Compositional Representation Learning

Overview

The field studies how models represent reusable concepts, attributes, objects, and relations so they can combine them in new ways. Approaches include factorized and tensor-product representations, object-centric or graph-based models, sparse autoencoders, and contrastive learning for vision-language models. Researchers test these ideas on compositional zero-shot recognition, image-text matching benchmarks such as SugarCrepe, and controlled tasks such as CLEVR, while probing learned features and their interactions. A central tension is that strong performance on unseen combinations does not by itself show that a model learned reusable structure: shortcuts and dataset biases can also produce apparent generalization.

Latest papers

CardsList

98 papers17 papers in the last four weeks, down 35% on the four weeks before. 0.1% of all new papers.

  1. Geometric Priors for Generalizable World Models via Vector Symbolic Architecture

    Feb 25, 2026William Youngwoo Chung, Calvin Yeung, Hansen Jin Lillemark +3World Model LearningWorld Models

  2. Referring Layer Decomposition

    Feb 22, 2026Fangyi Chen, Yaojie Shen, Lu Xu +4Compositional Representation Learning

  3. Deep Learning of Compositional Targets with Hierarchical Spectral Methods

    Feb 11, 2026Hugo Tabanelli, Yatin Dandi, Luca Pesce +1Statistical Learning TheoryCompositional Representation Learning

  4. Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

    Jan 22, 2026Geo Ahn, Inwoong Lee, Taeoh Kim +3Zero-Shot LearningVideo Action Recognition

  5. Functional Compression as Occam's Razor: Algebraic Complexity from Sensitivity Minimization

    Nov 28, 2025Dongsung Huh, Lior Horesh, Halyun JeongCompositional Representation LearningRepresentation Learning

  6. Disassociating performance from compositional feature learning

    May 14, 2025George Dimitriadis, Spyridon SamothrakisRepresentation LearningOOD Generalization