4 papers · 1 filter
Stable initialization without the CLT
Simon Kuang, Kyle Chickering, Xinfan Lin
Successful training of deep neural networks is highly dependent on the distribution of the initial weights. If the weights are too large, network training blows up; if they are too…
Abra: Scaling Diffusion Image Training
Kyle Chickering, Wei-An Lin, Swayam Bhanded +5
Compute-optimal scaling laws guide the training of frontier language models yet remain largely unexplored for visual generation. We present a systematic scaling law study for text-…
VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images
Zhaonan Li, Kyle R. Chickering, Bangzheng Li +13
A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties…
GQA-μP: The maximal parameterization update for grouped query attention
Kyle R. Chickering, Huijuan Wang, Mengxi Wu +7
Hyperparameter transfer across model architectures dramatically reduces the amount of compute necessary for tuning large language models (LLMs). The maximal update parameterization…