BEGIN:VCALENDAR BEGIN:VEVENT SUMMARY:Towards AI Models That Can Visually Understand the World's Culture s DTSTART:20241122T213000Z DTEND:20241122T230000Z UID:https://cdh.princeton.edu/events/2024/11/towards-ai-models-that-can-vi sually-understand-the-worlds-cultures/ DESCRIPTION:\n\n\n\n\n \n \n \n Watch recording:\n \n\n \n\n \n \n \n\n\n\n \n\n\n\n\n \n \n A photo albu m from the lecture is on our Flickr.\n \n\n \n\n \n \n \n View photos\n\n\n \n\n\n \n\n\n\n\n Neubig will discuss a new f rontier in AI models\, vision-language models that understand the world&#x 27\;s cultures. First\, he will talk through the training of multilingual\ , multimodal\, multicultural models that understand images and text and ha ve an increased ability to answer culture-specific questions about multimo dal data. Then he will discuss work on "\;image transcreation"\;\, where models have been developed that can transform images to make them m ore relevant to a particular culture. This work has applications in severa l areas\, such as cultural localization of educational materials (to accom pany translated text). The talk will focus on examples from the African co ntext and the challenges we currently face.Graham Neubig is an associate p rofessor at the Language Technologies Institute of Carnegie Mellon Univers ity. His research focuses on natural language processing\, with a particul ar interest in fundamentals\, applications\, and understanding of large la nguage models for tasks such as question answering\, code generation\, and multilingual applications. His final goal is that every person in the wor ld should be able to communicate with each other\, and with computers in t heir own language. He also contributes to making NLP research more accessi ble through open publishing of research papers\, advanced NLP course mater ials and video lectures\, and open-source software\, all of which are avai lable on his website.\n\n\n\n\n \n\n \n \n \n \ n \n Related events\n \n\n \n\n \n \n \n\n \n\n \n \n \n\n \n \n \n \n \n African Languag es in the Age of AI (AAA) Speaker Series\n \n \n \n\n \n \n\n \n Bringing leading scholars to Princeton to discuss the op portunities and challenges for developing technologies that empower Africa n languages\n\n \n \n\n \n \n\n \n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\n \n \n\n \n \n \n \n \n A New Agenda for African Languages x AI: Everything\, Everywhere\, All At Once\n \n \n \n\n \n \n\n \n\ n \n \n \n \n \n \n \n \n \n Sep 19 2024 4:30PM–6:00PM\n \n \n \n \n \n \n \n\n \n \n Vukosi Marivate\n \n \n\n \n\n \n \n\n \n \n \ n African Languages in the Age of AI\n \ n \n \n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\ n \n \n\n \n \n \n \ n \n End-to-End African Language Technology\n \n \n \n\n \n \n\n \n\n \n \n \n \n \n \n \n \n \n Oct 24 20 24 4:30PM–6:00PM\n \n \n \n \n \n \n \n\n \n \n Ernest Mwebaze\n \n \n\n \n\n \n \n \n \n \n \n African La nguages in the Age of AI\n \n \n \n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\n \n \n \n\n\n\n\n\n \n\n \n \n \n \n \n Related research gro up\n \n\n \n\n \n \n \n\n \n\n \n \n \n\n \n \n \n \n \n African Language Technologies Lab\n \n \n \n\n \n \n\n \n Focused on increasing the r epresentation of African languages in NLP\, LLMs\, and AI. Directors: Chri stiane Fellbaum\, Happy Buzaaba\n\n \n \n\n \n \n\n \n\n \n \n \n \n \n \n\n \ n \n \n \n \n \n \n \n \n \n \n\n \n \n \n\n\n\nhttps://cdh.princeton.edu/events/2024 /11/towards-ai-models-that-can-visually-understand-the-worlds-cultures/ LOCATION:Friend Center 006\, A Level END:VEVENT END:VCALENDAR