Portrait of Luca Scimeca

Luca Scimeca

Postdoctorate - Université de Montréal

Supervisor

Research Topics

Bayesian Inference

Causality

Computational Biology

Deep Learning

Generative Models

Probabilistic Models

Representation Learning

Blog Posts

A tab representation of the Pre trained CLIP Vision Transformer

October 8, 2025

Why AI Models Hallucinate and How to Fix Them

by

Read the article

Publications

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise

Thomas Jiralerspong

Berton Earnshaw

Jason Hartford

Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In th… (see more)is work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. We introduce an anisotropic noise operator that shapes these biases by replacing the isotropic forward covariance with a structured, frequency-diagonal covariance. This operator unifies band-pass masks and power-law weightings, allowing us to emphasize or suppress designated frequency bands, while keeping the forward process Gaussian. We refer to this as spectrally anisotropic Gaussian diffusion (SAGD). In this work, we derive the score relation for anisotropic covariances and show that, under full support, the learned score converges to the true data score as

2025-10-07

ArXiv (preprint)

Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models

Siddarth Venkatraman

Any well-behaved generative model over a variable …

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (published)

proceedings.mlr.press

Torsional-GFN: a conditional conformation generator for small molecules

Alexandra Volokhova

Lena Nehale Ezzine

Piotr Gai'nski

Emmanuel Bengio

Prudencio Tossou

Alex Hernandez-Garcia

Generating stable molecular conformations is crucial in several drug discovery applications, such as estimating the binding affinity of a mo… (see more)lecule to a target. Recently, generative machine learning methods have emerged as a promising, more efficient method than molecular dynamics for sampling of conformations from the Boltzmann distribution. In this paper, we introduce Torsional-GFN, a conditional GFlowNet specifically designed to sample conformations of molecules proportionally to their Boltzmann distribution, using only a reward function as training signal. Conditioned on a molecular graph and its local structure (bond lengths and angles), Torsional-GFN samples rotations of its torsion angles. Our results demonstrate that Torsional-GFN is able to sample conformations approximately proportional to the Boltzmann distribution for multiple molecules with a single model, and allows for zero-shot generalization to unseen bond lengths and angles coming from the MD simulations for such molecules. Our work presents a promising avenue for scaling the proposed approach to larger molecular systems, achieving zero-shot generalization to unseen molecules, and including the generation of the local structure into the GFlowNet model.

2025-07-15

ArXiv (preprint)

Torsional-GFN: a conditional conformation generator for small molecules

Alexandra Volokhova

Lena Nehale Ezzine

Emmanuel Bengio

Prudencio Tossou

Alex Hernandez-Garcia

2025-06-11

ICML.cc/2025/Workshop/GenBio (poster)

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Siddarth Venkatraman

Any well-behaved generative model over a variable …

2025-05-01

ICML.cc/2025/Conference (poster)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles

Alexander Rubinstein

Damien Teney

Seong Joon Oh

Armand Mihai Nicolicioiu

Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut lea… (see more)rning, where a model relies on erroneous, easy-to-learn cues while ignoring reliable ones. In this work, we propose

2025-03-06

ICLR.cc/2025/Workshop/SCSL (published)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control

Thomas Jiralerspong

Berton Earnshaw

Jason Hartford

Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks… (see more). In this work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. For topologically structured data, we devise a frequency-based noising operator to purposefully manipulate, and set, these inductive biases. We first show that appropriate manipulations of the noising forward process can lead DPMs to focus on particular aspects of the distribution to learn. We show that different datasets necessitate different inductive biases, and that appropriate frequency-based noise control induces increased generative performance compared to standard diffusion. Finally, we demonstrate the possibility of ignoring information at particular frequencies while learning. We show this in an image corruption and recovery task, where we train a DPM to recover the original target distribution after severe noise corruption.

2025-03-06

ICLR.cc/2025/Workshop/DeLTa (poster)

Solving Bayesian inverse problems with diffusion priors and off-policy RL

Siddarth Venkatraman

Moksh J. Jain

Emmanuel Bengio

Jarrid Rector-Brooks

Laurence Perreault-Levasseur

This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (R… (see more)L) objective that can asymptotically solve Bayesian inverse problems optimally. We extend the original work by using RTB to train conditional diffusion model posteriors from pretrained unconditional priors for challenging linear and non-linear inverse problems in vision, and science. We use the objective alongside techniques such as off-policy backtracking exploration to improve training. Importantly, our results show that existing training-free diffusion posterior methods struggle to perform effective posterior inference in latent space due to inherent biases.

2025-03-06

ICLR.cc/2025/Workshop/DeLTa (poster)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control

Thomas Jiralerspong

Berton Earnshaw

Jason Hartford

Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks… (see more). In this work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. For topologically structured data, we devise a frequency-based noising operator to purposefully manipulate, and set, these inductive biases. We first show that appropriate manipulations of the noising forward process can lead DPMs to focus on particular aspects of the distribution to learn. We show that different datasets necessitate different inductive biases, and that appropriate frequency-based noise control induces increased generative performance compared to standard diffusion. Finally, we demonstrate the possibility of ignoring information at particular frequencies while learning. We show this in an image corruption and recovery task, where we train a DPM to recover the original target distribution after severe noise corruption.

2025-02-14

ArXiv (preprint)

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Siddarth Venkatraman

Any well-behaved generative model over a variable …

2025-02-10

ArXiv (preprint)

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Siddarth Venkatraman

Any well-behaved generative model over a variable …

2025-02-10

ArXiv (preprint)

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Siddarth Venkatraman

Any well-behaved generative model over a variable …

2025-02-10

ArXiv (preprint)