Search Results for author:
Found 12 papers, 6 papers with code
Dialogue avec Molière (Dialogue with Molière )
A l’occasion du quatre-centième anniversaire de la naissance de Molière (1622-1673), nous présentons un agent conversationnel qui parle comme un personnage du théâtre de Molière.
Large Language Models for Compiler Optimization
We explore the novel application of Large Language Models to code optimization.
Code Translation with Compiler Representations
Here we propose to augment code translation with IRs, specifically LLVM IR, with results on the C++, Java, Rust, and Go languages.
Leveraging Automated Unit Tests for Unsupervised Code Translation
With little to no parallel data available for programming languages, unsupervised methods are well-suited to source code translation.
DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks.
Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking
We demonstrate the advantages of such a broad collection by deriving from it Automated Black Box Optimizer (ABBO), a general-purpose algorithm selection wizard.
EvolGAN: Evolutionary Generative Adversarial Networks
We propose to use a quality estimator and evolutionary methods to search the latent space of generative adversarial networks trained on small, difficult datasets, or both.
Tarsier: Evolving Noise Injection in Super-Resolution GANs
More generally, our approach can be used to optimize any method based on noise injection.
Unsupervised Translation of Programming Languages
We train our model on source code from open source GitHub projects, and show that it can translate functions between C++, Java, and Python with high accuracy.
Versatile Black-Box Optimization
Choosing automatically the right algorithm using problem descriptors is a classical component of combinatorial optimization.
Adversarial Attacks on Linear Contextual Bandits
In many of these domains, malicious agents may have incentives to attack the bandit algorithm to induce it to perform a desired behavior.
Polygames: Improved Zero Learning
Since DeepMind's AlphaZero, Zero learning quickly became the state-of-the-art method for many board games.
