Grégoire Mialon — accepted AI-conference papers

2026

Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

Romain Froger, Amine Benhalloum, Andrey Rusakov, Dheeraj Mekala, Emilien Garreau, Gerard Moreno-Torres Bertran +18

ICLR 2026oral

We introduce **Gaia2**, a benchmark for evaluating large language model agents in realistic, asynchronous environments. Unlike prior static or synchronous evaluations, Gaia2 introduces scenarios where environments evolve independently of agent actions, requiring agents to operate under temporal cons…

Cited by 0 Source ↗Scholar ↗

2024

GAIA: a benchmark for General AI Assistants

Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, Thomas Scialom

ICLR 2024poster

We introduce GAIA, a benchmark for General AI Assistants that, if solved, would represent a milestone in AI research. GAIA proposes real-world questions that require a set of fundamental abilities such as reasoning, multi-modality handling, web browsing, and generally tool-use proficiency. GAIA ques…

Cited by 125 Source ↗PDF ↗Scholar ↗

2023

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

Grégoire Mialon, Quentin Garrido, Hannah Lawrence, Danyal Rehman, Yann LeCun, Bobak Kiani

NeurIPS 2023poster

Machine learning for differential equations paves the way for computationally efficient alternatives to numerical solvers, with potentially broad impacts in science and engineering. Though current algorithms typically require simulated training data tailored to a given setting, one may instead wish…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗

2021

A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention

Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, Julien Mairal

ICLR 2021poster

We address the problem of learning on sets of features, motivated by the need of performing pooling operations in long biological sequences of varying sizes, with long-range dependencies, and possibly few labeled data. To address this challenging task, we introduce a parametrized representation of f…

Cited by 65 Source ↗PDF ↗code ↗Scholar ↗

2020

Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions

Grégoire Mialon, Julien Mairal, Alexandre d’Aspremont

AISTATS 2020poster

We design simple screening tests to automatically discard data samples in empirical risk minimization withoutlosing optimization guarantees. We derive loss functions that produce dual objectives with a sparse solution. We also show how to regularize convex losses to ensure such a dual sparsity-induc…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2019

A Kernel Perspective for Regularizing Deep Neural Networks

Alberto Bietti, Grégoire Mialon, Dexiong Chen, Julien Mairal

ICML 2019oral

We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS). Even though this norm cannot be computed, it admits upper and lower approximations leading to various practical strategies. Specifically, this perspective (i) provides…

Cited by 84 Source ↗PDF ↗code ↗Scholar ↗