Large Models bridge the Digital-Real World Gap: from Understanding to Generation
Date:
NCAA 2023 tutorial speaker
Tutorial Abstract
In recent years, both the academic and industrial communities have witnessed a remarkable revolution in the field of large models. These models have exhibited significant advancements in addressing tasks related to understanding and are progressively tackling challenges in generation tasks as well. Traditionally, smaller models were employed to map real-world content into the digital realm. However, their limited capacity hindered their ability to address this challenge effectively. With the advent of large models, characterized by an increased number of parameters, a significant shift has occurred. These models have demonstrated remarkable potential in bridging the gap and achieving a more seamless interaction between the digital and real worlds.
