Pedro O. Pinheiro

I am a research scientist at Genentech, Prescient Design team.

Previously, I was a research scientist at Deep Genomics and Element AI (where I work closely with people from Mila). I received a Ph.D. from École Polytechnique Fédérale de Lausanne (EPFL) and Idiap Research Institute (Switzerland), under supervision of Ronan Collobert. During my phd, I also spent time at Facebook AI Research (FAIR). Previously, I graduated with a MSc. in Image and Signal Processing from Institut National des Sciences Appliquées de Lyon (INSA), in France. I am originally form sunny Fortaleza, Brazil.

Email | LinkedIn

Research

I am interested in machine learning and its applications, specifically deep learning methods for representation learning and generative modeling. Currently, I am interested in developing AI methods that can tackle complex scientific problems, such as molecular sciences and drug discovery.

Below is a list of some work that represent my research interests and style. For a full list of publications, please see my Google Scholar page.

	Implicit generative property enhancer Pedro O. Pinheiro, Pan Kessel, Aya A. Ismail, Sai P. Mahajan, Kyunghyun Cho, Saeed Saremi, Nataša Tagasovska NeurIPS, 2025 paper
	Unified all-atom molecule generation with neural fields Matthieu Kirchmeyer^, Pedro O. Pinheiro^, Karolis Martinkus, Emma Willett, ..., Richard Bonneau, Saeed Saremi NeurIPS, 2025 (^*equal contribution) paper \| code
	Score-based 3D molecule generation with neural fields Matthieu Kirchmeyer^, Pedro O. Pinheiro^, Saeed Saremi NeurIPS, 2024 (^*equal contribution) paper \| code
	Structure-based drug design by denoising voxel grids Pedro O. Pinheiro, Arian Jamasb, Omar Mahmood, Vishnu Sresht, Saeed Saremi ICML, 2024 paper \| code
	3D Molecule generation by denoising voxel grids Pedro O. Pinheiro, Joshua Rackers, Joseph Kleinhenz, Michael Maser, Omar Mahmood, Andrew Martin Watkins, Stephen Ra, Vishnu Sresht, Saeed Saremi NeurIPS, 2023 paper \| code
	DyAb: sequence-based antibody design and property prediction in a low-data regime Joshua Yao-Yu Lin, Jennifer L. Hofmann, Andrew Leaver-Fay,..., Pedro O. Pinheiro,..., Andrew Watkins, Kyunghyun Cho, and Nathan C. Frey bioRxiv, 2025 paper
	An RNA foundation model enables discovery of disease mechanisms and candidate therapeutics Albi Celaj, Alice Jiexin Gao, Tammy T.Y. Lau, Erle M. Holgersen, ..., Pedro O. Pinheiro, ..., Brendan J. Frey bioRxiv, 2023 paper
	Unsupervised learning of dense visual representations Pedro O. Pinheiro, Amjad Almahairi, Ryan Benmalek, Florian Golemo, Aaron C Courville NeurIPS, 2020 paper
	Reinforced active learning for image segmentation Arantxa Casanova, Pedro O. Pinheiro, Negar Rostamzadeh, Christopher J. Pal ICLR, 2020 paper \| code
	Predicting outdoor ultrafine particle number concentrations, particle size, and noise using street-level images and audio data Kris Hong, Pedro O. Pinheiro, Scott Weichenthal Environmental International, 2020 paper
	Adaptive cross-modal few-shot learning C Xing, N Rostamzadeh, B Oreshkin, Pedro O. Pinheiro NeurIPS, 2019 paper \| code
	Extending the spatial scale of land use regression models for ambient ultrafine particles using satellite images and deep convolutional neural networks Kris Hong, Pedro O. Pinheiro, Laura Minet, Marianne Hatzopoulou, Scott Weichenthal Environmental Research, 2019 paper
	Learning to refine object segments Pedro O. Pinheiro, Tsung-Yi Lin, Ronan Collobert, Piotr Dollár ECCV, 2016 paper \| code
	Learning to segment object candidates Pedro O. Pinheiro, Ronan Collobert, Piotr Dollár NIPS, 2015 paper \| code
	From Image-Level to Pixel-Level Labeling With Convolutional Networks Pedro O. Pinheiro, Ronan Collobert CVPR, 2015 paper
	Recurrent convolutional neural networks for scene labeling Pedro O. Pinheiro, Ronan Collobert ICML, 2014 paper