---
answer: direct
beat: ai-technology
source: 1 article · updated: November 17, 2026
---

What's the practical difference between late fusion and joint fusion when combining embeddings with tabular data?

Late fusion freezes the pretrained embeddings and feeds them alongside tabular features into a separate model like LightGBM — simple, but the embeddings never adapt to the specific downstream task. Joint fusion trains the transformer and the tabular model together end-to-end, letting the transformer learn to extract exactly the signal that complements the tabular features for that specific prediction task, which is more powerful but requires a more involved training setup.

Answered in

Why Fintechs Are Replacing Hand-Built Features With Foundation Models

Manually engineered features don't transfer between fraud, credit, and recommendation models. A transformer trained on raw transactions can.

Crashtech Editorial November 17, 2026 How AI Actually Works

Read the full analysis

Other questions this article answers

More how ai actually works questions

Every answer on Crashtech is written by the editor of the article it comes from — never auto-summarised. Browse all answers or the How AI Actually Works beat.