Search – talk-data.com

Title & Speakers	Event
Paris NLP saison 8 Meetup #2 2025-01-08 · 18:00 📍8-10 rue du Renard 75004 Paris 📆 January 8th, 7:00 p.m. ⚠️ Limited spots available. Be sure to reserve your place in advance! 👥 Alexandre Brasseur - ML Engineer ➡️ Lost in the feed: how ask from billions of social media posts Everyone knows what "RAG" means, but is it that simple ? Let's embark in our journey on building a Conversational Search Engine from scratch designed to deliver quick insights from billions of social media posts and news articles ingested daily. In this talk we will share the initiatives and failures we went through in order to build a production-grade RAG system. 👥 Léo Hunout & Kamel Guerda - AI Research Engineers @IDRIS ➡️ Jean Zay: Unlocking the Power of Supercomputing for Research Summary: In this talk, we’ll introduce Jean Zay, the French supercomputer hosted at IDRIS, and explain how it can empower the NLP community. We will cover how researchers and developers working on open-source projects can access and leverage this powerful resource, as well as key strategies for optimizing the training and fine-tuning of large language models (LLMs) on supercomputers. Whether you’re new to supercomputing or exploring its possibilities for NLP, this session aims to demystify the process and equip you with the foundational knowledge and tools to get started.	Paris NLP saison 8 Meetup #2
Paris NLP saison 8 Meetup #2 2024-01-10 · 18:00 This event is in-person only and will be followed by a networking apéro. We are looking forward to seeing you all in person! EDIT : We are unfortunately closing inscription due to high demand, thank you for your understanding Due to the Meetup's success, we'd like to inform you that the available places for the event are limited to the first 100 people to show up in order to ensure the safety and comfort of all attendees (we are closing registration at 250 people to anticipate no-shows) . Thank you for your understanding ! * Thomas Scialom - Research Scientist (LLMs) - Meta AI Title: LLMs: past present and future Summary : Thomas will present the brief history of LLMs from GPTs to the lattest fronteer models, before diving into the science beyind RLHF, the technology powering ChatGPT and Llama-2. Finally, we will present his perspective on what could be the future of the field. * Francois Role - Université Paris Cité Title: Aligning Text and Image Representations Using Vision-Language Pretrained Models Summary : Data related to the same topic often comes in many modalities (audio, image, text, etc.) The ability to bridge the gap between these modalities is what makes possible applications such as multimodal information-retrieval, multimodal classification, automatic image captioning, etc. In this talk, we will present Vision-Language Pretrained Models (VLP models) that have been designed to jointly encode vision and langage, with a focus on bidirectional contrastive learning. We will first explain the loss function used in this context, starting from an intuitive example before presenting its formal definition. It will then be shown that training methods based on this kind of loss, while very useful, do not necessarily lead to an optimal alignment of the different modalities. We will therefore present a method for improving the quality of the text and image representations produced by the VLP models.	Paris NLP saison 8 Meetup #2

📍8-10 rue du Renard 75004 Paris 📆 January 8th, 7:00 p.m. ⚠️ Limited spots available. Be sure to reserve your place in advance!

👥 Alexandre Brasseur - ML Engineer ➡️ Lost in the feed: how ask from billions of social media posts Everyone knows what "RAG" means, but is it that simple ? Let's embark in our journey on building a Conversational Search Engine from scratch designed to deliver quick insights from billions of social media posts and news articles ingested daily. In this talk we will share the initiatives and failures we went through in order to build a production-grade RAG system.

👥 Léo Hunout & Kamel Guerda - AI Research Engineers @IDRIS ➡️ Jean Zay: Unlocking the Power of Supercomputing for Research Summary: In this talk, we’ll introduce Jean Zay, the French supercomputer hosted at IDRIS, and explain how it can empower the NLP community. We will cover how researchers and developers working on open-source projects can access and leverage this powerful resource, as well as key strategies for optimizing the training and fine-tuning of large language models (LLMs) on supercomputers. Whether you’re new to supercomputing or exploring its possibilities for NLP, this session aims to demystify the process and equip you with the foundational knowledge and tools to get started.

This event is in-person only and will be followed by a networking apéro. We are looking forward to seeing you all in person!

EDIT : We are unfortunately closing inscription due to high demand, thank you for your understanding

Due to the Meetup's success, we'd like to inform you that the available places for the event are limited to the first 100 people to show up in order to ensure the safety and comfort of all attendees (we are closing registration at 250 people to anticipate no-shows) . Thank you for your understanding !

*** Thomas Scialom - Research Scientist (LLMs) - Meta AI Title: LLMs: past present and future Summary : Thomas will present the brief history of LLMs from GPTs to the lattest fronteer models, before diving into the science beyind RLHF, the technology powering ChatGPT and Llama-2. Finally, we will present his perspective on what could be the future of the field.

*** Francois Role - Université Paris Cité Title: Aligning Text and Image Representations Using Vision-Language Pretrained Models Summary : Data related to the same topic often comes in many modalities (audio, image, text, etc.) The ability to bridge the gap between these modalities is what makes possible applications such as multimodal information-retrieval, multimodal classification, automatic image captioning, etc. In this talk, we will present Vision-Language Pretrained Models (VLP models) that have been designed to jointly encode vision and langage, with a focus on bidirectional contrastive learning. We will first explain the loss function used in this context, starting from an intuitive example before presenting its formal definition. It will then be shown that training methods based on this kind of loss, while very useful, do not necessarily lead to an optimal alignment of the different modalities. We will therefore present a method for improving the quality of the text and image representations produced by the VLP models.

Activities & events