相关论文: When Does Model Collapse Occur in Structured Inter…

Generative agents are rapidly advancing in sophistication, raising urgent questions about how they might coordinate when deployed in online ecosystems. This is particularly consequential in information operations (IOs), influence campaigns…

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance. If we see these implicit…

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance. If we see these implicit…

Generative model-based imitation learning methods have recently achieved strong results in learning high-complexity motor skills from human demonstrations. However, imitation learning of interactive policies that coordinate with humans in…

Generative adversarial networks are generative models that are capable of replicating the implicit probability distribution of the input data with high accuracy. Traditionally, GANs consist of a Generator and a Discriminator which interact…

Despite its success, generative adversarial networks (GANs) still suffer from mode collapse, i.e., the generator can only map latent variables to a partial set of modes in the target distribution. In this paper, we analyze and seek to…

Machine learning has affected the way in which many phenomena for various domains are modelled, one of these domains being that of structural dynamics. However, because machine-learning algorithms are problem-specific, they often fail to…

Recent advances in generative models have made it increasingly difficult to distinguish real data from model-generated synthetic data. Using synthetic data for successive training of future model generations creates "self-consuming loops",…

The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…

Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by…

Generative modeling aims at producing new datapoints whose statistical properties resemble the ones in a training dataset. In recent years, there has been a burst of machine learning techniques and settings that can achieve this goal with…

It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…

As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overlooked in traditional AI risk assessment frameworks. This…

Researchers in empirical machine learning recently spotlighted their fears of so-called Model Collapse. They imagined a discard workflow, where an initial generative model is trained with real data, after which the real data are discarded,…

Large-scale pre-training has recently emerged as a technique for creating capable, general purpose, generative models such as GPT-3, Megatron-Turing NLG, Gopher, and many others. In this paper, we highlight a counterintuitive property of…

The training dynamics of deep neural networks often defy expectations, even as these models form the foundation of modern machine learning. Two prominent examples are grokking, where test performance improves abruptly long after the…

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Foundation models are increasingly trained on synthetic data generated by prior model iterations rather than exclusively on real data. This self-consuming training paradigm can lead to model collapse, divergence, or bias amplification.…

Generative AI models offer powerful capabilities but often lack transparency, making it difficult to interpret their output. This is critical in cases involving artistic or copyrighted content. This work introduces a search-inspired…

The real world is awash with multi-agent problems that require collective action by self-interested agents, from the routing of packets across a computer network to the management of irrigation systems. Such systems have local incentives…