Unifying AI Approaches towards Human and Animal Well-being

Title: Unifying AI Approaches towards Human and Animal Well-being

Abstract: AI/ML technologies are transforming how we understand the world, with tremendous potential for discovering new knowledge and solutions for improving well-being. To fully realize this potential, we need tight collaborations between AI researchers and domain experts to motivate model development with real-world needs, such as from neuroscience and veterinarian medicine. This talk will focus on developing AI systems for scientific applications, and we will discuss progress towards developing automated scientist-in-the-loop solutions for animal behavior analysis in behavioral neuroscience. I will present how different paradigms such as supervised learning, self-supervised learning, and, more recently, foundation models are used in new ways for scientists to study animal behavior from video data, including behavior quantification and structure discovery. My aim is to enable AI that collaborates with scientists to accelerate the scientific process and build the foundations for innovations to improve human and animal well-being.

Bio: Jennifer is a research scientist at Google, joining Cornell CIS as an assistant professor in fall 2024. Her research focuses on developing scientist-in-the-loop computational systems that automatically convert experimental data into insight with minimal expert effort. She aims to accelerate scientific discovery and optimize expert attention in real-world workflows, tackling challenges including annotation efficiency, model interpretability and generalization, and semantic structure discovery.