Publications

Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute
Kieran Didi
Zuobai Zhang
Guoqing Zhou
Danny Reidenbach
Zhonglin Cao
Sooyoung Cha
Tomas Geffner
Christian Dallago
Jian Tang
Michael Bronstein
Martin Steinegger
Emine Kucukbenli
Arash Vahdat
Karsten Kreis
Protein interaction modeling is central to protein design, which has been transformed by machine learning with broad applications in drug di… (see more)scovery and beyond. In this landscape, structure-based de novo binder design is most often cast as either conditional generative modeling or sequence optimization via structure predictors ("hallucination"). We argue that this is a false dichotomy and propose Complexa, a novel fully atomistic binder generation method unifying both paradigms. We extend recent flow-based latent protein generation architecture and leverage the domain-domain interactions of monomeric computationally predicted protein structures to construct Teddymer, a new large-scale dataset of synthetic binder-target pairs for pretraining. Combined with high-quality experimental multimers, this enables training a strong base model. We then perform inference-time optimization with this generative prior, unifying the strengths of previously distinct generative and hallucination methods. Complexa sets a new state of the art in computational binder design benchmarks: it delivers markedly higher in-silico success rates than existing generative approaches, and our novel test-time optimization strategies greatly outperform previous hallucination methods under normalized compute budgets. We further demonstrate explicit interface hydrogen bond optimization, fold class-guided binder generation, and extensions to small molecule targets and enzyme design tasks, again surpassing prior methods. Code, models and new data will be publicly released.
2025-12-31
International Conference on Learning Representations (Accept (Oral))
openreview.net
openreview.net
SelvaBox: A high‑resolution dataset for tropical tree crown detection
Hugo Baudchon
Arthur Ouaknine
Martin Weiss
Mélisande Teng
Thomas Walla
Antoine Caron-Guay
Christopher Pal
Étienne Laliberté
Detecting individual tree crowns in tropical forests is essential to study these complex and crucial ecosystems impacted by human interventi… (see more)ons and climate change. However, tropical crowns vary widely in size, structure, and pattern and are largely overlapping and intertwined, requiring advanced remote sensing methods applied to high-resolution imagery. Despite growing interest in tropical tree crown detection, annotated datasets remain scarce, hindering robust model development. We introduce SelvaBox, the largest open‑access dataset for tropical tree crown detection in high-resolution drone imagery. It spans three countries and contains more than
2025-12-31
International Conference on Learning Representations (Accept (Poster))
openreview.net
openreview.net
Sex Classification Based on the Functional Connectivity Patterns of the Language Network: A Resting State <scp>fMRI</scp> Study
Xanthy Lajoie
C. DeRoy
C. Bedetti
Bérengère Houzé
N. Clarke
Sébastien Hétu
M.‐È. Picard
Lune Bellec
S. M. Brambati
ABSTRACT Research on sex differences in the brain is essential for a better understanding of how the brain develops and ages, and how neurol… (see more)ogical and psychiatric conditions can impact men and women differently. While numerous studies have focused on sex differences in brain structures, few have examined the characteristics of functional networks, particularly the language network. Although previous research suggests similar overall language performance across sexes, differences may still exist in the brain networks that underlie language processing. In addition, prior studies on sex differences in language have predominantly relied on task‐based fMRI, which may fail to capture subtle differences in underlying functional activity. In this study, we applied a machine learning approach to classify participants' sex based on resting‐state functional connectivity patterns of the language network in healthy young adults (270 men and 288 women; age: 22–36 years), and to identify the most predictive functional connectivity features. The classifier achieved 91.3% accuracy, with key discriminant features anchored to the left opercular part of the inferior frontal gyrus, the left planum temporale, and the left anterior middle temporal gyrus. These regions show distinctive connectivity patterns with heteromodal association cortices, including the occipital poles, angular gyrus, posterior cingulate gyrus, and intraparietal sulcus. Although there was an overlap between men and women, men displayed stronger functional connectivity values in these regions. These findings highlight sex‐related differences in functional connectivity patterns of the language network at rest, underscoring the importance of considering sex as a variable in future research on language and brain function.
2025-12-31
Human Brain Mapping (published)
doi.org
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
Kaustubh Mani
Yann Pequignot
Vincent Mai
Liam Paull
Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains. In this paper, we approach s… (see more)afe exploration through the lens of epistemic uncertainty, where the actor’s sensitivity to parameter perturbations serves as a practical proxy for regions of high uncertainty. We propose Sharpness-Aware Policy Optimization (SHAPO), a sharpness-aware policy update rule that evaluates gradients at perturbed parameters, making policy updates pessimistic with respect to the actor’s epistemic uncertainty. Analytically we show that this adjustment implicitly reweighs policy gradients, amplifying the influence of rare unsafe actions while tempering contributions from already safe ones, thereby biasing learning toward conservative behavior in under-explored regions. Across several continuous-control tasks, our method consistently improves both safety and task performance over existing baselines, significantly expanding their Pareto frontiers.
2025-12-31
International Conference on Learning Representations (Accept (Poster))
openreview.net
openreview.net
Species Loss Scenarios Identify Canada's Northern Ecosystems as Disproportionately Vulnerable
Isaac Eckert
Dominique Caron
Laura J. Pollock
2025-12-31
Journal of Biogeography (published)
doi.org
SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
Riyasat Ohib
Bishal Thapaliya
Gintare Karolina Dziugaite
Jingyu Liu 0001
Vince D. Calhoun
Sergey Plis
In this work, we propose Salient Sparse Federated Learning (SSFL), a streamlined approach for sparse federated learning with efficient commu… (see more)nication. SSFL identifies a sparse subnetwork prior to training, leveraging parameter saliency scores computed separately on local client data in non-IID scenarios, and then aggregated, to determine a global mask. Only the sparse model weights are trained and communicated each round between the clients and the server. On standard benchmarks including CIFAR-10, CIFAR-100, and Tiny-ImageNet, SSFL consistently improves the accuracy sparsity trade off, achieving more than 20\% relative error reduction on CIFAR-10 compared to the strongest sparse baseline, while reducing communication costs by
2025-12-31
Trans. Mach. Learn. Res. (published)
arxiv.org
arxiv.org
Suspected Biliary Atresia in Brazil: Impact of Regional Healthcare Variations on Diagnostic Timeliness
Luiza Telles
Paulo Henrique Moreira Melo
Ana Maria Bicudo Diniz
Gabriele Lech
Ayla Gerk
Lauren Kratky
Dan Poenaru
David P. Mooney
Joaquim Bustorff-Silva
2025-12-31
Journal of Pediatric Surgery Open (published)
doi.org
The 2nd Workshop on Foundation Models for Science: Real-World Impact and Science-First Design
Wuyang Chen
Yongji Wang
N. Benjamin Erichson
Laurence Perreault-Levasseur
Bo Li
Damian Borth
Swarat Chaudhuri
Scientific foundation models should be built for science, not for generic AI tastes or leaderboard prestige. This workshop centers problem-d… (see more)riven design: models that measurably advance real scientific inquiries, e.g., forecasting extreme climate events, accelerating materials discovery, understanding biological mechanisms, co-developed with domain experts and validated against field data, experiments, and downstream impact. We argue that foundation models for science must be built differently from language and vision. Scientific data are physical, causal, spatiotemporal, and often scarce or biased; objectives must reflect mechanistic fidelity, not just predictive accuracy. This calls for scientific priors and constraints, robust uncertainty quantification (UQ), and architectures that natively handle multi-modality (e.g., grids, meshes, spectra, time series, point clouds, text, images, code). It also demands tight integration with classical scientific tools (simulators, PDE solvers, optimization and inference engines, and HPC workflows) to yield hybrid systems that are faster, more accurate, and more trustworthy. We will highlight opportunities and hard problems unique to science: enforcing conservation laws and symmetries; learning across vast spatial and temporal scales; representing extreme events and tipping points; calibrating and validating UQ; and developing evaluation protocols that reward mechanistic insight and actionable reliability. The goal is a roadmap for building, training, and deploying scientific foundation models that accelerate discovery while respecting the structure of the natural world.
2025-12-31
Workshop Proposals @ International Conference on Learning Representations (published)
openreview.net
openreview.net
The Expressive Limits of Diagonal SSMs for State-Tracking
Mehran Shakerinava
Behnoush Khavari
Siamak Ravanbakhsh
Sarath Chandar
State-Space Models (SSMs) have recently been shown to achieve strong empirical performance on a variety of long-range sequence modeling task… (see more)s while remaining efficient and highly-parallelizable. However, the theoretical understanding of their expressive power remains limited. In this work, we study the expressivity of input-Dependent Complex-valued Diagonal (DCD) State-Space Models (SSMs) on sequential state-tracking tasks for abstract groups. It is easy to show that a single DCD SSM layer with a universal decoder can track any Abelian group at finite precision by decomposing it into a product of cyclic groups. We show that this is tight by proving that such a model cannot track any non-Abelian group at finite precision. We further establish the expressivity of multi-layer DCD SSMs. We show that a
2025-12-31
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net
The Geometry and Topology of Circuits: the Manifolds of Modular Addition
Gabriela Moisescu-Pareja
Gavin McCracken
Harley Wiltzer
Vincent Létourneau
Colin Daniels
Doina Precup
Jonathan Love
The Clock and Pizza interpretations, associated with architectures differing in either uniform or learnable attention, were introduced to ar… (see more)gue that different architectural designs can yield distinct circuits for modular addition. In this work, we show that this is not the case, and that both the uniform and trainable attention architectures implement the same algorithm via topologically and geometrically equivalent representations. Our methodology goes beyond the interpretation of individual neurons and weights. Instead, we identify all of the neurons corresponding to each learned representation and then study the collective group of neurons as one entity. This method reveals that each learned representation is a manifold that we can study utilizing tools from topology. Based on this insight, we can statistically analyze the learned representations across hundreds of circuits to demonstrate the similarity between learned modular addition circuits that arise naturally from common deep learning paradigms.
2025-12-31
International Conference on Learning Representations (Accept (Poster))
openreview.net
openreview.net
The Impact of Pediatric Surgery Global Travel Fellowships: A Study by the Canadian Association of Paediatric Surgeons Global Partnership Committee.
Sacha Williams
Natasha Bejjani
Elena Guadagno
Robert Baird
Shahrzad Joharifard
Melanie Morris
Robin Petroze
Dan Poenaru
Sherif Emil
2025-12-31
Journal of Pediatric Surgery (published)
doi.org
The Intricate Dance of Prompt Complexity, Quality, Diversity and Consistency in T2I Models
Zhang Xiaofeng
Aaron Courville
Michal Drozdzal
Adriana Romero-Soriano
Text-to-image (T2I) models offer great potential for creating virtually limitless synthetic data, a valuable resource compared to fixed and … (see more)finite real datasets. Previous works evaluate the utility of synthetic data from T2I models on three key desiderata: quality, diversity, and consistency. While prompt engineering is the primary means of interacting with T2I models, the systematic impact of prompt complexity on these critical utility axes remains underexplored. In this paper, we first conduct synthetic experiments to motivate the difficulty of generalization w.r.t. prompt complexity and explain the observed difficulty with theoretical derivations. Then, we introduce a new evaluation framework that can compare the utility of real data and synthetic data, and present a comprehensive analysis of how prompt complexity influences the utility of synthetic data generated by commonly used T2I models. We conduct our study across diverse datasets, including CC12M, ImageNet-1k, and DCI, and evaluate different inference-time intervention methods. Our synthetic experiments show that generalizing to more general conditions is harder than the other way round, since the former needs an estimated likelihood that is not learned by diffusion models. Our large-scale empirical experiments reveal that increasing prompt complexity results in lower conditional diversity and prompt consistency, while reducing the synthetic-to-real distribution shift, which aligns with the synthetic experiments. Moreover, current inference-time interventions can augment the diversity of the generations at the expense of moving outside the support of real data. Among those interventions, prompt expansion, by deliberately using a pre-trained language model as a likelihood estimator, consistently achieves the highest performance in both image diversity and aesthetics, even higher than that of real data. Combining advanced guidance interventions with prompt expansion results in the most appealing utility trade-offs of synthetic data.
2025-12-31
International Conference on Learning Representations (Accept (Poster))
openreview.net
openreview.net