The paper examines generative models that are trained through self‑consuming loops where users curate preferred samples. It shows that when training relies solely on user‑curated synthetic data, initial biases are amplified, leading the system to converge to a single dominant outcome. Introducing reference data at a sufficient rate changes the dynamics, producing a unique globally attracting equilibrium, and the authors propose an algorithm to select reference distributions and mixing weights to steer the system toward desirable equilibria while reducing data collection costs.
By Xiukun Wei, Tian Xie, Ding Zhu, Xueru Zhang
arXiv:2510. 16657v3 Announce Type: replace-cross Abstract: Synthetic data has been increasingly used to train frontier generative models.
By Bingji Yi, Qiyuan Liu, Yuwei Cheng, Haifeng Xu
arXiv:2512. 15011v3 Announce Type: replace Abstract: Artificial intelligence (AI) increasingly generates the very content used to train future AI systems.
By Damian Hodel, Jevin D. West
arXiv:2602. 16065v2 Announce Type: replace-cross Abstract: As artificial intelligence (AI)-generated content proliferates, models are increasingly trained on their own outputs, risking progressive degradation or collapse.
By Kevin Wang, Hongqian Niu, Didong Li
arXiv:2608.21366v1 Announce Type: new
Abstract: Driven by massive amounts of web-scale data, generative AI (GenAI) has achieved remarkable progress, enabling various applications in diverse sectors....
By Xihao Xie, Beichen Hu
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.
By Hengzhi He, Shirong Xu, Guang Cheng
arXiv:2410. 12341v4 Announce Type: replace-cross Abstract: As AI-generated content increasingly populates the web, generative AI models are at growing risk of being trained on their own outputs, a process known as AI autophagy.
By Daniele Gambetta, Gizem Gezici, Fosca Giannotti, Dino Pedreschi, Alistair Knott, Luca Pappalardo
The paper introduces a generative graph model that combines mechanistic interpretability with amortized inference by formulating both the generative process and parameter recovery in function space. It extends step graphons to a multifractal construction, enabling a neural inverse operator that can infer parameters for unseen graph sizes. Experiments show the model outperforms a pretrained graph foundation model on zero‑shot generation and matches instance‑specific methods on single‑observation networks, while also sensitively tracking brain state changes in an EEG study.
By Wooseong Choi, Italo'Ivo Lima Dias Pinto, Chen Sun, Gaurav Gupta, Dong Song, Paul Bogdan
arXiv:2606. 05264v1 Announce Type: new Abstract: Training robust multivariate time series forecasting models requires large, diverse corpora, yet many real-world domains provide only a handful of observed sequences.
By Moulik Gupta (Birla AI Labs), Dhruv Kumar (Birla AI Labs, Birla Institute of Technology and Science, Pilani), Murari Mandal (Birla AI Labs, Kalinga Institute of Industrial Technology), Saurabh Deshpande (Birla AI Labs)
arXiv:2603. 14147v2 Announce Type: replace Abstract: The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability.
By Margarita Belova, Yuval Kansal, Yihao Liang, Jiaxin Xiao, Niraj K. Jha
The paper introduces xVGAE, a hierarchical variational graph autoencoder designed for exchangeable graphs. Leveraging the Aldous-Hoover theorem, the model uses a graph-level latent variable, exchangeable node-specific latent variables, and a graphon function to learn and generate graph distributions efficiently. Experiments demonstrate that xVGAE produces high-quality graphs quickly while capturing key structural properties of the training data.
By Daniele Micheletti, Federica Zoe Ricci, Erik B. Sudderth
How can an agent build a structured map of its world from nothing but an ongoing sequence of raw sensory input and its own movements, especially when natural variation means exact sensory patterns rarely repeat? The Clone-Structured Causal Graph algorithm (CSCG), a normative hippocampus model, shows how an interpretable map can be learned from aliased observations.