (2024). Neurosymbolic Markov Models. In the ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling (SPIGM 2024).