Full Name
Ani Kembhavi
Job Title
Research Manager
Allen Institute for AI
Brief Biography
Ani Kembhavi heads PRIOR, the computer vision research group at the Allen Institute for AI (AI2) in Seattle. He is also an Affiliate Associate Professor at the Computer Science & Engineering department at the University of Washington. He obtained his PhD in Electrical Engineering at the University of Maryland, College Park, and his Bachelors in Engineering from the College of Engineering in Pune, India. Prior to AI2, he spent 5 years at Microsoft Bing, building large-scale machine learning systems in the Image & Video Search Relevance team.

Ani's research interests lie at the intersection of computer vision, natural language processing, and embodied AI. They include creating general-purpose vision systems that can answer questions, write captions, locate objects in images, etc., training embodied AI agents to explore, navigate, follow instructions, locate objects and manipulate them, learning generalizable visual representations through gameplay, understanding complex situations in images and videos, and creating AI systems that can collaborate with one another and collaborate with humans to perform tasks.

Ani is passionate about creating open-source software that can be used by large numbers of AI researchers and practitioners. The PRIOR team has released and maintains several open-source projects, including the popular AI2-THOR simulated environment -- which has been extensively used by the research community to train embodied AI agents, RoboTHOR -- a simulation-to-real platform which is used to study the transfer of embodied AI policies from simulated environments to real-world settings, and AllenAct -- a learning framework with a focus on improving the reproducibility, reusability, and accessibility of embodied AI research.
Ani Kembhavi