Abstract--Visual diffusion models have revolutionized the field of creative AI, producing high-quality and diverse content. However, they inevitably memorize training images or videos, subsequently replicating their concepts, content, or styles during inference. In this survey, we provide the first comprehensive review of replication in visual diffusion models, marking a novel contribution to the field by systematically categorizing the existing studies into unveiling, understanding, and mitigating this phenomenon. Specifically, unveiling mainly refers to the methods used to detect replication instances. Understanding involves analyzing the underlying mechanisms and factors that contribute to this phenomenon. Mitigation focuses on developing strategies to reduce or eliminate replication. Beyond these aspects, we also review papers focusing on its real-world influence. For instance, in the context of healthcare, replication is critically worrying due to privacy concerns related to patient data. Finally, the paper concludes with a discussion of the ongoing challenges, such as the difficulty in detecting and benchmarking replication, and outlines future directions including the development of more robust mitigation techniques. By synthesizing insights from diverse studies, this paper aims to equip researchers and practitioners with a deeper understanding at the intersection between AI technology and social good. Compared to traditional Generative Adversarial Networks (GAN) [3] and Variational Autoencoders (VAE) [4], visual diffusion models excel in producing high-quality, diverse, and stable images.

AI Infrastructure plays a key role in the speed and cost-competitiveness of developing and deploying advanced AI models. The current demand for powerful AI infrastructure for model training is driven by the emergence of generative AI and foundational models, where on occasion thousands of GPUs must cooperate on a single training job for the model to be trained in a reasonable time. Delivering efficient and high-performing AI training requires an end-to-end solution that combines hardware, software and holistic telemetry to cater for multiple types of AI workloads. In this report, we describe IBM's hybrid cloud infrastructure that powers our generative AI model development. This infrastructure includes (1) Vela: an AI-optimized supercomputing capability directly integrated into the IBM Cloud, delivering scalable, dynamic, multi-tenant and geographically distributed infrastructure for large-scale model training and other AI workflow steps and (2) Blue Vela: a large-scale, purpose-built, on-premises hosting environment that is optimized to support our largest and most ambitious AI model training tasks. Vela provides IBM with the dual benefit of high performance for internal use along with the flexibility to adapt to an evolving commercial landscape. Blue Vela provides us with the benefits of rapid development of our largest and most ambitious models, as well as future-proofing against the evolving model landscape in the industry. Taken together, they provide IBM with the ability to rapidly innovate in the development of both AI models and commercial offerings.

The widespread use of generative AI systems is coupled with significant ethical and social challenges. As a result, policymakers, academic researchers, and social advocacy groups have all called for such systems to be audited. However, existing auditing procedures fail to address the governance challenges posed by generative AI systems, which display emergent capabilities and are adaptable to a wide range of downstream tasks. In this chapter, we address that gap by outlining a novel blueprint for how to audit such systems. Specifically, we propose a three-layered approach, whereby governance audits (of technology providers that design and disseminate generative AI systems), model audits (of generative AI systems after pre-training but prior to their release), and application audits (of applications based on top of generative AI systems) complement and inform each other. We show how audits on these three levels, when conducted in a structured and coordinated manner, can be a feasible and effective mechanism for identifying and managing some of the ethical and social risks posed by generative AI systems. That said, it is important to remain realistic about what auditing can reasonably be expected to achieve. For this reason, the chapter also discusses the limitations not only of our three-layered approach but also of the prospect of auditing generative AI systems at all. Ultimately, this chapter seeks to expand the methodological toolkit available to technology providers and policymakers who wish to analyse and evaluate generative AI systems from technical, ethical, and legal perspectives.

Human culture relies on collective innovation: our ability to continuously explore how existing elements in our environment can be combined to create new ones. Language is hypothesized to play a key role in human culture, driving individual cognitive capacities and shaping communication. Yet the majority of models of collective innovation assign no cognitive capacities or language abilities to agents. Here, we contribute a computational study of collective innovation where agents are Large Language Models (LLMs) that play Little Alchemy 2, a creative video game originally developed for humans that, as we argue, captures useful aspects of innovation landscapes not present in previous test-beds. We, first, study an LLM in isolation and discover that it exhibits both useful skills and crucial limitations. We, then, study groups of LLMs that share information related to their behaviour and focus on the effect of social connectivity on collective performance. In agreement with previous human and computational studies, we observe that groups with dynamic connectivity out-compete fully-connected groups. Our work reveals opportunities and challenges for future studies of collective innovation that are becoming increasingly relevant as Generative Artificial Intelligence algorithms and humans innovate alongside each other.

Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models. This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective: specific and technical. In this survey, we explore the background and motivation for the identified harms and risks in the context of LLMs being generative language models; our survey differentiates by emphasising the need for unified theories of the distinct safety challenges in the research development and applications of LLMs. We start our discussion with a concise introduction to the workings of LLMs, supported by relevant literature. Then we discuss earlier research that has pointed out the fundamental constraints of generative models, or lack of understanding thereof (e.g., performance and safety trade-offs as LLMs scale in number of parameters). We provide a sufficient coverage of LLM alignment -- delving into various approaches, contending methods and present challenges associated with aligning LLMs with human preferences. By highlighting the gaps in the literature and possible implementation oversights, our aim is to create a comprehensive analysis that provides insights for addressing AI safety in LLMs and encourages the development of aligned and secure models. We conclude our survey by discussing future directions of LLMs for AI safety, offering insights into ongoing research in this critical area.

Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. However, it is unclear whether these LLM-based evaluators can be applied in real-world classrooms to assess student assignments. This empirical report shares how we use GPT-4 as an automatic assignment evaluator in a university course with 1,028 students. Based on student responses, we find that LLM-based assignment evaluators are generally acceptable to students when students have free access to these LLM-based evaluators. However, students also noted that the LLM sometimes fails to adhere to the evaluation instructions. Additionally, we observe that students can easily manipulate the LLM-based evaluator to output specific strings, allowing them to achieve high scores without meeting the assignment rubric. Based on student feedback and our experience, we provide several recommendations for integrating LLM-based evaluators into future classrooms.

Perhaps unsurprisingly, July 4th was a quiet day for news, but we've still got editorials on e-ink writing, the most-delayed video game ever and more bad news from the makers of ChatGPT. Earlier this week, engineer and Swift developer Pedro José Pereira Vieito dug into OpenAI's Mac ChatGPT app and found that it was storing user conversations locally in plain text, rather than encrypting them. Because that app is only available from OpenAI's website, and since it's not available on the App Store, it doesn't have to follow Apple's sandboxing requirements. OpenAI released an update that added encryption to locally stored chats. Then, more bad news stemmed from issues in 2023. Last spring, a hacker obtained information about OpenAI after illicitly accessing the company's internal messaging systems.

Companies in Japan lag behind those in the United States and Europe in the use of generative artificial intelligence, a government white paper showed Friday. The white paper said that 46.8% of companies in Japan use generative AI in their operations, compared with 84.7% in the U.S. and 72.7% in Germany. Japanese companies' use of generative AI has been limited to taking meeting minutes and creating emails and documents. In contrast, firms in the U.S. and Europe use the technology in a wider range of operations, including for customer services, the white paper said. Including companies that use generative AI on a trial basis, the proportion of those using the technology stands at about 70% in Japan, lower than over 90% in both the U.S. and Germany.

An ensemble post-processing method is developed to improve the probabilistic forecasts of extreme precipitation events across the conterminous United States (CONUS). The method combines a 3-D Vision Transformer (ViT) for bias correction with a Latent Diffusion Model (LDM), a generative Artificial Intelligence (AI) method, to post-process 6-hourly precipitation ensemble forecasts and produce an enlarged generative ensemble that contains spatiotemporally consistent precipitation trajectories. These trajectories are expected to improve the characterization of extreme precipitation events and offer skillful multi-day accumulated and 6-hourly precipitation guidance. The method is tested using the Global Ensemble Forecast System (GEFS) precipitation forecasts out to day 6 and is verified against the Climate-Calibrated Precipitation Analysis (CCPA) data. Verification results indicate that the method generated skillful ensemble members with improved Continuous Ranked Probabilistic Skill Scores (CRPSSs) and Brier Skill Scores (BSSs) over the raw operational GEFS and a multivariate statistical post-processing baseline. It showed skillful and reliable probabilities for events at extreme precipitation thresholds. Explainability studies were further conducted, which revealed the decision-making process of the method and confirmed its effectiveness on ensemble member generation. This work introduces a novel, generative-AI-based approach to address the limitation of small numerical ensembles and the need for larger ensembles to identify extreme precipitation events.

The rapid growth of the Internet, driven by social media, web browsing, and video streaming, has made images central to the Web experience, resulting in significant data transfer and increased webpage sizes. Traditional image compression methods, while reducing bandwidth, often degrade image quality. This paper explores a novel approach using generative AI to reconstruct images at the edge or client-side. We develop a framework that leverages text prompts and provides additional conditioning inputs like Canny edges and color palettes to a text-to-image model, achieving up to 99.8% bandwidth savings in the best cases and 92.6% on average, while maintaining high perceptual similarity. Empirical analysis and a user study show that our method preserves image meaning and structure more effectively than traditional compression methods, offering a promising solution for reducing bandwidth usage and improving Internet affordability with minimal degradation in image quality.