The recent surge in versatile large language models (LLMs) demonstrates remarkable success across a wide range of contexts. A key factor contributing to this success is LLM alignment, in which human preference learning plays a decisive role in steering the models’ capabilities toward fulfilling human objectives. In this survey, we review the progress in human preference learning within a unified framework, aiming to provide a comprehensive perspective on established methodologies while exploring avenues to further advance LLM alignment. Specifically, we categorize human preference feedback based on data sources and formats, summarize techniques for human preference modeling and usage, and present an overview of prevailing evaluation protocols for LLM alignment. Finally, we discuss the existing challenges and identify potential directions for future research, with a particular emphasis on generalizability, transferability, and controllability.

In the next few years, people are called upon to collectively contribute to environmental sustainability, such as mitigating climate change, reducing waste, conserving biodiversity, or promoting sustainable resource management. With this literature review, we are interested in investigating how conversational agents have been used to persuade people toward environmental sustainability behavioral change, and which design features and methods are used in the persuasion process. This field sits at the crossroads of multiple disciplines, including Computer Science, Human-Computer Interaction (HCI), Environmental Science, and Psychology, each contributing unique insights into the design and effectiveness of persuasive conversational agents. The survey proposes a structured report analyzing the current state of the art in persuasive conversational agents for environmental sustainability, considering the multidisciplinary nature of the issue. We explored multiple perspectives, including the conversational agents’ design features, the persuasion strategy adopted, the environmental sustainability issue considered, and the empirical evaluation method (if an empirical study was performed). From the lessons learned, we propose a research agenda to fill the gaps in the field and a checklist to guide future research in persuasive conversational agents applied to environmental sustainability.

Idea and hypothesis generation are creative processes that demand a significant level of reasoning. Methods such as brainstorming, analytical reasoning, inductive reasoning and other forms of reasoning have proven useful in advancing research in this domain. Machine learning techniques have been widely investigated to address these challenging tasks. However, they are limited and have insufficient reasoning required for these tasks, making the emergence of language models reignite research in this direction. Large language models (LLMs) have debuted as the current state-of-the-art for achieving impressive generative tasks, and to support language understanding. Models such as the BERT, BARD, GPT and LLaMa have architectural layouts which are mostly transformer network based. These models headline impressive results in downstream tasks such as text classification, sentiment analysis, language inference, question answering, text summarization and named entity recognition among others. However, the need to adapt these models to the emerging downstream tasks of idea and hypothesis generation have uncovered a new research opportunity. In this study, systematic literature review is carried out to provide understanding on how LLMs have been applied to the classical downstream tasks and to then motivate adaptation of LLMs to idea and hypothesis generation. Furthermore, the study examines techniques applied to customization and knowledge distillation with the aim of contextualizing these methods to solve idea and hypothesis generation. We then explored the limitations of LLM-based research efforts to idea and hypothesis generation. A detailed and technical discussion of the findings of the study is presented, and we provide a high-level novel conceptual framework to describe and summarize our findings. Also, potential insights to combining knowledge graphs, causal inference, logic reasoning and LLMs distillation in idea and hypothesis generation are discussed. Finally, challenges in these research areas on adaptation of LLMs to idea and hypothesis generation are discussed.

Password-authenticated key exchange (PAKE) protocols tackle the important problem of how to enable two parties, who share a low-entropy password, to establish a cryptographically strong session key for secure data communication. Although considerable research efforts have been devoted to designing hundreds of PAKE protocols, to the best of our knowledge, there have been few systematic reviews. In this work, we provide a comprehensive overview of PAKE research. We first propose a list of 13 desirable properties of PAKE protocols in terms of security and usability, enabling PAKE protocols to be systematically rated across a common spectrum. We then provide a taxonomy for PAKE protocols, and classify them into seven types according to their underlying design strategies. For each type, we investigate the inner working mechanisms of various representative protocols, and identify their pros, and cons. We further classify existing PAKE protocols from five other key perspectives (i.e., symmetry, number of participants, hardness assumptions, security goals, and round complexity) and review their development history under each classification, aiming to provide an in-depth and thorough understanding of the status quo of PAKE research. Based on 13 properties and six perspectives, we conduct a large-scale comparative evaluation of 71 representative PAKE protocols in a systematic manner. Finally, we highlight a few potential directions for the future design of PAKE protocols.

Graph neural networks (GNNs) have significantly advanced learning and predictive tasks in many domains like social networks and biology. Given the inherent graph structure of integrated circuits (ICs), GNNs have also shown strong results for various IC-related tasks. Here, we review GNN methodologies across three key areas for ICs: electronic design automation (EDA), reliability, and hardware security. We introduce a comprehensive taxonomy and survey, covering various tasks and their solutions by GNNs in depth. We also outline key challenges like scalability and EDA tool integration. Finally, we present GNN4CIRCUITS, an open-source tool for plug-and-play GNN integration for various IC tasks.

Heterogeneous information networks (HINs) comprise vertices and edges with different types, representing different objects and links, so as to abstract and model the real world more completely and naturally. Rich structural and semantic information contained in HINs provides new opportunities and challenges to discover hidden patterns in HINs. Community Search (CS) over HINs, aiming to find a subgraph that satisfies the given conditions, provides important support for various applications such as team formation, personalized recommendation, fraud detection, group identification, and so on, and many CS approaches have been proposed recently. This study introduces types of HINs, CS constraints, search strategies, proposes a novel taxonomy of CS over HINs, and reviews the CS models as well as solutions over different HINs. It then analyzes and compares the characteristics of different models and solutions, and summarizes evaluation metrics generally used in literature. This survey aims to provide valuable insights on the latest progress of CS over HINs, facilitating researchers conduct in-depth research in this field.

Recent strides in hardware-accelerated ray tracing have propelled algorithms once deemed suitable only for offline rendering, like Monte Carlo path tracing, into interactive frame rates. While path tracing has been regarded as a practical utility in animating scenes for the film industry, achieving visually noise-free imagery often mandates thousands of samples per pixel and considerable computation time. Regrettably, this poses a difficulty for video games and virtual reality applications, which demand high frame rates and resolutions, thereby constraining the computational overhead of path tracing. Two extant approaches, in-process sampling, and post-processing reconstruction methods, i.e., denoising and upsampling, address this challenge. The giant evolution of deep learning technology has emerged as pivotal in path tracing processing. We explore and advance Monte Carlo path tracing technology based on deep learning. Moreover, we illustrate the merits and demerits of diverse designs and technologies, propose potential future development trends, and aim at providing researchers with a comprehensive understanding of the cutting-edge in deep learning-driven Monte Carlo path tracing.

Inspired by the rapid development of Large Language Models (LLMs), LLM agents have evolved to perform complex tasks. LLM agents are now extensively applied across various domains, handling vast amounts of data to interact with humans and execute tasks. The widespread applications of LLM agents demonstrate their significant commercial value; however, they also expose security and privacy vulnerabilities. At the current stage, comprehensive research on the security and privacy of LLM agents is highly needed. This survey aims to provide a comprehensive overview of the newly emerged privacy and security issues faced by LLM agents. We begin by introducing the fundamental knowledge of LLM agents, followed by a categorization and analysis of the threats. We then discuss the impacts of these threats on humans, environment, and other agents. Subsequently, we review existing defensive strategies, and finally explore future trends. Additionally, the survey incorporates diverse case studies to facilitate a more accessible understanding. By highlighting these critical security and privacy issues, the survey seeks to stimulate future research towards enhancing the security and privacy of LLM agents, thereby increasing their reliability and trustworthiness in future applications.

With recent advancements in speech recognition, it is crucial to ensure that automatic speech recognition (ASR) systems do not exhibit systematic biases, such as those related to gender, age, accent, and dialect. Although research has extensively examined systematic biases such as those related to gender, age, accent, and dialect, for high-resource languages, research on low-resource African languages remains limited. This systematic literature review synthesizes evidence on bias evaluation and mitigation in ASR models for African languages, adhering to the PRISMA reporting guidelines. Our analysis reveals that most biases stem from data imbalances and limited linguistic diversity in training datasets, resulting in disproportionately high error rates for underrepresented speaker groups. Mitigation strategies in African contexts have primarily focused on data-centric methods, including dataset expansion, augmentation, and transfer learning. In contrast, more advanced approaches, including fairness-aware modeling, bias-aware loss functions, adversarial debiasing, and speaker-adaptive techniques, are rarely applied. Gender, accent, and dialect biases dominate the few African studies available, while age and racial biases are almost absent. The limited number of African languages covered highlights the urgent need for more representative and inclusive research. Addressing these gaps will support the development of fairer and more robust ASR technologies across the continent.

Salient Object Detection (SOD) focuses on identifying the most noticeable regions in images or videos those that naturally draw human attention. It has become an active area of research in computer vision, with direct applications in tasks such as video summarization, intelligent cropping, image captioning, and visual tracking. Over the past two decades, many efforts have been made to simulate how the human visual system processes and prioritizes visual information. These approaches have evolved from conventional, handcrafted techniques to more recent deep learning-based models. This review aims to provide a clear and structured overview of the progress in deep learning methods for saliency detection. It also summarizes widely used benchmark datasets, evaluation metrics, and key application areas where saliency detection plays an important role.