talk-data.com

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.