• A toy model of distillation

  6 min read   ·   March 12, 2026

  2026   ·   Physics-of-AI   Optimization     ·   AI  

• When does Muon work? Model depth is a key factor

  3 min read   ·   March 11, 2026

  2026   ·   Physics-of-AI   Optimization     ·   AI  

• MOE 1 -- Experssive power of MOEs through the lens of spectral bias and memorization capacity

  4 min read   ·   March 10, 2026

  2026   ·   Physics-of-AI   MLP   MOE   Memorization   Spectral-bias     ·   AI  

• A toy model of video generative models -- bottleneck dimension controls "classical"/"quantum" strategies

  7 min read   ·   March 09, 2026

  2026   ·   Physics-of-AI   Representation   Diffusion   Flow-matching   Autoencoder   Video-generative-model     ·   AI  

• Memory 2 -- How many bits does each parameter store? An analysis of MLP

  8 min read   ·   March 06, 2026

  2026   ·   Physics-of-AI   Memory   Activation-function     ·   AI