1 code implementation • 27 Nov 2023 • Youssef Benchekroun, Megi Dervishi, Mark Ibrahim, Jean-Baptiste Gaya, Xavier Martinet, Grégoire Mialon, Thomas Scialom, Emmanuel Dupoux, Dieuwke Hupkes, Pascal Vincent
We propose WorldSense, a benchmark designed to assess the extent to which LLMs are consistently able to sustain tacit world models, by testing how they draw simple inferences from descriptions of simple arrangements of entities.
1 code implementation • 21 Nov 2023 • Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf, Yann Lecun, Thomas Scialom
GAIA's philosophy departs from the current trend in AI benchmarks suggesting to target tasks that are ever more difficult for humans.
1 code implementation • NeurIPS 2023 • Grégoire Mialon, Quentin Garrido, Hannah Lawrence, Danyal Rehman, Yann Lecun, Bobak T. Kiani
Machine learning for differential equations paves the way for computationally efficient alternatives to numerical solvers, with potentially broad impacts in science and engineering.
1 code implementation • 21 Feb 2023 • Grégoire Mialon
More precisely, we study the problem of safe sample screening, i. e, executing simple tests to discard uninformative samples from a dataset even before fitting a machine learning model, without affecting the optimal model.
1 code implementation • 15 Feb 2023 • Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, Edouard Grave, Yann Lecun, Thomas Scialom
This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools.
no code implementations • 29 Sep 2022 • Grégoire Mialon, Randall Balestriero, Yann Lecun
Self-Supervised Learning (SSL) methods such as VICReg, Barlow Twins or W-MSE avoid collapse of their joint embedding architectures by constraining or regularizing the covariance matrix of their projector's output.
1 code implementation • 10 Jun 2021 • Grégoire Mialon, Dexiong Chen, Margot Selosse, Julien Mairal
We show that viewing graphs as sets of node features and incorporating structural and positional information into a transformer architecture is able to outperform representations learned with classical graph neural networks (GNNs).
1 code implementation • ICLR 2021 • Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, Julien Mairal
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.
1 code implementation • 5 Dec 2019 • Grégoire Mialon, Alexandre d'Aspremont, Julien Mairal
We design simple screening tests to automatically discard data samples in empirical risk minimization without losing optimization guarantees.
1 code implementation • 30 Sep 2018 • Alberto Bietti, Grégoire Mialon, Dexiong Chen, Julien Mairal
We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS).