Constrained Generative Modeling

Overview

Constrained generative modeling studies how to generate useful samples while respecting requirements such as grammatical rules, molecular validity, physical laws, or safe trajectories. Common approaches include grammar and automaton-based decoding, diffusion and flow-matching methods with projections or primal-dual guidance, and models that build constraints into their representations or training objectives. Applications range from structured text and synthetic data to molecules, motion planning, scientific fields, and engineering design, with evaluation often balancing constraint satisfaction against sample quality, diversity, and computational cost. A central challenge is that enforcing feasibility does not necessarily preserve the model’s intended distribution or uncertainty, so methods must limit bias while remaining efficient and reliable under complex constraints.

Latest papers

CardsList

192 papers50 papers in the last four weeks, up 163% on the four weeks before. 0.3% of all new papers.

  1. Framework-Conditional Open Materials Generation

    Oct 29, 2026Maya M. Martirossyan, Hillary Pan, Philipp Höllmer +1Crystal Structure GenerationMaterials Discovery

  2. AegisFlow: Training-Free Non-Myopic Path-Safe Guided Flow Matching

    Oct 29, 2026Kunpeng Liu, Boshi Zhang, Keyou YouConstrained Generative ModelingFlow-Based Generative Modeling

  3. Discovery of Diverse and Realistic Financial Tail-Risk Using Generative Flow Networks

    Oct 28, 2026Adir Serruya, Gilad KatzGenerative Flow NetworksDiversity-Aware Sampling

  4. AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models

    Oct 28, 2026Pengfei Cai, Katharina S. C. Jäger, Utkarsh Utkarsh +4Constrained Generative ModelingCrystal Structure Generation

  5. Condition-Enhanced Generative Adversarial Network for Aerodynamic Configuration Design of Commercial Aircraft

    Oct 25, 2026Youzheng Yu, Jiaqing Kou, Weiwei ZhangConditional Generative ModelingGenerative Adversarial Networks

  6. From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries

    Oct 22, 2026Bayram Ayadi, Florian Geissler, Johanna SchmidhuberText SummarizationHealthcare

  7. Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion

    Oct 22, 2026Ricardo Luna Gutierrez, Vineet Gundecha, Rahman Ejaz +5Inverse DesignConstrained Generative Modeling

  8. Orbitol: Crystal Generation on Wyckoff Orbits

    Oct 21, 2026Ivan Žugec, Joshua Rosenthal, Ivor Lončarić +2Crystal Structure GenerationMaterials Discovery

  9. CrystalAR: Autoregressive Modeling for Symmetric Crystal Generation

    Oct 20, 2026Ziqiao Meng, Rongsheng Chen, Zhi Zheng +4Crystal Structure GenerationCrystal Structure Prediction

  10. CAST: Cast-Admissible Generative Design and Shape Optimization with Paired Depth Images

    Oct 19, 2026Jihoon Kim, Yongmin Kwon, Namwoo Kang3D Shape GenerationConstrained Generative Modeling

  11. Logic-Guided Graph Denoising Diffusion Models

    Oct 16, 2026Samuel Cognolato, Luciano Serafini, Alessandro Sperduti +1Graph GenerationConstrained Generative Modeling

  12. PONDER: Learning to Generate in the Right Order

    Oct 16, 2026Julius Erbach, Dominik Narnhofer, Bernt Schiele +2RL for Generative ModelsAutoregressive Image Generation

  13. Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models

    Oct 15, 2026Kostas Triaridis, Morris E. Sharp, Nebojsa JojicGenerative ModelingDiversity-Aware Sampling

  14. Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion

    Oct 15, 2026Renxiang Huang, Yuchen Liang, Yingbin Liang +2Diffusion ModelsDiffusion Sampling

  15. Machine-learning-based neutrino-event generation constrained by experimental measurements

    Oct 14, 2026Jose Luis Bonilla, Krzysztof M. Graczyk, Rwik Dharmapal Banerjee +3High-Energy PhysicsConstrained Generative Modeling

  16. Exact Topological Compliance: Generating Persistence-Equivalent Graphs

    Oct 13, 2026Mattie Ji, Indradyumna Roy, Vikas GargGraph ConstructionConstrained Generative Modeling

  17. When do explicit penalties improve flow matching?

    Oct 11, 2026Lea Kunkel, Alberto González-Sanz, Sophie LangerFlow MatchingConstrained Generative Modeling

  18. MontageFlow: Physically Valid High Fidelity EEG Generation

    Oct 10, 2026Sudarshan Regmi, Nabaraj Subedi, Arvind Pillai +6EEG Signal GenerationTime Series Generation

  19. ConicFlow: constrained Inference-time optimal control for flow matching models

    Oct 9, 2026Shervin Khalafi, Kasra Fallah, Sung Cho +3Constrained Generative ModelingConstrained Sampling

  20. Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories

    Oct 9, 2026Zhenhao Huang, Li Sun, Philip S. YuTrajectory GenerationConstrained Generative Modeling

  21. Localized Generative Design of Ship Hulls with Diffusion Models and High-Fidelity Assessment

    Oct 9, 2026Hadi Keramati, Mohammed A. Hannan, Patrick Kirchen +4Generative ModelingConstrained Generative Modeling

  22. Primal-Dual Flow Matching for Sample-Wise Constrained Generation

    Oct 8, 2026Zhengyan Huan, Peter Y. Lu, Shuchin AeronConstrained Generative ModelingConstrained Sampling

  23. Think Before You Paint: Recursive Latent Reasoning for Diffusion Models

    Oct 7, 2026Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk +2Latent Visual ReasoningDiffusion Models

  24. Constrained Diffusion for Data-Scarce Orbital Monte Carlo in Constellation Tasking

    Oct 7, 2026Omar Ramadan, Sam Siavoshian, Amir Kashif Saeed +3Constrained Generative ModelingPhysics-Informed Diffusion Models

  25. Evolutionary One-Step Generators: Fast and Diverse Sampling for Discrete Design

    Oct 6, 2026Marcus Vukojevic, Erik Nielsen, Veronica Lachi +2Constrained Generative ModelingGraph Generation