3 citations · 3 across the 5 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.CL2025
Length-MAX Tokenizer for Language Models
Dong Dong, Weijie Su
We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and…
math.OC2025
Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?
Weijie Su
In this paper, we introduce a model for analyzing deep learning optimization over a single iteration by leveraging the matrix structure of the weights. We derive the model by assum…