activity
20182023
most citedGraphiT: Encoding Graph Structure in Transformers

42 citations · 52 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CL20231 cited

WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models

Youssef Benchekroun, Megi Dervishi, Mark Ibrahim +7

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…

cs.CL20239 cited

GAIA: a benchmark for General AI Assistants

Grégoire Mialon, Clémentine Fourrier, Craig Swift +3

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 funda…

cs.LG202142 cited

GraphiT: Encoding Graph Structure in Transformers

Grégoire Mialon, Dexiong Chen, Margot Selosse +1

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 l…

cs.LG2020

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

Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont +1

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 depend…

cs.LG2019

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

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. We derive loss functions that produce…

stat.ML2018

A Kernel Perspective for Regularizing Deep Neural Networks

Alberto Bietti, Grégoire Mialon, Dexiong Chen +1

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 ad…