AIConfPaper
← Search

Pablo Lemos

10 accepted papers

2026

MIRA: A Score for Conditional Distribution Accuracy and Model Comparison

Sammy Sharief, Justine Zeghal, Gabriel Missael Barco, Pablo Lemos, Yashar Hezaveh, Laurence Perreault-Levasseur
ICML 2026spotlight

We present Mira, a method for estimating the expected probability that samples from a candidate conditional distribution match the true, unknown conditional distribution, for which only data-label pairs are available. We derive theoretical bounds obtained when the candidate distribution matches the …

Cited by 0Source ↗Scholar ↗
2026

SAIR: Enabling Deep Learning for Protein-Ligand Interactions with a Synthetic Structural Dataset

Pablo Lemos, Zane Beckwith, Sasaank Bandi, Maarten Van Damme, Jordan Crivelli-Decker, Benjamin J. Shields +8
ICLR 2026poster

Accurate prediction of protein-ligand binding affinities remains a cornerstone problem in drug discovery. While binding affinity is inherently dictated by the 3D structure and dynamics of protein-ligand complexes, current deep learning approaches are limited by the lack of high-quality experimental…

Cited by 0Source ↗Scholar ↗
2025

PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

Pablo Lemos, Sammy Nasser Sharief, Nikolay Malkin, Salma Salhi, Connor Stone, Laurence Perreault-Levasseur +1
ICLR 2025poster

We propose a likelihood-free method for comparing two distributions given samples from each, with the goal of assessing the quality of generative models. The proposed approach, PQMass, provides a statistically rigorous method for assessing the performance of a single generative model or the comparis…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

Amortizing intractable inference in diffusion models for vision, language, and control

Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan +9
NeurIPS 2024poster

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies *amortized* sampling of the posterior over data, $\mathbf{x}\sim p^{\rm…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2024

Improved off-policy training of diffusion samplers

Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks +3
NeurIPS 2024poster

We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow netw…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2024

Improving Gradient-Guided Nested Sampling for Posterior Inference

Pablo Lemos, Nikolay Malkin, Will Handley, Yoshua Bengio, Yashar Hezaveh, Laurence Perreault-Levasseur
ICML 2024poster

We present a performant, general-purpose gradient-guided nested sampling (GGNS) algorithm, combining the state of the art in differentiable programming, Hamiltonian slice sampling, clustering, mode separation, dynamic nested sampling, and parallelization. This unique combination allows GGNS to scale…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2024

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities

Tara Akhound-Sadegh, Jarrid Rector-Brooks, Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu +6
ICML 2024poster

Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a nove…

Cited by 49Source ↗PDF ↗code ↗Scholar ↗
2024

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation

Guillaume Huguet, James Vuckovic, Kilian FATRAS, Eric Thibodeau-Laufer, Pablo Lemos, Riashat Islam +6
NeurIPS 2024poster

Proteins are essential for almost all biological processes and derive their diverse functions from complex $3 \rm D$ structures, which are in turn determined by their amino acid sequences. In this paper, we exploit the rich biological inductive bias of amino acid sequences and introduce FoldFlow++,…

Cited by 31Source ↗PDF ↗Scholar ↗
2023

A theory of continuous generative flow networks

Salem Lahlou, Tristan Deleu, Pablo Lemos, Dinghuai Zhang, Alexandra Volokhova, Alex Hernández-García +3
ICML 2023poster

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory fo…

Cited by 90Source ↗PDF ↗code ↗Scholar ↗
2023

Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Pablo Lemos, Adam Coogan, Yashar Hezaveh, Laurence Perreault-Levasseur
ICML 2023poster

Parameter inference, i.e. inferring the posterior distribution of the parameters of a statistical model given some data, is a central problem to many scientific disciplines. Posterior inference with generative models is an alternative to methods such as Markov Chain Monte Carlo, both for likelihood-…

Cited by 50Source ↗PDF ↗code ↗Scholar ↗