# Individuation in Neural Models with and without Visual Grounding

arXiv: https://arxiv.org/abs/2409.18868 · HTML: https://mlsanity.com/paper/2409.18868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 31 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Builds on (most cited first, 6 of 6)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)
- [Multimodal Intelligence: Representation Learning, Information Fusion, and Applications](https://mlsanity.com/paper/1911.03977/) (2019)

## Abstract (arXiv)

We show differences between a language-and-vision model CLIP and two text-only models - FastText and SBERT - when it comes to the encoding of individuation information. We study latent representations that CLIP provides for substrates, granular aggregates, and various numbers of objects. We demonstrate that CLIP embeddings capture quantitative differences in individuation better than models trained on text-only data. Moreover, the individuation hierarchy we deduce from the CLIP embeddings agrees with the hierarchies proposed in linguistics and cognitive science.