Samira Ebrahimi Kahou

Biography

Samira is an Associate Professor at the University of Calgary in the Schulich School of Engineering. She is also an Adjunct Professor at École de technologie supérieure (ÉTS) in the Department of Software Engineering and Information Technology and McGill University in the School of Computer Science. She is an academic member of Mila - Québec Artificial Intelligence Institute and holds a Canada CIFAR AI Chair. Samira received her Ph.D. in Computer Engineering from Polytechnique Montréal/Mila with an award for the best thesis in the department. Samira also worked as a Postdoctoral Fellow at the McGill School of Computer Science and as a Researcher at Microsoft Research Montréal.

Samira and her group work on solving fundamental problems in representation learning for decision making, with a broad focus on explainability, generalization and efficient learning. Her work has been published in top-tier venues, such as NeurIPS, ICLR, ICML, ICCV, CVPR, TMLR and CoRL. Samira received the 2024 Early Career Excellence in Research Award from the Schulich School of Engineering. Her impactful work in multi-modal learning was recognized twice by ACM ICMI Ten-Year Technical Impact Awards, 2023 as Runner-up and 2025 as Winner.

Current Students

Ivan Anokhin

PhD - Université de Montréal

Principal supervisor :

Irina Rish

ivan.anokhin@mila.quebec

Github

Meghana Bhange

PhD - École de technologie suprérieure

Principal supervisor :

meghana.bhange@mila.quebec

PhD - École de technologie suprérieure

Principal supervisor :

patrik.kenfack@mila.quebec

Website

Github

Somjit Nath

PhD - McGill University

Co-supervisor :

Derek Nowrouzezahrai

somjit.nath@mila.quebec

Website

Facilitating Audits of Language Models

Priyesh Vijayan

PhD - McGill University

Principal supervisor :

Blog Posts

Abstract digital visualization of layered, semi-transparent curved blue and purple panels featuring glowing lines of code, sparkling data points, and bokeh lights against a dark background.

August 7, 2026

Ankur Garg

Xuemin Yu

Hassan Sajjad

Samira Ebrahimi Kahou

Read the article

Publications

GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities

Victor May

Massimo Caccia

The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent v… (see more)ersion updates while preserving backward compatibility. While existing code evolution benchmarks provide valuable insights, they typically lack execution-based evaluation for generating code compliant with specific library versions. To address this, we introduce GitChameleon 2.0, a novel, meticulously curated dataset comprising 328 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. GitChameleon 2.0 rigorously evaluates the capacity of contemporary large language models (LLMs), LLM-powered agents, code assistants, and RAG systems to perform version-conditioned code generation that demonstrates functional accuracy through execution. Our extensive evaluations indicate that state-of-the-art systems encounter significant challenges with this task; enterprise models achieving baseline success rates in the 48-51% range, underscoring the intricacy of the problem. By offering an execution-based benchmark emphasizing the dynamic nature of code libraries, GitChameleon 2.0 enables a clearer understanding of this challenge and helps guide the development of more adaptable and dependable AI code generation methods. We make the dataset and evaluation code publicly available at https://github.com/mrcabbage972/GitChameleonBenchmark.

2026-12-30

OpenReview (published)

Learning From the Past with Cascading Eligibility Traces

Tokiniaina Raharison Ralambomihanta

Ivan Anokhin

Roman Pogodin

Jonathan Cornford

Blake A. Richards

2026-12-30

OpenReview (published)

TRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation

Ankur Garg

Xuemin Yu

Hassan Sajjad

Large language models (LLMs) can produce harmful content while generating a response. A useful safeguard should not only detect this risk du… (see more)ring generation but also intervene while leaving safe responses largely unchanged and provide an auditable record of the internal patterns supporting its decisions. We propose TRACE (Temporal Risk Assessment and Concept Editing), a framework that tracks harmful-response risk during generation, selectively edits token activations, and leaves an auditable trace of its detection and steering decisions. TRACE learns a codebook of recurring activation patterns, with each codebook vector representing a latent concept. At inference time, it assigns each token activation to the nearest codebook vector to obtain the corresponding concept. A gated recurrent unit (GRU) processes the activations and their assigned concept features to predict completed-response harmfulness and a monotone cumulative streaming risk. During steering, activations assigned to harmful concepts are steered along directions defined by nearby benign targets. An external LLM labels the learned concepts post hoc, making detection sequences and harmful-to-benign edit records interpretable. Experiments across three generators and the WildGuard and S-Eval benchmarks show that TRACE improves streaming F1 over Kelp in five of six comparisons while remaining competitive on completed-response detection. TRACE's selective steering reduces Harmbench attack success with little change in refusal on originally safe responses. The post-hoc audit reveals recurring semantic structure in the learned concepts and distinct traces associated with harmful detection, safe generation, and activation edits.

2026-10-10

arXiv (preprint)

Gated Knowledge-Guided Prototype Transfer for Zero-Support Medical Vision-Language Adaptation

Sumaiya Fazal

Rizwan Qureshi

Realistic few-shot adaptation of medical vision-language models (VLMs) can leave low-prevalence classes without any labeled support. The tra… (see more)ining-free ss-text+ solver remains operational in this setting, but its zero-support prototypes receive no visual adaptation and fall back to a completely textual class prototype. We introduce gated Knowledge-Guided Prototype Transfer gated KGPT, a pre-repulsion module that transfers supported-class visual residuals to missing classes using VLM similarity and an ontology-based clinical distance. A validation-free evidence gate scales transfer based on semantic relevance and residual agreement, thereby limiting unsupported extrapolation. In 50 paired realistic one-shot trials on MESSIDOR with FLAIR features, severe and proliferative diabetic retinopathy were absent from every support set. Relative to ss-text+, gated KGPT improved missing-class recall by 5.23\%, average class accuracy by 1.37\%, and the missing/supported recall harmonic mean by 1.83\%. It reduced negative-transfer frequency from 46 to 48\% for ungated transfer to 2\%, while leads to 1.20\% supported-class recall reduction and a 0.45\% top-1 reduction. These results identify that evidence-based gating provides a safety mechanism for the knowledge source.

2026-09-29

WiML @ Neural Information Processing Systems (published)

REBOOT: From Failure to Recovery - A Dataset and Benchmark for Precision Assembly

Nana Yaw Owusu Ofori-Ampofo

Joseph Thekinen

Robot learning policies fail in characteristic ways: they stall in uncertain states, drift during contact-rich alignment, and miss targets b… (see more)y millimetres in precision tasks. Yet training datasets consist largely of successful demonstrations, while real-world benchmarks often reduce performance to binary success. This limits both supervision for recovery and analysis of where failures occur. We introduce REBOOT (Recovery Episode Benchmark for Off-nominal Trajectories), the first robot manipulation benchmark designed around failure as a first-class signal. REBOOT contains 2,160 demonstrations across 18 precision assembly tasks, each decomposed into five shared phases: Align(pick), Engage(pick), Transport, Align(place), and Engage(place), enabling phase-level evaluation beyond terminal success. Failures are introduced across phases and paired with expert recovery trajectories that return the system to a valid continuation state. Tasks are annotated with rotational symmetry, engagement-clearance precision tier, and assembly direction through matched install-remove pairs. Failure episodes are labeled by phase and categorical failure mode, enabling attribution to kinematic stage and tolerance violation. Data includes synchronized RGB-D observations from four viewpoints and grounded natural-language descriptions of phase-level success and failure conditions. Half the dataset contains expert demonstrations; the other half contains recovery demonstrations sampled to reflect failures observed in imitation-learned policy rollouts. We benchmark action-chunked transformer, diffusion, and

2026-09-17

arXiv (preprint)

Discovering Latent Groups for Robust Classification

Ankur Garg

Vincent Michalski

Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented su… (see more)bgroups. Existing methods address this by adjusting network parameters, guided either by subgroup annotations or inferred pseudo-group labels. Yet at inference, these methods produce only a class prediction, with no insight into a sample's latent subgroup. We propose neural classification trees (NCT), a framework that achieves robustness by encoding subgroup structure in its tree-shaped architecture. By routing each sample to an "easy" or "hard" node of this tree -- based on prediction correctness -- and reusing these routes as pseudo-labels for the next iteration, NCT disentangles conflicting subgroups, without requiring subgroup supervision. We evaluate NCT on five benchmarks spanning binary and multi-class spurious correlations. Our experiments show that the learned tree topology provides strong interpretability by consistently isolating minority subgroups, which provides a transparent mapping between the model architecture and the data's latent group structure, while yielding competitive robustness with state-of-the-art methods.

2026-06-21

arXiv (preprint)

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

Parsa Esmati

Somjit Nath

Katja Hofmann

Derek Nowrouzezahrai

Majid Mirmehdi

Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simula… (see more)tors. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this question by probing video diffusion models along latent trajectories corresponding to real videos with known physical plausibility. To obtain such trajectories, we approximately invert the deterministic sampling process by integrating the learned velocity field backward from a clean video latent to noise, giving access to the model's intermediate states and attention maps. Using these recovered trajectories, we show that physical plausibility is linearly decodable from diffusion transformer states across IntPhys and InfLevel, reaching around 81.27% average accuracy and outperforming dedicated representation-learning baselines such as V-JEPA and VideoMAE. Surprisingly, this signal is absent from the VAE latent input and emerges inside the denoising transformer itself, despite the model not being trained with a self-supervised predictive objective. These findings suggest that physically meaningful representations can arise as a byproduct of generative denoising.

2026-06-02

arXiv (preprint)

Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion

Somjit Nath

Jackson J Cone

Derek Nowrouzezahrai

Neuroscientific research has revealed that the brain encodes complex behaviors by leveraging structured, low-dimensional manifolds and dynam… (see more)ically fusing multiple sources of information through adaptive gating mechanisms. Inspired by these principles, we propose a novel reinforcement learning (RL) framework that encourages the disentanglement of dynamics-specific and reward-specific features, drawing direct parallels to how neural circuits separate and integrate information for efficient decision-making. Our approach leverages locally linear embeddings (LLEs) to capture the intrinsic, locally linear structure inherent in many environments—mirroring the local smoothness observed in neural population activity—while concurrently deriving reward-specific features through the standard RL objective. An attention mechanism, analogous to cortical gating, adaptively fuses these complementary representations on a per-state basis. Experimental results on benchmark tasks demonstrate that our method, grounded in neuroscientific principles, improves learning efficiency and overall performance compared to conventional RL approaches, highlighting the benefits of explicitly modeling local state structures and adaptive feature selection as observed in biological systems.

2026-05-24

Transactions on Machine Learning Research (accepted)

Training Fair Tabular Foundation Models

Patrik Kenfack

Jesse C. Cresswell

Anthony L. Caterini

Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on … (see more)new data without task-specific training. Despite the increased use of TFMs in high-stakes decision-making, their fairness properties remain largely unexplored. In this work, we incorporate fairness constraints directly into TFM training, enabling fair predictions in a single forward pass. Our approach addresses two key challenges: limited access to sensitive attributes in training data, and the incompatibility of existing fairness techniques with the in-context learning paradigm. We propose \ftfm{}, a scalable training strategy based on synthetic fairness tasks and a fairness-aware architecture using a gradient reversal layer, which encourages the model to learn representations invariant to sensitive attributes. Experiments on 120 fairness tasks show consistent improvements in fairness while maintaining competitive accuracy.

2026-05-24

FMSD @ International Conference on Machine Learning (oral)

Bootstrap Sampling Improves Model Soup Performance via Increased Model Diversity for Pneumonia Classification

Sara Early

Omata I. Ehizokhale

Nils D. Forkert

Model soups combine multiple trained neural network checkpoints through weight averaging, often outperforming individual models and achievin… (see more)g performance comparable to deep ensembles without increasing inference cost. However, their effectiveness depends critically on checkpoint diversity, and when models are trained on the same dataset, optimization trajectories may converge toward similar regions of parameter space, limiting this diversity. In this work, we investigate bootstrap resampling as a simple data-level mechanism for increasing checkpoint diversity. Using a binary pneumonia classification task and 644 radiographs from the National Institutes of Health (NIH) ChestXray14 dataset, we train pools of convolutional neural networks under varying bootstrap ratios and construct greedy model soups. While checkpoint models trained on the full dataset achieve the highest mean individual accuracy, they are highly similar and offer little complementary signal, limiting the effectiveness of greedy selection. Bootstrap sampling introduces variability in the training data, producing more diverse checkpoints that, although individually weaker, enable greedy soup construction to combine complementary representations and achieve superior overall performance. The strongest model soup, obtained with 70\% bootstrap sampling, achieves a test accuracy of 0.650, representing a 9.8 percentage point improvement over the mean individual checkpoint accuracy (0.551) under the same condition. While absolute performance is limited by the small cohort size and training-from-scratch setting, this result highlights the substantial gains achievable through diversity-driven weight averaging.

2026-05-08

Medical Imaging with Deep Learning (poster)

Estimation of head motion in structural MRI and its impact on cortical morphometry

Charles Bricout

Sylvain Bouix

Motion-related artifacts are inevitable in Magnetic Resonance Imaging (MRI) and can bias automated neuroanatomical metrics such as cortical … (see more)thickness. These biases can interfere with statistical analysis which is a major concern as motion has been shown to be more prominent in certain populations such as children or individuals with ADHD. Manual review cannot objectively quantify motion in anatomical scans, and existing quantitative automated approaches often require specialized hardware or custom acquisition protocols. Here, we train a 3D convolutional neural network to estimate a summary motion metric in retrospective routine research scans by leveraging a large training dataset of synthetically motion-corrupted volumes. We validate our method with one held-out site from our training cohort and with 14 fully independent datasets, including one with manual ratings, achieving a Spearman Rank correlation of 0.71 vs. manual labels. We also tested the correlation of our predicted motion score with morphometric measurements known to be impacted by motion, achieving significant correlation on most datasets. Furthermore, our predicted motion correlates with subject age in line with prior studies. Our approach shows good generalization across scanner brands and protocols, enabling objective, scalable motion assessment in structural MRI studies without prospective motion correction. Finally, we provide empirical evidence that our motion estimator significantly improve model fitness when studying cortical thickness and volume. Our final model is made openly and freely available through “Agitation," a tool usable as a CLI, python package and integrated in Nipoppy and Boutiques. By providing reliable motion estimates, our method offers researchers a tool to assess and account for potential biases in cortical morphometric analyses.

2026-05-07

Frontiers in Neuroscience (published)

Does a Hybrid Space-Aware Randomized Defense Improve Empirical and Certified Adversarial Robustness?

Joy Dhar

Manish Kumar Pandey

Behzad Bozorgtabar

Nayyar Zaidi

Wenyu Zhang

Wei-Hong Li

Tingting Mu

Dwarikanath Mahapatra

Mahsa Baktashmotlagh

Trung Le

Chen Chen

Sajib Mistry

Camila Gonzalez

Lina Yao

Piotr Koniusz

Robert Burns Fisher

Dinh Phung

Bohyung Han

Nuno Vasconcelos … (see 1 more)

Pietro Lio

We introduce Hybrid Space-aware Stochastic Convolution Attention Noise (HySCAN), a hybrid randomized defense that helps close the long-stand… (see more)ing gap between provable robustness under ℓ2 certificates and empirical robustness against strong ℓ∞ attacks, while maintaining strong generalization across diverse imaging benchmarks. HySCAN jointly explores complementary sources of stochasticity at both training and inference: (i) implicit weight-space randomness via stochastic-aware Random Weights, and (ii) explicit feature-space randomness via Stochastic Attention Noise Injection modules. By incorporating randomness at both the parameter and representation levels, HySCAN enables meaningful certified guarantees while improving empirical robustness in practice. Comprehensive experiments on diverse imaging datasets, e.g., CelebA, CIFAR-10, and CIFAR-100, ImageNet-1k, HAM10000, and NIH Chest X-ray, demonstrate that HySCAN outperforms existing certified and empirical defenses, improving certified robustness by up to ≈ 9.6% and empirical robustness by up to ≈ 5% without reducing clean accuracy.

2026-04-29

International Conference on Machine Learning (accepted)