Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
TwelveLabs (twelvelabs.io) Profile picture
TwelveLabs (twelvelabs.io)
@twelve_labs
🎥 Building multimodal foundation models for video understanding: https://t.co/iKo4kmNv6p 👉 Join our community: https://t.co/1b53LYUCBc
Oct 24, 2023 • 6 tweets • 2 min read
🚀We are thrilled to release Pegasus-1, our latest video-language foundation model.

We are also excited to share that Twelve Labs has received strategic investments from NVentures of @nvidia, @intelcapital, and @SamsungNext.

Check thread for model details and early access👇 @nvidia @intelcapital @SamsungNext 🎥 We adopt a “Video First” strategy, focusing our model, data, and systems solely on processing and understanding video data.

Our 4 core principles: Efficient Long-form Video Processing, Multimodal Understanding, Video-native Embeddings, Deep Alignment of Video and Language. Image
Oct 18, 2023 • 17 tweets • 9 min read
🚀What an incredible weekend it was at the @TEDAI2023 23Labs Hackathon!

We are still buzzing from the energy, creativity, and innovation that we witnessed during this two-day event at @SHACK15sf.


Image
Image
Image
Image @TEDAI2023 @SHACK15sf The enthusiasm for Multimodal AI was immense, with a multitude of projects leveraging text, image, audio, and video modalities to create groundbreaking applications.

It was truly inspiring to see how the participants pushed the boundaries of what's possible with AI.😯


Image
Image
Image
Image