Equation 2 · Part 1 · One Model, Many Modalities: What Multimodal Systems Actually Share
Symbol H
What this part means
the height.
Its job in the formula
H is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Full expression→Symbol H→Article meaning
Where the article explains it
for an image of height H and width W at patch size P .
The passage around this formula
for an image of height H and width W at patch size P . The quadratic relationship is the entire practical story of image tokenisation. Halving the patch size quadruples the sequence, and attention cost grows faster still. Every deployed system therefore resolves a three-way tension between input resolution, patch size, and context budget, and it resolves it by throwing away detail.
Learn the underlying idea
A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.
Open the illustrated variables: a letter stands for a value guide →
See this notation across published equations →
Sources cited in the article section
- [2] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale ↗
- [3] Neural Discrete Representation Learning ↗
- [4] High Fidelity Neural Audio Compression ↗
- [5] Robust Speech Recognition via Large-Scale Weak Supervision ↗
These citations provide research context; check each source for the exact claim it supports.