Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Reinauer, Raphael"'
Reinforcement Learning from Human Feedback (RLHF) and derivative techniques like Direct Preference Optimization (DPO) are task-alignment algorithms used to repurpose general, foundational models for specific tasks. We show that applying task-alignmen
Externí odkaz:
http://arxiv.org/abs/2409.17673
We prove the Gromov-Lawson-Rosenberg Conjecture for the group Z/4xZ/4 by computing the connective real k-homology of the classifying space with the Adams spectral sequence and two types of detection theorems for the kernel of the alpha invariant: one
Externí odkaz:
http://arxiv.org/abs/2408.07895
The emergent ability of Large Language Models to use a small number of examples to learn to perform in novel domains and tasks, also called in-context learning (ICL). In this work, we show that a much smaller model can be trained to perform ICL by fi
Externí odkaz:
http://arxiv.org/abs/2309.08590
Autor:
Shamsaddini, Vahid, Kirveslahti, Henry, Reinauer, Raphael, de Oliveira, Wallyson Lemes, Caorsi, Matteo, Voutaz, Etienne
The goal of this project is to create and study novel techniques to identify early warning signals for socially disruptive events, like riots, wars, or revolutions using only publicly available data on social media. Such techniques need to be robust
Externí odkaz:
http://arxiv.org/abs/2303.05401
Autor:
Perez, Ilan, Reinauer, Raphael
In recent years, the introduction of the Transformer models sparked a revolution in natural language processing (NLP). BERT was one of the first text encoders using only the attention mechanism without any recurrent parts to achieve state-of-the-art
Externí odkaz:
http://arxiv.org/abs/2206.15195
One of the main challenges of Topological Data Analysis (TDA) is to extract features from persistent diagrams directly usable by machine learning algorithms. Indeed, persistence diagrams are intrinsically (multi-)sets of points in $\mathbb{R}^2$ and
Externí odkaz:
http://arxiv.org/abs/2112.15210