Zobrazeno 1 - 10
of 139
pro vyhledávání: '"SOULIER, LAURE"'
Autor:
Aissi, Mohamed Salim, Romac, Clement, Carta, Thomas, Lamprier, Sylvain, Oudeyer, Pierre-Yves, Sigaud, Olivier, Soulier, Laure, Thome, Nicolas
Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of fine-tuning them
Externí odkaz:
http://arxiv.org/abs/2410.19920
Co-speech gestures are fundamental for communication. The advent of recent deep learning techniques has facilitated the creation of lifelike, synchronous co-speech gestures for Embodied Conversational Agents. "In-the-wild" datasets, aggregating video
Externí odkaz:
http://arxiv.org/abs/2409.10357
Autor:
Djeddal, Hanane, Erbacher, Pierre, Toukal, Raouf, Soulier, Laure, Pinel-Sauvagnat, Karen, Katrenko, Sophia, Tamine, Lynda
With the growing success of Large Language models (LLMs) in information-seeking scenarios, search engines are now adopting generative approaches to provide answers along with in-line citations as attribution. While existing work focuses mainly on att
Externí odkaz:
http://arxiv.org/abs/2409.08014
Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders
With the recent addition of Retrieval-Augmented Generation (RAG), the scope and importance of Information Retrieval (IR) has expanded. As a result, the importance of a deeper understanding of IR models also increases. However, interpretability in IR
Externí odkaz:
http://arxiv.org/abs/2406.19309
Co-speech gestures play a crucial role in the interactions between humans and embodied conversational agents (ECA). Recent deep learning methods enable the generation of realistic, natural co-speech gestures synchronized with speech, but such approac
Externí odkaz:
http://arxiv.org/abs/2406.15111
Autor:
Baldassini, Folco Bertini, Shukor, Mustafa, Cord, Matthieu, Soulier, Laure, Piwowarski, Benjamin
Large Language Models have demonstrated remarkable performance across various tasks, exhibiting the capacity to swiftly acquire new skills, such as through In-Context Learning (ICL) with minimal demonstration examples. In this work, we present a comp
Externí odkaz:
http://arxiv.org/abs/2404.15736
Conversational systems have made significant progress in generating natural language responses. However, their potential as conversational search systems is currently limited due to their passive role in the information-seeking process. One major lim
Externí odkaz:
http://arxiv.org/abs/2402.16608
Autor:
Bronnec, Florian Le, Duong, Song, Ravaut, Mathieu, Allauzen, Alexandre, Chen, Nancy F., Guigue, Vincent, Lumbreras, Alberto, Soulier, Laure, Gallinari, Patrick
State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text generation with
Externí odkaz:
http://arxiv.org/abs/2401.17919
Publikováno v:
Advances in Information Retrieval. ECIR 2024. Lecture Notes in Computer Science, vol 14610
In Information Retrieval, and more generally in Natural Language Processing, adapting models to specific domains is conducted through fine-tuning. Despite the successes achieved by this method and its versatility, the need for human-curated and label
Externí odkaz:
http://arxiv.org/abs/2401.11509
While Large Language Models (LLM) are able to accumulate and restore knowledge, they are still prone to hallucination. Especially when faced with factual questions, LLM cannot only rely on knowledge stored in parameters to guarantee truthful and corr
Externí odkaz:
http://arxiv.org/abs/2401.01780