#vision-transformer
2 articles
01
·Inference & Serving·★ MEMBER·PAPER·6 min read
Paper Explained: IntBMoE — Every Expert Contributes, Yet Each Token Runs Only a Few Blocks
In a Mixture-of-Experts layer, how many experts inform a token, how many get computed, and how many weight sets must be built have always been tied together. IntBMoE (arXiv:2609.21346) cuts those ties by composing experts densely and executing blocks sparsely. Explained from scratch, using only the paper itself.
02
·Inference & Serving·★ MEMBER·PAPER·10 min read
Paper Explained: FreeFlow — Optical Flow with a Hierarchical Transformer and No Flow-Specific Parts
FreeFlow drops correlation volumes, warping, and iterative refinement, and reaches the top of Sintel, KITTI-2015, and Spring using only window, shifted-window, and low-resolution global attention. We walk through it from zero.