1 citations · 1 across the 2 of their papers we have counts for
2 papers
cs.LG2026
Ember: A Kilobyte-State Optimizer for Token Interfaces
Kathan Shah
Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them. We show that this interface h…
cs.CV2023★ 1 cited
Positional Embedding-Aware Activations
Kathan Shah, Chawin Sitawarin
We present a neural network architecture designed to naturally learn a positional embedding and overcome the spectral bias towards lower frequencies faced by conventional activatio…