- machine-learning
- deep-learning
- artificial-intelligence
- robotics
- robotik
- reinforcement-learning
- computer-vision
- data-science
- neuroscience
- wordpress
- medium
- external-posts
•
•
•
•
•
•
•
•
•
•
•
-
From Seeing to Acting
-
Where Does a Vision Transformer Keep Its Sense of Geometry?
A self-supervised ViT can predict depth from a single image with no 3D supervision at all. That’s usually treated as one fact. A recent paper asks a sharper question: is that geometry sitting in a few clean directions the network can read out directly, or is it smeared across the whole feature space, waiting for…Daha fazla
-
From 99.8% to 2.2%: Diagnosing the Sim2Real Gap in a 144-Class Clock Classifier
-
Conway’s Game of Life Is Small, but It Teaches Big Engineering Lessons
-
Why AI Companies Are Building Their Own Chips (And What It Actually Buys Them)
A note on scope: chip architecture isn’t my research area. This is a synthesis of public reporting on a trend worth understanding, written with the same care about sourcing and overclaiming I try to apply to my own work. In about 18 months, nearly every major AI lab and cloud provider has quietly become a…Daha fazla