Equation 11 · Adapters, Native Pretraining, and Unified Tokens: The Main Multimodal Architectures, Compared
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
allowed to denote. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
subscript
subscript
The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
The same cross-entropy objective a text-only language model uses is the entire training objective here — the only thing that changed is what is allowed to denote. Whether index names a subword, a 16-by-16 image patch code, or a discretised robot joint angle is invisible to the loss function; the difficulty this section documents is not in the objective but in keeping training numerically stable once the vocabulary spans quantities of such different statistical character.
Sources cited in the article section
- [6] A Generalist Agent ↗
- [7] Chameleon: Mixed-Modal Early-Fusion Foundation Models ↗
- [8] CM3: A Causal Masked Multimodal Model of the Internet ↗
These citations give research context. Read each source to check which claims it supports.