Memorization in Generative Models

Ask about this topic

Overview

Memorization research asks when generative models reproduce training data rather than learn reusable patterns, raising concerns about privacy, copyright, and trustworthy evaluation. Researchers test language models with extraction prompts and canaries, and use membership inference, similarity measures, and functional comparisons; for diffusion models, they also study score geometry, denoising trajectories, and noise schedules. Mitigation approaches include training-time regularization, unlearning and weight filtering, and inference-time steering or sampling changes, evaluated against both memorization and retained generation quality. A central challenge is distinguishing harmful recall from legitimate generalization, since near-duplicates and dataset structure can confound audits, while reducing copying may also weaken fidelity or utility.

Latest papers

CardsList

88 papers13 papers in the last four weeks, up 117% on the four weeks before. 0.1% of all new papers.

  1. Valid Early Detection of Memorization in Diffusion Models

    Oct 25, 2026Yixiao Jing, Chia-Yu Hsu, Milad Hoseinpour +1Memorization in Generative ModelsSequential Hypothesis Testing

    Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA

  2. Information-Theoretic Scaling Laws for Generative Diffusion Training

    Oct 23, 2026Druv Pai, Dejan Stancevic, Yi Ma +1Diffusion ModelsMemorization in Generative Models

    UC Berkeley · Radboud University · HKU, UC Berkeley

  3. Detection of Memorization in Diffusion Models Through Thermodynamic Singularity

    Oct 20, 2026Iljung Kim, Kangwoo Park, Yung-Kyun Noh +1Memorization in Generative ModelsDiffusion Models

    Hanyang University Seoul 04763, Rep. of Korea. · Cornell Tech New York, NY 10044, USA

  4. Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models

    Oct 13, 2026Shashank Sule, Xinyue Yu, Boonam Shin +3Memorization in Generative ModelsDiffusion Models

    Department of Mathematics, University of California, Los Angeles, CA 90095, USA. · Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA.

  5. Your Discrete Graph Diffusion Model is Secretly Memorizing

    Oct 9, 2026Adarsh Jamadandi, Nicolas KerivenMemorization in Generative ModelsGraph Diffusion

    CNRS, IRISA, Rennes, France

  6. Early Signatures of Memorization in Diffusion Models via Basin Geometry and Cyclic Denoising

    Oct 8, 2026Nikhil Verma, Siddharthan Dileep, Anoop Singh +4Memorization in Generative ModelsDiffusion Models

    Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi · Department of Computer Science and Engineering, Indian Institute of Technology Delhi · Jawaharlal Nehru Centre for Advanced Scientific Research +2

  7. Memorization and Malign Generalization in Conditional Diffusion Models with Random Features

    Oct 8, 2026Gwangho Kim, Sungyoon LeeRandom Feature MethodsConditional Diffusion Models

    Department of Computer Science Hanyang University, Seoul

  8. Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval

    Oct 6, 2026Hicham Randrianarivo, Logan Renaud, Alexia AllalGenerative RetrievalMemorization in Generative Models

    Artefact Research Center France

  9. Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioning

    Oct 1, 2026Hyungjun Joo, Sehwan Kim, Hyeonggeun Han +2Diffusion Model AlignmentAttention Control in Diffusion Models

    Seoul National University · Konkuk University

  10. From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models

    Sep 30, 2026Cristina López Amado, Marco Fumero, Francesco LocatelloMemorization in Generative ModelsDiffusion Models

    Institute of Science and Technology Austria (ISTA)

  11. PEG-Tab: Sampling-Time Record Repair and Release Control for Tabular Synthesis

    Sep 30, 2026Pengfei Li, QinYi Liu, Mohammad KhalilSynthetic Data GenerationSynthetic Tabular Data Generation

  12. Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation

    Sep 30, 2026Arhan Vohra, Choenden Kyirong, Laura Ibáñez-Martínez +1Text-to-Music GenerationAudio Diffusion Models

    Music Technology Group, Universitat Pompeu Fabra

  13. First Learn, Then Memorize: The Spectral Bias of Diffusion Models

    Sep 28, 2026Raphaël Urfin, Tony Bonnaire, Giulio Biroli +1Neural Network GeneralizationMemorization in Generative Models

    Laboratoire de Physique de l’École normale supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris Cité, F-75005 Paris, France · Université Paris-Saclay, CNRS, Institut d’Astrophysique Spatiale, 91405 Orsay, France · Department of Computing Sciences, Bocconi University, Milano, Italy

  14. Background Gradients Shape Memorization in Flow Matching

    Sep 27, 2026Xuanhua Yin, Boyu Wei, Shuyi Zhang +3Memorization in Generative ModelsFlow-Based Generative Modeling

    School of Computer Science, The University of Sydney · Institute of Automation, Chinese Academy of Sciences

  15. The Null Is the Hard Part: Exact Tests for Memorization in Generative Models

    Sep 23, 2026Sushovan Majhi, Pramita BagchiPermutation TestingMemorization in Generative Models

    Data Science, George Washington University, USA · Statistics, George Washington University, USA

  16. Double Descent and Malign Overfitting in Diffusion Models

    Sep 22, 2026Raphaël Urfin, Tony Bonnaire, Giulio Biroli +1Double DescentBenign Overfitting

    Laboratoire de Physique de l’École normale supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris Cité, F-75005 Paris, France · Université Paris-Saclay, CNRS, Institut d’Astrophysique Spatiale, 91405 Orsay, France · Department of Computing Sciences, Bocconi University, Milano, Italy

  17. Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning

    Sep 21, 2026Donghyun Kim, Taehyuk Lee, Jinyeong Kim +4Memorization in Generative ModelsDiffusion Model Unlearning

    Department of Computer Science and Engineering, Konkuk University Trustworthy Machine Learning Lab Seoul, Republic of Korea

  18. Copying Versus Randomization in Lempel-Ziv Music Synthesis

    Sep 10, 2026Nadav Mishan, Ram ZamirControllable Music GenerationSymbolic Music Generation

    Department of Electrical Engineering Tel Aviv University Tel Aviv, Israel

  19. Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++

    Sep 3, 2026Antonio Scardace, Francesco Guarnera, Sebastiano Battiato +1Privacy AuditingMemorization in Generative Models

    University of Catania, Department of Mathematics and Computer Science, Catania, Italy

  20. Generalization, memorization, and overfitting for diffusion models trained in the lazy high-dimensional regime

    Aug 25, 2026Hugo Latourelle-Vigeant, Sinho Chewi, Aram-Alexandre Pooladian +2Generative ModelingScore-Based Generative Modeling

    Department of Statistics and Data Science, Yale University · Institute for Foundations of Data Science, Yale University · Department of Applied Physics, Yale University

  21. Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination

    Aug 7, 2026Ruijie Hou, Yueyang Jiao, Zhao Wang +1LLM EvaluationMemorization in Generative Models

    Zhejiang University

  22. The Geometry of Memorization: Finite-Time Spectral Sensitivity as a Diagnostic for Flow Matching Models

    Jul 14, 2026Shuchan WangFlow MatchingNeural Network Memorization

  23. An exact information theory of generalization phase transitions in Bayesian diffusion models

    Jul 9, 2026Henry Hunt, Mason Kamb, Surya GanguliMemorization in Generative ModelsDiffusion Models

    Department of Applied Physics Stanford University Stanford, CA 94305

  24. Anchored or Drifting: What Recursive Self-Generation Reveals About Training Data

    Jun 30, 2026Wojciech Łapacz, Stanisław PawlakMembership Inference AttacksMemorization in Generative Models

    Warsaw University of Technology

  25. Explaining Machine Learning and Memorization with Statistical Mechanics

    Jun 30, 2026Robin TheriaultStatistical Physics of LearningNeural Network Memorization

    Faculty of Science

  26. Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models

    Jun 22, 2026Rishabh Sharma, Stefano MartinianiTraining Data ExtractionDiffusion Model Sampling

    Simons Center for Computational Physical Chemistry, New York University · Center for Soft Matter Research, Department of Physics, New York University · Center for Neural Science, New York University +1

  27. MGI: Member vs Generated Inference

    Jun 22, 2026Bihe Zhao, Michel Meintz, Juangui Xu +2Image GenerationMemorization in Generative Models

    CISPA Helmholtz Center for Information Security

  28. Substitution-Based Analysis of Structural Novelty for Generative Models of Materials

    Jun 22, 2026Masahiro Negishi, Aron WalshMemorization in Generative ModelsCrystal Structure Generation

    Department of Materials, Imperial College London, Exhibition Road, South Kensington, SW7 2AZ, London, United Kingdom.

  29. NAMESAKES: Probing Identity Memorization in Text-to-Image Models

    Jun 18, 2026Morris Alper, Vasudha Varadarajan, Moran Yanuka +2Memorization in Generative ModelsT2I Generation Evaluation

    Carnegie Mellon University · Tel Aviv University · Cornell University

  30. Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory

    Jun 11, 2026Zhibao Chen, Qian ChengLLM Agent MemoryPersistent Memory for Language Models

    Huatai Securities, Nanjing, China