# Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings

arXiv: https://arxiv.org/abs/2605.22391 · HTML: https://mlsanity.com/paper/2605.22391/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [All-but-the-Top: Simple and Effective Postprocessing for Word Representations](https://mlsanity.com/paper/1702.01417/) (2017)
- [Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images](https://mlsanity.com/paper/1810.06553/) (2018)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario](https://mlsanity.com/paper/2210.11431/) (2022)
- [Epicure: Multidimensional Flavor Structure in Food Ingredient Embeddings](https://mlsanity.com/paper/2604.22776/) (2026)

## Built on by (most cited first, 1 of 1)

- [FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Training](https://mlsanity.com/paper/2608.20574/) (2026)

## Abstract (arXiv)

We present Epicure, a family of three sibling skip-gram ingredient embeddings retrained from scratch on a multilingual recipe corpus. We aggregate 4.14M recipes from 11 sources spanning seven languages, English, Chinese, Russian, Vietnamese, Spanish, Turkish, Indonesian, German, and Indian-English, and normalise the raw ingredient strings to 1,790 canonical entries via an LLM-augmented pipeline. A 203,508-edge ingredient-ingredient NPMI graph and an 80,019-edge typed FlavorDB ingredient-compound graph, 2,247 typed compound nodes across 15 categories, seed three Metapath2Vec variants that share architecture and hyperparameters and differ only in the random-walk schema: Cooc walks the co-occurrence graph only, Chem walks the typed compound metapaths only, and Core blends both via injected ingredient-ingredient walks at controlled mixing, placing each model at a distinct point on the chemistry-vs-recipe-context spectrum.