We release Code Llama, a family of large language models for code based ...
Group fairness is a popular approach to prevent unfavorable treatment of...
Disaggregated performance metrics across demographic groups are a hallma...
Demonstrations provide insight into relevant state or action space regio...
We consider Contextual Bandits with Concave Rewards (CBCR), a multi-obje...
Fisher markets are those where buyers with budgets compete for scarce it...
As recommender systems become increasingly central for sorting and
prior...
As learning machines increase their influence on decisions concerning hu...
There is growing interest in designing recommender systems that aim at b...
Does everyone equally benefit from computer vision systems? Answers to t...
We consider the problem of generating rankings that are fair towards bot...
In reinforcement learning, pre-trained low-level skills have the potenti...
Citizens' assemblies need to represent subpopulations according to their...
We propose to assess the fairness of personalized recommender systems in...
Machine learning systems typically assume that the distributions of trai...
In this work we explore an auxiliary loss useful for reinforcement learn...
We present a new method that views object detection as a direct set
pred...
We study the problem of learning exploration-exploitation strategies tha...
Most algorithms for representation learning and link prediction in relat...
We provide a simple proof of the convergence of the optimization algorit...
Source separation for music is the task of isolating contributions, or s...
Effective coordination is crucial to solve multi-agent collaborative (MA...
We study the problem of source separation for music using deep learning ...
In complex tasks, such as those with large combinatorial action spaces,
...
Current state-of-the-art speech recognition systems build on recurrent n...
Transcribed datasets typically contain speaker identity for each instanc...
We formulate the problem of defogging as state estimation and future sta...
We consider the problem of high-level strategy selection in the adversar...
Recent progress in deep learning for audio synthesis opens the way to mo...
The problem of Knowledge Base Completion can be framed as a 3rd-order bi...
State-of-the-art speech recognition systems rely on fixed, hand-crafted
...
We present Value Propagation (VProp), a parameter-efficient differentiab...
We train a bank of complex filters that operates on the raw waveform and...
This paper introduces a new encoder-decoder architecture that is trained...
We introduce Parseval networks, a form of deep neural networks in which ...
We propose an extension to neural network language models to adapt their...
We present TorchCraft, a library that enables deep learning research on
...
Hashing produces compact representations for documents, to perform tasks...
We consider scenarios from the real-time strategy game StarCraft as new
...
This paper tackles the problem of endogenous link prediction for Knowled...
Model selection is a crucial issue in machine-learning and a wide variet...