Compositional Representation Learning

Ask about this topic

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

86 papers21 papers in the last four weeks, up 24% on the four weeks before. 0.1% of all new papers.

  1. Aitchison Embeddings for Learning Compositional Graph Representations

    May 1, 2026Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas +2Neural Representation GeometryGraph Representation Learning

    Human Nature Lab, Yale University, New Haven, USA · Universit´e Paris Saclay, Universit´e Paris Cit´e, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, Gif-sur-Yvette, France · Yale Institute for Network Science, Yale University, New Haven, USA +2

  2. Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding

    Apr 14, 2026Eun Woo Im, Dhruv Madhwal, Vivek GuptaCompositional Reasoning in VLMsVLM Reasoning

    Arizona State University

  3. SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models

    Apr 14, 2026SungHo Kim, Juhyeong Park, Eda Atalay +1Language ModelingCompositional Representation Learning

    Department of Artificial Intelligence, Korea University, Seoul, South Korea · Department of Computer Science and Engineering, Korea University, Seoul, South Korea

  4. State Space Models are Effective Sign Language Learners: Exploiting Phonological Compositionality for Vocabulary-Scale Recognition

    Apr 9, 2026Bryan Cheng, Austin Jin, Jasper ZhangSign Language RecognitionCompositional Representation Learning

    William A. Shine Great Neck South High School

  5. Spectral Edge Dynamics Reveal Functional Modes of Learning

    Apr 6, 2026Yongzhong XuNeural Network Training DynamicsGrokking

  6. Event Embedding of Protein Networks : Compositional Learning of Biological Function

    Apr 1, 2026Antonin SulcProtein Representation LearningGraph Embedding

    Lawrence Berkeley National Lab

  7. Factorization Regret mediates compositional generalization in latent space

    Mar 28, 2026John SchwarczGeneralization in RLCompositional Representation Learning

    Edmond & Lily Safra Center for Brain Sciences (ELSC), The Hebrew University of Jerusalem

  8. Emergent Compositional Communication for Latent World Properties

    Mar 18, 2026Tomek KaszyńskiEmergent CommunicationCompositional Representation Learning

    Independent Researcher, Amsterdam, Netherlands

  9. FlowComposer: Composable Flows for Compositional Zero-Shot Learning

    Mar 17, 2026Zhenqi He, Lin Li, Long ChenZero-Shot LearningCompositional Representation Learning

    The Hong Kong University of Science and Technology

  10. Functorial Neural Architectures from Higher Inductive Types

    Mar 17, 2026Karen SargsyanCompositional GeneralizationCompositional Representation Learning

    Institute of Chemistry, Academia Sinica, Taipei, Taiwan

  11. Training for Compositional Sensitivity Reduces Dense Retrieval Generalization

    Mar 16, 2026Radoslav Ralev, Aditeya Baral, Iliya Zhechev +2Information RetrievalDense Retrieval

    Redis, Bulgaria and Redis, USA

  12. Ternary Gamma Semirings: From Neural Implementation to Categorical Foundations

    Mar 15, 2026Ruoqi SunNeural Network GeneralizationCompositional Representation Learning

    Intelligent Game and Decision Lab(IGDL), No.1 Xianghongqi Road, Haidian District, Beijing, 100091,China.

  13. Evaluating Compositional Structure in Audio Representations

    Mar 14, 2026Chuyang Chen, Bea Steers, Brian McFee +1Compositional Representation LearningAudio Representation Learning

    Music and Audio Research Laboratory, New York University, USA

  14. Separable neural architectures as a primitive for unified predictive and generative intelligence

    Mar 12, 2026Reza T. Batley, Apurba Sarker, Rajib Mostakim +2Compositional Representation Learning

    Kevin T. Crofton Department of Aerospace and Ocean Engineering, Virginia Polytechnic Institute and State University, Blacksburg, VA 24060, USA · Department of Mechanical Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh

  15. Intrinsic Concept Extraction Based on Compositional Interpretability

    Mar 12, 2026Hanyu Shi, Hong Tao, Guoheng Huang +5Compositional Representation Learning

    Guangdong University of Technology · VIPSHOP · Huizhou University +1

  16. From Word2Vec to Transformers: Text-Derived Composition Embeddings for Filtering Combinatorial Electrocatalysts

    Mar 9, 2026Lei Zhang, Markus StrickerVirtual ScreeningCompositional Representation Learning

    Interdisciplinary Centre for Advanced Materials Simulation, Ruhr University Bochum, Universitätsstraße 150, 44801 Bochum, Germany

  17. Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning

    Mar 4, 2026Yihang Duan, Jiong Wang, Pengpeng Zeng +5Zero-Shot LearningPrompt Learning

    University of Electronic Science and Technology of China · Ningbo University · Southwest Jiaotong University +1

  18. Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

    Feb 27, 2026Arnas Uselis, Andrea Dittadi, Seong Joon OhNeural Representation GeometryVisual Representation Learning

    Tübingen AI Center, University of Tübingen · Helmholtz · Technical University of Munich

  19. Half-Truths Break Similarity-Based Retrieval

    Feb 27, 2026Bora Kargi, Arnas Uselis, Seong Joon OhContrastive Learning for VLMsVision-Language Models

    University of Tübingen, Tübingen AI Center · Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA)

  20. WARM-CAT: Warm-Started Test-Time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning

    Feb 26, 2026Xudong Yan, Songhe Feng, Jiaxin Wang +2Zero-Shot LearningTest-Time Adaptation

    School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China

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

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

    University of California, Irvine, United States · University of California, San Diego, United States

  22. Referring Layer Decomposition

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

    Intelligent Editing Team, Intelligent Creation, ByteDance

  23. Recursive Concept Evolution for Compositional Reasoning in Large Language Models

    Feb 17, 2026Sarim ChaudhryCompositional ReasoningTest-Time Adaptation

    Purdue University

  24. 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

    1Kyung Hee University · ∗This work was done during an internship at NAVER Cloud. · 2NAVER Cloud

  25. Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders

    May 28, 2025Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev +2Representation LearningActivation Sparsity

    T-Tech

  26. Disassociating performance from compositional feature learning

    May 14, 2025George Dimitriadis, Spyridon SamothrakisRepresentation LearningOOD Generalization

    Computer Science and Electronic Engineering Department of the University of Essex