Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such as large language models (LLMs) and diffusion models, have shown remarkable capabilities (e.g., in-context learning, code-completion, and text-to-image generation and editing). However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks. This paper reports the findings of a workshop held at Google (co-organized by Stanford University and the University of Wisconsin-Madison) on the dual-use dilemma posed by GenAI. This paper is not meant to be comprehensive, but is rather an attempt to synthesize some of the interesting findings from the workshop. We discuss short-term and long-term goals for the community on this topic. We hope this paper provides both a launching point for a discussion on this important topic as well as interesting problems that the research community can work to address.

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, educations, natural and social sciences, agent applications, and other areas. Secondly, we answer the `where' and `how' questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that evaluation should be treated as an essential discipline to better assist the development of LLMs. We consistently maintain the related open-source materials at: https://github.com/MLGroupJLU/LLM-eval-survey.

The emerging field of Graph Signal Processing (GSP) aims to bridge the gap between signal processing and spectral graph theory. One of the objectives is to generalize fundamental analysis operations from regular grid signals to irregular structures in the form of graphs. There is an abundant literature on GSP, in particular we refer the reader to Shuman et al. (2013) and Ortega et al. (2018) for an introduction to this field and an overview of recent developments, challenges and applications. GSP has also given rise to numerous applications in machine/deep learning: convolutional neural networks (CNN) on graphs Bruna et al. (2014), Henaff et al. (2015), Defferrard et al. (2016), semi-supervised classification with graph CNN Kipf and Welling (2017), Hamilton et al. (2017), community detection Tremblay and Borgnat (2014), to name just a few. Different software programs exist for processing signals on graphs, in different languages. The Graph Signal Processing toolbox (GSPbox) is an easy to use matlab toolbox that performs a wide variety of operations on graphs. This toolbox was port to Python as the PyGSP Perraudin et al. (2014). There is also another matlab toolbox the Spectral Graph Wavelet Transform (SGWT) toolbox dedicated to the implementation of the SGWT developed in Hammond et al. (2011). However, to our knowledge, there are not yet any tools dedicated to GSP in R. A development version of the gasper package is currently available online

Special-purpose Autonomous Underwater Vehicles (AUVs) are utilised for benthic (seafloor) surveys, where the vehicle collects optical imagery of the seafloor. Due to the small-sensor footprint of the cameras and the vast areas to be surveyed, these AUVs can not feasibly collect full coverage imagery of areas larger than a few tens of thousands of square meters. Therefore it is necessary for AUV paths to sample the surveys areas sparsely, yet effectively. Broad-scale acoustic bathymetric data is readily available over large areas, and is often a useful prior of seafloor cover. As such, prior bathymetry can be used to guide AUV data collection. This research proposes methods for planning initial AUV surveys that efficiently explore a feature space representation of the bathymetry, in order to sample from a diverse set of bathymetric terrain. This will enable the AUV to visit areas that likely contain unique habitats and are representative of the entire survey site. We propose several information gathering planners that utilise a feature space exploration reward, to plan freeform paths or to optimise the placement of a survey template. The suitability of these methods to plan AUV surveys is evaluated based on the coverage of the feature space and also the ability to visit all classes of benthic habitat on the initial dive. Informative planners based on Rapidly-expanding Random Trees (RRT) and Monte-Carlo Tree Search (MCTS) were found to be the most effective. This is a valuable tool for AUV surveys as it increases the utility of initial dives. It also delivers a comprehensive training set to learn a relationship between acoustic bathymetry and visually-derived seafloor classifications.

Recent years have witnessed significant progress in a variety of emerging areas including meta-learning and fine-tuning [11, 52], automated hyperparameter optimization [13, 10], reinforcement learning [31, 21], fair batch selection in machine learning [54], adversarial learning [76, 40], AI-aware communication networks [27], fairness-aware federated learning [75], etc. These problems share a common nested optimization structure, and have inspired intensive study on the theory and algorithmic development of bilevel optimization. Prior efforts have been taken mainly on the single-machine scenario. However, in modern machine learning applications, data privacy has emerged as a critical concern in centralized training, and the data often exhibit an inherently distributed nature [70]. This highlights the importance of recent research and attention on federated bilevel optimization, and has inspired many emerging applications including but not limited to federated meta-learning [9], hyperparameter tuning for federated learning [25], resource allocation over communication networks [27] and graph-aided federated learning [71], adversarial robustness on edge computing [46], etc.

Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of machine learning systems in the real world. Great progress has been made over the past years. This paper presents the first review of recent advances in OOD detection with a particular focus on natural language processing approaches. First, we provide a formal definition of OOD detection and discuss several related fields. We then categorize recent algorithms into three classes according to the data they used: (1) OOD data available, (2) OOD data unavailable + in-distribution (ID) label available, and (3) OOD data unavailable + ID label unavailable. Third, we introduce datasets, applications, and metrics. Finally, we summarize existing work and present potential future research topics.

Online education platforms, leveraging the internet to distribute education resources, seek to provide convenient education but often fall short in real-time communication with students. They often struggle to offer personalized education resources due to the challenge of addressing the diverse obstacles students encounter throughout their learning journey. Recently, the emergence of large language models (LLMs), such as ChatGPT, offers the possibility for resolving this issue by comprehending individual requests. Although LLMs have been successful in various fields, creating an LLM-based education system is still challenging for the wide range of educational skills required. This paper reviews the recently emerged LLM researches related to educational capabilities, including mathematics, writing, programming, reasoning, and knowledge-based question answering, with the aim to explore their potential in constructing the next-generation intelligent education system. Based on the current development status, we further outline two approaches for an LLM-based education system: a unified approach and a mixture-of-expert (MoE) approach. Finally, we explore the challenges and future directions, providing new research opportunities and perspectives on adapting LLMs for education.

The exponential growth of digital content has generated massive textual datasets, necessitating advanced analytical approaches. Large Language Models (LLMs) have emerged as tools capable of processing and extracting insights from massive unstructured textual datasets. However, how to leverage LLMs for text-based Information Systems (IS) research is currently unclear. To assist IS research in understanding how to operationalize LLMs, we propose a Text Analytics for Information Systems Research (TAISR) framework. Our proposed framework provides detailed recommendations grounded in IS and LLM literature on how to conduct meaningful text-based IS research. We conducted three case studies in business intelligence using our TAISR framework to demonstrate its application across several IS research contexts. We also outline potential challenges and limitations in adopting LLMs for IS. By offering a systematic approach and evidence of its utility, our TAISR framework contributes to future IS research streams looking to incorporate powerful LLMs for text analytics.

In the field of Prognostics and Health Management (PHM), recent years have witnessed a significant surge in the application of machine learning (ML). Despite this growth, the field grapples with a lack of unified guidelines and systematic approaches for effectively implementing these ML techniques and comprehensive analysis regarding industrial open-source data across varied scenarios. To address these gaps, this paper provides a comprehensive review of machine learning approaches for diagnostics and prognostics of industrial systems using open-source datasets from PHM Data Challenge Competitions held between 2018 and 2023 by PHM Society and IEEE Reliability Society and summarizes a unified ML framework. This review systematically categorizes and scrutinizes the problems, challenges, methodologies, and advancements demonstrated in these competitions, highlighting the evolving role of both conventional machine learning and deep learning in tackling complex industrial tasks related to detection, diagnosis, assessment, and prognosis. Moreover, this paper delves into the common challenges in PHM data challenge competitions by emphasizing both data-related and model-related issues and summarizes the solutions that have been employed to address these challenges. Finally, we identify key themes and potential directions for future research, providing opportunities and prospects for ML further development in PHM.

Global visual localization in LiDAR-maps, crucial for autonomous driving applications, remains largely unexplored due to the challenging issue of bridging the cross-modal heterogeneity gap. Popular multi-modal learning approach Contrastive Language-Image Pre-Training (CLIP) has popularized contrastive symmetric loss using batch construction technique by applying it to multi-modal domains of text and image. We apply this approach to the domains of 2D image and 3D LiDAR points on the task of cross-modal localization. Our method is explained as follows: A batch of N (image, LiDAR) pairs is constructed so as to predict what is the right match between N X N possible pairings across the batch by jointly training an image encoder and LiDAR encoder to learn a multi-modal embedding space. In this way, the cosine similarity between N positive pairings is maximized, whereas that between the remaining negative pairings is minimized. Finally, over the obtained similarity scores, a symmetric cross-entropy loss is optimized. To the best of our knowledge, this is the first work to apply batched loss approach to a cross-modal setting of image & LiDAR data and also to show Zero-shot transfer in a visual localization setting. We conduct extensive analyses on standard autonomous driving datasets such as KITTI and KITTI-360 datasets. Our method outperforms state-of-the-art recall@1 accuracy on the KITTI-360 dataset by 22.4%, using only perspective images, in contrast to the state-of-the-art approach, which utilizes the more informative fisheye images. Additionally, this superior performance is achieved without resorting to complex architectures. Moreover, we demonstrate the zero-shot capabilities of our model and we beat SOTA by 8% without even training on it. Furthermore, we establish the first benchmark for cross-modal localization on the KITTI dataset.