Zobrazeno 1 - 10
of 1 089
pro vyhledávání: '"Charton, P."'
Autor:
Butter, Anja, Charton, François, Villadamigo, Javier Mariño, Ore, Ayodele, Plehn, Tilman, Spinner, Jonas
Generative networks are an exciting tool for fast LHC event generation. Usually, they are used to generate configurations with a fixed number of particles. Autoregressive transformers allow us to generate events with variable numbers of particles, ve
Externí odkaz:
http://arxiv.org/abs/2412.12074
We introduce PatternBoost, a flexible method for finding interesting constructions in mathematics. Our algorithm alternates between two phases. In the first ``local'' phase, a classical search algorithm is used to produce many desirable constructions
Externí odkaz:
http://arxiv.org/abs/2411.00566
Despite their spectacular progress, language models still struggle on complex reasoning tasks, such as advanced mathematics. We consider a long-standing open problem in mathematics: discovering a Lyapunov function that ensures the global stability of
Externí odkaz:
http://arxiv.org/abs/2410.08304
Autor:
Charton, François, Kempe, Julia
We study the performance of transformers as a function of the number of repetitions of training examples with algorithmically generated datasets. On three problems of mathematics: the greatest common divisor, modular multiplication, and matrix eigenv
Externí odkaz:
http://arxiv.org/abs/2410.07041
Understanding and accurately following instructions is critical for large language models (LLMs) to be effective across diverse tasks. In this work, we rigorously examine the key factors that enable models to generalize to unseen instructions, provid
Externí odkaz:
http://arxiv.org/abs/2410.04717
Autor:
Leigh, Matthew, Klein, Samuel, Charton, François, Golling, Tobias, Heinrich, Lukas, Kagan, Michael, Ochoa, Inês, Osadchy, Margarita
In this work, we significantly enhance masked particle modeling (MPM), a self-supervised learning scheme for constructing highly expressive representations of unordered sets relevant to developing foundation models for high-energy physics. In MPM, a
Externí odkaz:
http://arxiv.org/abs/2409.12589
Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of the pre-training corpus, or because synthetized data is used as a replacement for expensive human-annotation.
Externí odkaz:
http://arxiv.org/abs/2406.07515
Autor:
Cabannes, Vivien, Arnal, Charles, Bouaziz, Wassim, Yang, Alice, Charton, Francois, Kempe, Julia
Chain-of-Thought (CoT) reasoning is known to improve Large Language Models both empirically and in terms of theoretical approximation power. However, our understanding of the inner workings and conditions of apparition of CoT capabilities remains lim
Externí odkaz:
http://arxiv.org/abs/2406.02128
Autor:
Gach, Jean-Luc, Bruno, Piero, Charton, Julien, Feautrier, Philippe, Fusco, Thierry, Neichel, Benoit, Sauvage, Jean-François
The Cassiop\'ee project aims to develop the key technologies that will be used to deploy very high-performance Adaptive Optics for future ELTs. The ultimate challenge is to detect earth-like planets and characterize the composition of their atmospher
Externí odkaz:
http://arxiv.org/abs/2406.00547
Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow instructions n
Externí odkaz:
http://arxiv.org/abs/2405.19787