
V-JEPA, AI Reasoning from a Non-Generative Architecture with Mido Assran - #677
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Predicting Encodings vs. Pixels
- Predicting low-level pixels is computationally intensive and doesn't necessarily contribute to building a world model capable of reasoning.
- Instead, focus on predicting encodings/embeddings for more efficient learning and abstract understanding.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.