Model Architecture & Training MethodsWortsman et al.

Model Soups

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Model Soups

Why it matters

Demonstrated that simply averaging the weights of several fine-tuned models raises performance; the starting point of model merging

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/2203.05482

Added in Week 35, 2026 · See that week

On the map — ⑪ Model Architecture line

  1. Previous stopSwitch Transformer
  2. This recordModel Soups
  3. Next stopChinchilla
See it on the map

Same week

Marcus writes Deep Learning Is Hitting a Wall for NautilusOfficialmuP / Tensor Programs VPaper

Nearby on the same axis

muP / Tensor Programs VPaperChinchillaPaperGoogle Research announces PaLM (540B)OfficialEmergent Abilities of LLMsPaper