LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
Paper • 2511.04952 • Published
Shao Wei
visionshao
AI & ML interests
Text Generation, Interpretable Machine Translation
Recent Activity
authored a paper 1 day ago
LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model authored a paper 1 day ago
AIS: Adaptive Importance Sampling for Quantized RL published a dataset about 2 months ago
visionshao/olmocr3-books-remix-1T-stackOrganizations
None yet
authored 2
papers 1 day ago
published a
dataset about 2 months ago
updated a
dataset about 2 months ago