Equation 2 · Part 1 · Adapters, Native Pretraining, and Unified Tokens: The Main Multimodal Architectures, Compared
Symbol theta_bridge
What this part means
thetridge is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Its job in the formula
thetridge 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 theta_bridge→Article meaning
The passage around this formula
This is the formal shape of “freeze the backbones”: the gradient update is masked to zero everywhere except the bridge parameters , so || — a few hundred million parameters in BLIP-2’s case, dramatically fewer than either tower — is the entire quantity being optimised, and and contribute a forward pass but never a gradient.
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 article section
- [3] Flamingo: a Visual Language Model for Few-Shot Learning ↗
- [2] BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models ↗
- [1] Visual Instruction Tuning ↗
These citations provide research context; check each source for the exact claim it supports.