报告题目：具备高效长期记忆和高事实性的大语言模型（LLMs with efficient long-term memory and better factuality）
报告时间：6月22日10：00—11：30
报告地点：浙江大学紫金港蒙民伟楼402会议室
主持人：武伯熹 博士
 
内容摘要：Seamlessly communicate with machines has always been the ultimate goal of artificial intelligence. This talk address the two key milestones towards general intelligence: how to effectively track infinite long history and how to improve factuality of the generation content. Specifically we will talk about a stateful transformer architecture that can achieve effective memory read and write. We will also address how to use reinforcement learning with human feedback to improve generation content's faithfulness.
个人简介：Zhou (Jo) Yu is an Associate Professor at Columbia University Computer Science Department. Zhou is the CEO of Aritculate AI Inc, a startup that supercharges the workforce with Generative and conversational AI. Her research interest includes dialog systems, language understanding and generation, vision and language, human-computer interaction, and social robots. Dr. Yu has built various dialog systems with major practical impacts, their chatbots have reached ten million Amazon Alexa users. Dr. Yu's work earned a 2019 ACL best paper award nomination. She was recognized in the Forbes 2018 30 under 30 in Science and won the 2018 Amazon Alexa Prize.