У нас вы можете посмотреть бесплатно Aditri Bhagirath - Persona Guided Personalization или скачать в максимальном доступном качестве, видео которое было загружено на ютуб. Для загрузки выберите вариант из формы ниже:
Если кнопки скачивания не
загрузились
НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием видео, пожалуйста напишите в поддержку по адресу внизу
страницы.
Спасибо за использование сервиса ClipSaver.ru
Modern calls for pluralistic alignment argue that AI systems should adapt to individual users, yet most personalization approaches depend on explicit identity labels or predefined preference categories. In this talk, I introduce SynthesizeMe, a method for inferring implicit user personas directly from interaction behavior. By synthesizing and validating reasoning about user preferences, inducing latent personas, and selectively grounding prompts in informative prior interactions, SynthesizeMe enables personalization without demographic data or manual labeling. I’ll show how persona-guided prompting improves LLM-as-a-judge accuracy and how the same persona representations can power real product personalization: from ranking and generation to evaluation and feedback loops. Intended audience: Engineers, researchers. Aditri is a machine learning research engineer at Onton, an AI-powered e-commerce search engine. She earned her MS in Computer Science from Stanford University, where her research on persona creation was published at ACL. Previously, she spent four years at Meta, building community chat experiences across Messenger and Instagram. As an undergraduate, she studied Computer Science and Creative Writing at Carnegie Mellon University and conducted research in Tom Mitchell’s lab, focusing on predicting neural activation using LSTMs. Her other interests include consistent long-form video generation, acting, and writing. This session is brought to you by the Cohere Labs Open Science Community - a space where ML researchers, engineers, linguists, social scientists, and lifelong learners connect and collaborate with each other. We'd like to extend a special thank you to Vaibhavi Singh, Arya Suneesh and Prahitha Movva Leads of our ML Industry group for their dedication in organizing this event. If you’re interested in sharing your work, we welcome you to join us! Simply fill out the form at https://forms.gle/ALND9i6KouEEpCnz6 to express your interest in becoming a speaker. Join the Cohere Labs Open Science Community to see a full list of upcoming events (https://tinyurl.com/CohereLabsCommuni....