Skip to contentScience, DecodedContext Jamming
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling (H-Net)
Sukjun Hwang, Brandon Wang, Albert Gu · 2025
Why this paper
Recent work on learned tokenization. Its key equation reuses a dot product and cosine similarity you already know from attention, now used to decide where "chunks" begin.
Pass 1 of 8
Research question
What problem is the paper attacking?
Where to look: Abstract and Introduction
Your read