1. X
  2. Omer Bar Tal
Log inSign up
Omer Bar Tal
364 posts
Omer Bar Tal profile banner
user avatar

Omer Bar Tal

@omerbartal
Founder @ Stealth, previously @runwayml @pika_labs @Google @WeizmannScience
New York, NY
omerbt.github.io
Joined March 2016
131
Following
3,016
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    Omer Bar Tal
    @omerbartal
    Nov 6, 2025
    Update: I’ve recently left Runway to start a new company! GenAI transformed how we create, but not how we experience what’s created. It’s time to rethink how we interact with intelligence. We’ve just closed a seed round with amazing top-tier investors. If you’re excited building
  • user avatar
    Omer Bar Tal
    @omerbartal
    Aug 11
    Impressive zero shot capabilities, congrats @j0nathanj and team!
    user avatar
    Enigma
    @Enigma_AI
    Aug 11
    We just did the largest live deployment of interactive robots in history. Users online could ask the robot to do things it was never taught to do. A true foundation model, with 0 task-specific data and 0 task fine tuning. 1/10
    Image
    00:00
  • user avatar
    Omer Bar Tal
    @omerbartal
    Dec 2, 2025
    At NeurIPS until Friday! Happy to chat about model personalization, human-AI interaction, and startups :)
  • user avatar
    Omer Bar Tal
    @omerbartal
    Aug 28, 2025
    Being able to produce something this cinematic end-to-end on a laptop for the price of an Uber ride is insane
    user avatar
    Nicolas Neubert
    Runway
    @iamneubert
    Aug 27, 2025
    It's crazy what you can do in 2 hours with $100.
    Image
    00:00
  • user avatar
    Omer Bar Tal
    @omerbartal
    Aug 14, 2025
    I think one of the most important parts of working on foundation models is conviction. Once you truly believe something should work, it usually does. A great example is text-to-video: the biggest insight (credit to Sora) was that simply training video models properly at scale
    user avatar
    Cristóbal Valenzuela
    Runway
    @c_valenzuelab
    Aug 14, 2025
    I found an internal presentation from 2018 that could've been made yesterday. This was by far the hardest time to build Runway. No one really cared about or believed in what generative models could do for art and media. We were describing a future that didn't make sense to anyone
    Image

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement