Search Results for author:
Found 10 papers, 9 papers with code
WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models
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.
GAIA: a benchmark for General AI Assistants
GAIA's philosophy departs from the current trend in AI benchmarks suggesting to target tasks that are ever more difficult for humans.
Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
Machine learning for differential equations paves the way for computationally efficient alternatives to numerical solvers, with potentially broad impacts in science and engineering.
On Inductive Biases for Machine Learning in Data Constrained Settings
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.
Augmented Language Models: a Survey
This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools.
Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations
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.
GraphiT: Encoding Graph Structure in Transformers
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).
A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
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.
Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions
We design simple screening tests to automatically discard data samples in empirical risk minimization without losing optimization guarantees.
A Kernel Perspective for Regularizing Deep Neural Networks
We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS).
