Some of our recent publications are included below. You can find a more comprehensive, up to date list at Google Scholar.


Paper Thumbnail
Scalable and cost-efficient de novo template-based molecular generation
Gaiński, P., Boussif, O., Shevchuk, D., Rekesh, A., Parviz, A., Tyers, M., Batey, R.A., Koziarski, M.
ICLR 2025 Workshop on Generative and Experimental Perspectives for Biomolecular Design. 2025.
Link to paper

Paper Thumbnail
Learning decision trees as amortized structure inference
Mahfoud, M., Boukachab, G., Koziarski, M., Hernandez-Garcia, A., Bauer, S., Bengio, Y., Malkin, N.
arXiv. 2025.
Link to paper

Paper Thumbnail
Diverse and feasible retrosynthesis using GFlowNets
Gaiński, P., Koziarski, M., Maziarz, K., Segler, M., Tabor, J. and Śmieja, M.
Information Sciences. 2025.
Link to paper

Paper Thumbnail
Action abstractions for amortized sampling
Boussif, O., Ezzine, L.N., Viviano, J.D., Koziarski, M., Jain, M., Malkin, N., Bengio, E., Assouel, R., Bengio, Y.
ICLR. 2025.
Link to paper

Paper Thumbnail
RGFN: synthesizable molecular generation using GFlowNets
Koziarski, M., Rekesh, A., Shevchuk, D., van der Sloot, A., Gaiński, P., Bengio, Y., Liu, C.H., Tyers, M. and Batey, R.A.
NeurIPS. 2024.
Link to paper

Paper Thumbnail
A high-throughput phenotypic screen combined with an ultra-large-scale deep learning-based virtual screening reveals novel scaffolds of antibacterial compounds
Scalia, G., Rutherford, S. T., Lu, Z., Buchholz, K. R., Skelton, N., Chuang, K., ... & Biancalani, T.
bioRxiv. 2024.
Link to paper

Paper Thumbnail
Cell morphology-guided small molecule generation with GFlowNets
Lu, S.Z., Lu, Z., Hajiramezanali, E., Biancalani, T., Bengio, Y., Scalia, G. and Koziarski, M.
ICML AI for Science Workshop. 2024.
Link to paper

Paper Thumbnail
Towards equilibrium molecular conformation generation with GFlowNets
Volokhova, A., Koziarski, M., Hernández-García, A., Liu, C.H., Miret, S., Lemos, P., Thiede, L., Yan, Z., Aspuru-Guzik, A. and Bengio, Y.
Digital Discovery. 2024.
Link to paper

Paper Thumbnail
Towards foundational models for molecular learning on large-scale multi-task datasets
Beaini, D., Huang, S., Cunha, J. A., Li, Z., Moisescu-Pareja, G., Dymov, O., ... & Masters, D.
ICLR. 2024.
Link to paper

Paper Thumbnail
ChiENN: embracing molecular chirality with graph neural networks
Gaiński, P., Koziarski, M., Tabor, J. and Śmieja, M.
ECML. 2023.
Link to paper