Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation

Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence

arXiv:2510. 16657v3 Announce Type: replace-cross Abstract: Synthetic data has been increasingly used to train frontier generative models.

On Forgetting and Stability of Score-based Generative models

arXiv:2601. 21868v2 Announce Type: replace-cross Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning.

FFJORD: Free-form continuous dynamics for scalable reversible generative models

Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework

arXiv:2502. 18049v5 Announce Type: replace-cross Abstract: Recent studies identified an intriguing phenomenon in recursive generative model training known as model collapse, where models trained on data generated by previous models exhibit severe performance degradation.

Self-Consistent Generative Paths via Admissible Random Variational Transport

arXiv:2606. 08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map.

Unifying Generative Models with Path Integrals

arXiv:2608. 12438v1 Announce Type: new Abstract: We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for a single master action.

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences

arXiv:2605. 07724v2 Announce Type: replace-cross Abstract: Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal, the model tends to collapse onto a narrow set of outputs that over-optimize that objective.

Retraining Seeks Stable Signals

arXiv:2607. 15623v1 Announce Type: cross Abstract: Predictive models deployed at scale influence future data, a phenomenon called performativity.

Midpoint Generative Models

arXiv:2605. 29920v2 Announce Type: replace Abstract: We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models.

Second Order Drifting Models

arXiv:2608. 07924v1 Announce Type: cross Abstract: Drifting models are a recent class of one-step generative models that evolve the model distribution during training using a predefined sample-based drift field.

Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle

arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.

Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes

arXiv:2608. 15867v1 Announce Type: cross Abstract: Synthetic populations are critical inputs for activity-based travel demand models, yet generating realistic populations from limited survey data remains challenging.