Gauthier Gidel

sadhana.anand@mila.quebec

Biographie

Je suis professeur adjoint au Département d’informatique et de recherche opérationnelle (DIRO) de l'Université de Montréal et membre académique principal de Mila – Institut québécois d’intelligence artificielle. J'ai obtenu une bourse Borealis AI destinée aux étudiant·e·s des cycles supérieurs et je suis actuellement titulaire d'une chaire en IA Canada-CIFAR. J'ai travaillé chez DeepMind et Element AI, et j'ai récemment été un visiteur de longue durée au Simons Institute de l’Université de Californie à Berkeley. Mes intérêts de recherche se situent à l'intersection de la théorie des jeux, de l'optimisation et de l'apprentissage automatique.

Étudiants actuels

Sadhana Anand

Maîtrise recherche - UdeM

yuan-chen.chang@mila.quebec

Yuan-Chen Chang

Doctorat - UdeM

david-a.dobre@mila.quebec

David Dobre

Doctorat - UdeM

damien.ferbach@mila.quebec

Damien Ferbach

Doctorat - UdeM

Co-superviseur⋅e :

Courtney Paquette

niklas.herbster@gmail.com

Niklas Herbster

Stagiaire de recherche - UdeM

Superviseur⋅e principal⋅e :

Irina Rish

marco.jiralerspong@mila.quebec

Marco Jiralerspong

Doctorat - UdeM

andjela.mladenovic@mila.quebec

Zichu Liu

Doctorat - UdeM

Co-superviseur⋅e :

Ioannis Mitliagkas

zichu.liu@mila.quebec

Andjela Mladenovic

Doctorat - UdeM

Co-superviseur⋅e :

Aaron Courville

mehrnaz.mofakhami@mila.quebec

Mehrnaz Mofakhami

Collaborateur·rice de recherche - UdeM

Co-superviseur⋅e :

Ioannis Mitliagkas

Nneka Okolo

Visiteur de recherche indépendant - N/A

nneka.okolo@mila.quebec

Ailin Rasteh

Doctorat - UdeM

ailin.rasteh@mila.quebec

Leo Schwinn

Visiteur de recherche indépendant - Technical Univeristy of Munich

leo.schwinn@mila.quebec

Tom Stanic

Maîtrise recherche - UdeM

tom.stanic@mila.quebec

tommaso.tosato@mila.quebec

Tommaso Tosato

Postdoctorat - UdeM

Doctorat - UdeM

danilo.vucetic@mila.quebec

Sophie Xhonneux

Doctorat - UdeM

Co-superviseur⋅e :

Jian Tang

lpxhonneux@gmail.com

Que nous apprennent les distributions des coefficients synaptiques au sujet de l’apprentissage dans le cerveau ?

Billets de blogue

13 juin 2024

par

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Lire l'article

Publications

On the Stability and Convergence of Flow Map Training

Ishan Nath

Tom Stanic

Avishek Joey Bose

Quentin Bertrand

Flow maps are a recent method of probabilistic generation that amortize diffusion trajectories into one-step samplers, unlocking efficient g… (voir plus)eneration. While progress has been made in improving their empirical performance, there is still a lack of understanding behind the mechanisms underlying their success. Specifically, many flow map learning methods employ stop gradient operators as a crucial part of their training target. Adaptive weighting also drastically improves the generation capabilities of flow maps. Although many interpretations have been proposed to support the inclusion of these heuristics, none have analyzed the impact of these assumptions on the training dynamics of flow maps themselves. In this work, we address this issue by providing grounded theory explaining why such tricks are required. Analyzing the functional gradient flow induced by the MeanFlow and Lagrangian losses, we show their convergence to the true flow map, settling the validity of these objectives. For finite updates, we highlight a severe roadblock to the usage of these losses in practice: the possible unboundedness of the update. Adaptive normalization not only provides bounded updates, but, combined with a specific weighting, additionally provides convergence guarantees towards a neighborhood of the solution. On synthetic data, we show that our functional gradient flow analysis exactly describes the true training dynamics for flow maps. Experiments on standard image datasets demonstrate that a proper reweighting scheme is essential for strong empirical performance, which is only achieved for a specific range of reweighting strengths.

2026-10-13

arXiv (prépublication)

Visual Memory Attacks Can Persist Through The KV Cache

Pierre-Andre Noel

Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial … (voir plus)input continue to steer a model even after that input is removed from its context? We show that attacks can be trained to persist through the key/value (KV) cache of subsequent tokens, allowing adversarial influence to outlive direct access to its source.We consider the Visual Memory Injection (VMI; Schlarmann and Hein, 2026) attack setting, in which an adversarial image that stays in the context plants a hidden backdoor: the model behaves normally until a chosen trigger elicits an attacker-chosen response. We first demonstrate persistence in this setting with optimized soft prompts, which remain effective after we mask the prompt from attention. We then introduce Persistent Visual Memory Injection (P-VMI), which optimizes images to preserve this adversarial behaviour after they are masked from attention. These attacks persist over conversations substantially longer than those used during optimization. On Qwen3-VL-8B-Instruct, P-VMI achieves up to approximately

2026-10-05

arXiv (prépublication)

Fixed-Point Rates for Self-Distillation of Flow Maps

Stanic Tom

Quentin Bertrand

Avishek Joey Bose

Flow and diffusion models generate high-quality samples, but inference typically requires many sequential neural-network evaluations. Flow-m… (voir plus)ap models address this bottleneck by learning finite-time transitions directly, enabling generation in one or a few evaluations. Previous work introduced Lagrangian, Eulerian, and progressive self-distillation rules with training targets derived from the model's own predictions. Does reconstructing a candidate flow map from its own predictions correct errors or reinforce them? With the learned velocity field held fixed, we view each rule as an operator on candidate flow maps and study its iterates. By composing two half-length transitions, progressive reconstruction converges globally and geometrically in a weighted norm. This requires spatial Lipschitz bounds and initial errors relative to the teacher flow that vanish uniformly at least quadratically as transitions become shorter. Every reconstruction reduces the worst-case weighted error by at least half, although it can amplify error in the ordinary supremum norm. Lagrangian reconstruction has a factorial convergence guarantee, whereas Eulerian reconstruction admits no general same-order Lipschitz stability bound. Under the stated assumptions, Lagrangian and progressive reconstruction yield two-sided bounds on the error to the frozen teacher flow in terms of the full weighted residual norm. For progressive reconstruction, analogous mean-square bounds hold over teacher-generated states, with a supremum over time pairs. A two-dimensional experiment illustrates how reconstruction reduces errors over short intervals and how its changes indicate the remaining error. Lagrangian reconstruction gives faster initial improvement in this example.

2026-10-03

STODY @ Conference on Neural Information Processing Systems (poster)

On the Stability and Convergence of Flow Map Training

Ishan Nath

Mathurin Massias

Avishek Joey Bose

Quentin Bertrand

Flow maps are a recent method of probabilistic generation that amortize diffusion trajectories into one-step samplers, unlocking efficient g… (voir plus)eneration. While progress has been made into improving their empirical performance, the understanding of the mechanisms underlying their success remains largely unknown. Specifically, flow maps employ stop gradient operators as a crucial part of their training target, which seem necessary to obtain convergent methods. Adaptive weighting also drastically improves the generation capabilities of flow maps. Although many interpretations have been proposed to support the inclusion of these heuristics, none have analyzed the impact of these assumptions on the training dynamics of flow maps themselves. In this work, we address this issue by providing grounded theory explaining why such tricks are required. Analyzing the functional gradient flow induced by the MeanFlow and Lagrangian objective, we show their convergence to the true flow map, settling the validity of these objectives. For finite updates, we highlight a severe roadblock to the usage of these losses in practice; the possible unboundedness of the update. Adaptive normalization not only provides bounded updates, but combined with a specific weighting, additionally provides convergence guarantees towards a neighborhood of the solution. On synthetic data, we show that our functional gradient flow analysis exactly describes the true training dynamics for flow maps. Experiments on standard image datasets demonstrate that a proper reweighting scheme is essential for strong empirical performance, which is only achieved for a specific range of reweighting strengths.

2026-10-03

STODY @ Conference on Neural Information Processing Systems (poster)

Surrogate Loss Gradient Descent in Variational Inequalities with Linear Approximation

The use of surrogate losses to approximate principled updates in prediction space has been instrumental in the success of scaling function a… (voir plus)pproximation in reinforcement learning. These methods are motivated by approximating an update in prediction space with an optimization inner-loop that takes a fixed number of gradient steps on a surrogate loss. Despite its prevalence, there is a disconnect between existing theory and algorithms used in practice with respect to the number of gradient steps. In this paper, we focus on the linear approximation case to derive sharp guarantees when parameters are updated by a fixed number of gradient steps on a surrogate loss. It provides a unified approach that naturally connects the mean-path analysis of TD and LSPE, which correspond to both extremes from one step to an infinite number of inner-steps, and have been previously analysed with different techniques. Our analysis, however, gives a precise insight into the compute-optimal number of gradient steps

2026-09-30

OPT @ Neural Information Processing Systems (poster)

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence

Niklas Herbster

Martin Zborowski

Alberto Tosato

Tommaso Tosato

Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent mi… (voir plus)salignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors are encoded as linear structure in activation space, making it tractable via activation steering, which could be used as a lightweight runtime defense. We implement three methods: Steer-With-Fixed-Coefficient (SwFC), which applies uniform additive steering, and two novel projection-aware methods, Steer-to-Target-Projection (StTP) and Steer-to-Mirror-Projection (StMP), that use a logistic regression decision boundary to selectively intervene only on tokens whose activations fall below the threshold. We evaluate these methods on two threat models, dishonesty and dismissiveness, using malicious system prompts as a controlled proxy for misalignment. We conduct our experiments on two architectures (Llama-3.3-70B-Instruct and Qwen3.6-27B). All methods substantially recover alignment. StTP and StMP preserve general capabilities (MMLU, MT-Bench, AlpacaEval) better than uniform steering. Finally, we show that our honesty steering generalizes to out-of-distribution scenarios: a single honesty direction extracted from the aligned model significantly raises scores on the MASK benchmark, suppresses deception in multi-agent settings (Among Us), doubles the hidden-behavior discovery rate on AuditBench, and restores honesty in an emergently misaligned model

2026-07-07

Conference on Language Modeling (accepté)

Accelerated and Stable Convergence with Anchored Optimistic Method

Jianxin You

We study first-order methods for solving monotone variational inequalities arising in min-max optimization. Classical approaches such as the… (voir plus) extragradient method rely on two gradient queries per iteration, which limits their analysis and applicability in the online and stochastic settings. We propose a family of Generalized Optimistic Methods with Anchoring (GOMA), which combine two-time-scale optimistic updates with an anchoring term inspired by Halpern iteration. In the deterministic setting, GOMA achieves the optimal accelerated last-iterate rate

2026-06-18

arXiv (prépublication)

Why Open Source? A Game-Theoretic Analysis of the AI Race

Andjela Mladenovic

Aaron Courville

In recent years, with the advancement of frontier AI, we have observed certain dynamics in open-sourcing and closed-sourcing decisions. We p… (voir plus)ropose a game-theoretic model to analyze these dynamics in the current landscape of the AI race. Our model builds on an R&D race framework under a winner-takes-all setting, and it accounts for the cases where the players' actions can be either discrete or continuous (i.e., partial open-sourcing, such as open weights). We show that determining the existence of a discrete pure non-trivial Nash equilibrium is NP-hard in general but that we can transform the discrete Nash existence computation into a MIP (Mixed-Integer Programming) problem, making it tractable for small instances using a standard MIP solver. Next, we show the existence and tractability of pure Nash equilibria in the continuous version of our problem, leveraging standard convex analysis results, and constructing an equivalent MIP formulation. Throughout this work, we leverage both our main technical results as well as surrounding technical analysis, to derive socially relevant insights that we believe can serve both to understand already existing decisions and dynamics and to potentially inform new policies.

2026-04-16

arXiv (prépublication)

Soft Mellowmax Monte Carlo Planning

Danilo Vucetic

Soft mellowmax (SMM) recently emerged as an alternative operator in Q-learning, achieving impressive performance in games and scientific dis… (voir plus)covery tasks. Despite SMM's ability to achieve high returns and its enticing robustness, diversity, and sample efficiency characteristics, SMM has not yet been translated into a Monte Carlo tree search algorithm. To address this gap, a soft mellowmax-based Monte Carlo tree search algorithm, SMM-TS, is proposed and theoretically justified. It is empirically demonstrated that SMM-TS converges significantly faster than other tree search methods in synthetic environments, while maintaining competitive performance in games. The fast convergence of SMM-TS makes recursive self-improvement loops more scalable, while the stability gained via planning and the robustness of the operator make SMM-TS more practical for agents operating in uncertain and changing environments.

2026-03-04

RSI @ International Conference on Learning Representations (poster)

Beyond Reward Maximization: Evaluating the Diversity of Trajectories in Reinforcement Learning with Temporal Vendi Score

In domains such as scientific discovery and automated design using reinforcement learning (RL), the final task of an agent should extend bey… (voir plus)ond maximising a single scalar reward; it requires identifying diverse sets of high-quality trajectories to uncover distinct solutions that can provide novel insights on how to solve the problems of interest and transfer robustly from simulation to the real world. However, the RL literature currently lacks a holistic, domain-agnostic standard for measuring trajectory diversity. Existing metrics have been developed to improve exploration at training time but not to evaluate and compare diversity induced by different agents, rendering cross-method comparisons inconsistent and challenging. To address this, we introduce the Temporal Vendi Score (TVS), a novel metric designed to evaluate the diversity of an RL agent by computing the entropy of the eigenvalues' similarity matrix of sampled trajectories. Unlike previous approaches, our metric captures the behavioural diversity of trajectories by accounting for both the sequential nature of state visitations and the temporal structure of the underlying MDP, rather than relying on order-agnostic state comparisons. We validate the TVS on simple environments where we can control the number of different ways a problem can be solved, demonstrating that it provides a more robust, semantically meaningful ranking of diversity than standard baselines. We then show that our metric can scale to a high-dimensional, continuous environment.

2026-03-01

LLA @ International Conference on Learning Representations (poster)

Logarithmic-time Schedules for Scaling Language Models with Momentum

In practice, the hyperparameters …

2026-02-04

arXiv (prépublication)

Accelerated and Stable Convergence with Anchored Generalized Optimistic Method

Jianxin You

We study first-order methods for solving monotone variational inequalities arising in min-max optimization. Classical approaches such as the… (voir plus) extragradient method rely on two gradient queries per iteration, which limits their analysis and applicability in the online and stochastic settings. We propose a family of Generalized Optimistic Methods with Anchoring (GOMA), which combine two time-scale optimistic updates with an anchoring term inspired by Halpern iteration. In particular, we show that for monotone Lipschitz operators, GOMA achieves an accelerated last-iterate convergence rate of

2025-12-31

International Conference on Machine Learning (Accept (regular))