# Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)

arXiv: https://arxiv.org/abs/2508.20322 · HTML: https://mlsanity.com/paper/2508.20322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)](https://mlsanity.com/paper/2402.10376/) (2024)
- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning](https://mlsanity.com/paper/1509.01692/) (2015)
- [Embedding Arithmetic of Multimodal Queries for Image Retrieval](https://mlsanity.com/paper/2112.03162/) (2021)
- [The CLIP Model is Secretly an Image-to-Prompt Converter](https://mlsanity.com/paper/2305.12716/) (2023)
- [Exact and Heuristic Algorithms for Semi-Nonnegative Matrix Factorization](https://mlsanity.com/paper/1410.7220/) (2014)
- [InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images](https://mlsanity.com/paper/2211.12760/) (2022)

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

- [Conducting Stylistic Analysis of Paintings through an Art-History Agent](https://mlsanity.com/paper/2608.29644/) (2026)

## Abstract (arXiv)

Vision-language co-embedding networks, such as CLIP, provide a latent embedding space with semantic information that is useful for downstream tasks. We hypothesize that the embedding space can be disentangled to separate the information on the content of complex scenes by decomposing the embedding into multiple concept-specific component vectors that lie in different subspaces. We propose a supervised dictionary learning approach to estimate a linear synthesis model consisting of sparse, non-negative combinations of groups of vectors in the dictionary (atoms), whose group-wise activity matches the multi-label information. Each concept-specific component is a non-negative combination of atoms associated to a label. The group-structured dictionary is optimized through a novel alternating optimization with guaranteed convergence. Exploiting the text co-embeddings, we detail how semantically meaningful descriptions can be found based on text embeddings of words best approximated by a concept's group of atoms, and unsupervised dictionary learning can exploit zero-shot classification of training set images using the text embeddings of concept labels to provide instance-wise multi-labels. We show that the disentangled embeddings provided by our sparse linear concept subspaces (SLiCS) enable concept-filtered image retrieval (and conditional generation using image-to-prompt) that is more precise. We also apply SLiCS to highly-compressed autoencoder embeddings from TiTok and the latent embedding from self-supervised DINOv2. Quantitative and qualitative results highlight the improved precision of the concept-filtered image retrieval for all embeddings.