No Priors: Artificial Intelligence | Technology | Startups The Timeline for Realistic 4-D: Devi Parikh from Meta on Research Hurdles for Generative AI in Video and Multimodality
Jul 20, 2023
Devi Parikh, Research Director in Generative AI at Meta and an Associate Professor at Georgia Tech, dives into the challenges of creating AI-generated videos. She discusses her innovative project, MAV3D, which creates animations from text prompts, and highlights the importance of multimodal inputs for user control. The conversation also touches on the evolution of computer vision techniques and the democratization of creative expression through generative AI. Both exciting advancements and significant research hurdles in the field are explored.
AI Snips
Chapters
Transcript
Episode notes
Devi's Path to AI
- Devi Parikh's journey into AI began with pattern recognition at Rowan University.
- CMU's PhD program solidified her path, shifting from non-visual to visual modalities.
Human-Computer Interaction
- Devi Parikh's research interest in human-computer interaction guided her exploration of various modalities.
- This led her from visual attributes to natural language and eventually to AI for creativity.
Joining Meta
- Devi Parikh joined Meta (then Facebook) initially for a one-year research stint.
- Enjoying the experience, she maintained a split role between Meta and Georgia Tech for several years.