← All parts of this equation

Equation 6 · Part 4 · One Model, Many Modalities: What Multimodal Systems Actually Share

Symbol u_i

L=−1B∑i=1Blog⁡exp⁡(⟨ui,vi⟩/τ)∑j=1Bexp⁡(⟨ui,vj⟩/τ),\mathcal{L} = -\frac{1}{B} \sum_{i=1}^{B} \log \frac{\exp(\langle u_i, v_i \rangle / \tau)}{\sum_{j=1}^{B} \exp(\langle u_i, v_j \rangle / \tau)},
uiu_i

What this part means

the image embedding.

Its job in the formula

uiu_i is one of the signed contributions combined to compute the quantity on the left.

Where the article explains it

with image embedding uiu_i , text embedding viv_i , and a learned temperature τ\tau .

The passage around this formula

…encodes each side separately into a normalised vector, and trains both encoders so that matched pairs score higher than mismatched ones. In its softmax form the objective is L=−1B∑i=1Blog⁡exp⁡(⟨ui,vi⟩/τ)∑j=1Bexp⁡(⟨ui,vj⟩/τ)\mathcal{L} = -\frac{1}{B} \sum_{i=1}^{B} \log \frac{\exp(\langle u_i, v_i \rangle / \tau)}{\sum_{j=1}^{B} \exp(\langle u_i, v_j \rangle / \tau)}. with image embedding uiu_i , text embedding viv_i , and a learned temperature τ\tau . Radford and colleagues showed that this simple pre-training task, applied to 400 million image–text pairs collected from the internet, matched the accuracy of the original ResNet-50 on ImageNet zero-shot without using any of the 1.28…

Read this part in the article →

Learn the underlying idea

A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.

Open the illustrated subscripts: which member of a family? guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.