On research
- Learning like a baby: a plan for an embodied world model
Google DeepMind's Gemini Robotics ER 2 gives robots a better high-level brain. The part I still think nobody has built is the body-first learning underneath. Here's the research plan I'd run.
3 min reads likes comments - LeCun's path, read carefully
Yann LeCun's position paper argues that intelligence needs world models that predict in representation space, not pixels. Where I agree, and where I'd push back: bodies and hands.
2 min reads likes comments - The Bitter Lesson, read by someone who hand-built facial features
Rich Sutton says 70 years of AI research show that general methods plus computation beat human knowledge every time. He's right, and it stings. My one objection is about data.
2 min reads likes comments - Every lab is building a playground
DeepMind open-sourced its 3D lab and OpenAI released Universe in the same week. Environments are becoming the new datasets.
2 min reads likes comments - Still caring about facial conformation
My last paper from grad school is out. Why I still think geometric priors for faces matter when every result now comes from deep learning.
2 min reads likes comments - Radial basis functions, for people who don't care about radial basis functions
I presented a facial animation paper this week. What it's about, explained with a rubber sheet, some pins and a steel plate.
3 min reads likes comments