Naomi ken korem

Mastering the Art of Generative Models: Training and Controlling Text-to-Video Models


I am Naomi Ken Korem, an expert in the field of computer vision and generative AI, holding an MSc in Computer Science. With 8 years of industry experience, my specialization lies in the precise control of generative AI models and their large-scale training.


Generating realistic images and brief videos from text has marked a significant milestone. However, as human beings, our ambitions extend further. We aim not only for visually appealing outcomes but also for enhanced control and the ability to produce longer, more detailed videos. In my talk, I will explore the techniques employed to precisely control model outputs and detail our approach to scaling the training of text-to-video models to fulfill our specific requirements at Lightricks.


8:45 Reception
9:30 Opening remarks by WiDS TLV ambassadors Noah Eyal Altman, Or Basson, and Nitzan Gado
9:45 Dr. Aya Soffer, IBM: "Putting Generative AI to Work: What Have We Learned So Far?"
10:15 Prof. Reut Tsarfaty, Bar-llan University: "Will Hebrew Speakers Be Able to Use Generative AI in Their Native Tongue?"
10:45 Poster Pitches
10:55 Break
11:10 Lightning talks
12:30 Lunch & poster session
13:30 Roundtable session & poster session
14:15 Roundtable closing
14:30 Break
14:40 Naomi Ken Korem, Lightricks: "Mastering the Art of Generative Models: Training and Controlling Text-to-Video Models"
15:00 Dr. Yael Mathov, Intuit: "Surviving the AI-pocalypse: Your Guide to LLM Security"
15:20 Closing remarks
15:30 The end