Today we’re joined by Mido Assran, a research scientist at Meta’s Fundamental AI Research (FAIR). In this conversation, we discuss V-JEPA, a new model being billed as “the next step in Yann LeCun's vision” for true artificial reasoning. V-JEPA, the video version of Meta’s Joint Embedding Predictive Architecture, aims to bridge the gap between human and machine intelligence by training models to learn abstract concepts in a more efficient predictive manner than generative models. V-JEPA uses a novel self-supervised training approach that allows it to learn from unlabeled video data without being distracted by pixel-level detail. Mido walks us through the process of developing the architecture and explains why it has the potential to revolutionize AI.

🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confi...


🗣️ CONNECT WITH US!
===============================
Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/
Join our Slack Community: https://twimlai.com/community/
Subscribe to our newsletter: https://twimlai.com/newsletter/
Want to get in touch? Send us a message: https://twimlai.com/contact/


📖 CHAPTERS
===============================
00:00 - Introduction to the Video Joint-Embedding Predictive Architecture (V-JEPA)
01:33 - Inspiration for the JEPA
08:08 - How V-JEPA works
17:25 - How V-JEPA was built
29:10 - Prediction vs Generation
40:21 - Potential of V-JEPA
42:50 - Challenges and lessons learned
46:19 - The future of AI reasoning
47-55 - Conclusion


🔗 LINKS & RESOURCES
===============================
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture - https://arxiv.org/abs/2301.08243
Revisiting Feature Prediction for Learning Visual Representations from Video (V-JEPA) - https://ai.meta.com/research/publicat...


📸 Camera: https://amzn.to/3TQ3zsg
🎙️Microphone: https://amzn.to/3t5zXeV
🚦Lights: https://amzn.to/3TQlX49
🎛️ Audio Interface: https://amzn.to/3TVFAIq
🎚️ Stream Deck: https://amzn.to/3zzm7F5