Reward models (RMs) play a critical role in enhancing the reasoning performance of LLMs. For example, they can provide training signals to finetune LLMs during reinforcement learning (RL) and help select the best answer from multiple candidates during inference. In this paper, we provide a systematic introduction to RMs, along with a comprehensive survey of their applications in LLM reasoning. We first review fundamental concepts of RMs, including their architectures, training methodologies, and evaluation techniques. Then, we explore their key applications: (1) guiding generation and selecting optimal outputs during LLM inference, (2) facilitating data synthesis and iterative self-improvement for LLMs, and (3) providing training signals in RL-based finetuning. Finally, we discuss critical open questions regarding the selection, generalization, evaluation, and enhancement of RMs, based on existing research and our own empirical findings. Our analysis aims to provide actionable insights for the effective deployment and advancement of RMs for LLM reasoning.

Pun generation seeks to creatively modify linguistic elements in text to produce humour or evoke double meanings. It also aims to preserve coherence and contextual appropriateness, making it useful in creative writing and entertainment across various media and contexts. Although pun generation has received considerable attention in computational linguistics, there is currently no dedicated survey that systematically reviews this specific area. To bridge this gap, this paper provides a comprehensive review of pun generation datasets and methods across different stages, including conventional approaches, deep learning techniques, and pre-trained language models. Additionally, we summarise both automated and human evaluation metrics used to assess the quality of pun generation. Finally, we discuss the research challenges and propose promising directions for future work.

Artificial Intelligence (AI) technology epitomizes the complex challenges posed by human-made artifacts, particularly those widely integrated into society and exerting significant influence, highlighting potential benefits and their negative consequences. While other technologies may also pose substantial risks, AI's pervasive reach makes its societal effects especially profound. The complexity of AI systems, coupled with their remarkable capabilities, can lead to a reliance on technologies that operate beyond direct human oversight or understanding. To mitigate the risks that arise, several theoretical tools and guidelines have been developed, alongside efforts to create technological tools aimed at safeguarding Trustworthy AI. The guidelines take a more holistic view of the issue but fail to provide techniques for quantifying trustworthiness. Conversely, while technological tools are better at achieving such quantification, they lack a holistic perspective, focusing instead on specific aspects of Trustworthy AI. This paper aims to introduce an assessment method that combines the ethical components of Trustworthy AI with the algorithmic processes of PageRank and TrustRank. The goal is to establish an assessment framework that minimizes the subjectivity inherent in the self-assessment techniques prevalent in the field by introducing algorithmic criteria. The application of our approach indicates that a holistic assessment of an AI system's trustworthiness can be achieved by providing quantitative insights while considering the theoretical content of relevant guidelines.

Recent advancements in deep learning have significantly impacted the field of speech signal processing, particularly in the analysis and manipulation of complex spectrograms. This survey provides a comprehensive overview of the state-of-the-art techniques leveraging deep neural networks for processing complex spectrograms, which encapsulate both magnitude and phase information. We begin by introducing complex spectrograms and their associated features for various speech processing tasks. Next, we examine the key components and architectures of complex-valued neural networks, which are specifically designed to handle complex-valued data and have been applied to complex spectrogram processing. As recent studies have primarily focused on applying real-valued neural networks to complex spectrograms, we revisit these approaches and their architectural designs. We then discuss various training strategies and loss functions tailored for training neural networks to process and model complex spectrograms. The survey further examines key applications, including phase retrieval, speech enhancement, and speaker separation, where deep learning has achieved significant progress by leveraging complex spectrograms or their derived feature representations. Additionally, we examine the intersection of complex spectrograms with generative models. This survey aims to serve as a valuable resource for researchers and practitioners in the field of speech signal processing, deep learning and related fields.

Recent advancements in self-improvement for Large Language Models (LLMs) have efficiently enhanced model capabilities without significantly increasing costs, particularly in terms of human effort. While this area is still relatively young, its extension to the multimodal domain holds immense potential for leveraging diverse data sources and developing more general self-improving models. This survey is the first to provide a comprehensive overview of self-improvement in Multimodal LLMs (MLLMs). We provide a structured overview of the current literature and discuss methods from three perspectives: 1) data collection, 2) data organization, and 3) model optimization, to facilitate the further development of self-improvement in MLLMs. We also include commonly used evaluations and downstream applications. Finally, we conclude by outlining open challenges and future research directions.

Artificial Intelligence (AI) systems introduce unprecedented privacy challenges as they process increasingly sensitive data. Traditional privacy frameworks prove inadequate for AI technologies due to unique characteristics such as autonomous learning and black-box decision-making. This paper presents a taxonomy classifying AI privacy risks, synthesised from 45 studies identified through systematic review. We identify 19 key risks grouped under four categories: Dataset-Level, Model-Level, Infrastructure-Level, and Insider Threat Risks. Findings reveal a balanced distribution across these dimensions, with human error (9.45%) emerging as the most significant factor. This taxonomy challenges conventional security approaches that typically prioritise technical controls over human factors, highlighting gaps in holistic understanding. By bridging technical and behavioural dimensions of AI privacy, this paper contributes to advancing trustworthy AI development and provides a foundation for future research.

Network intrusion detection, a well-explored cybersecurity field, has predominantly relied on supervised learning algorithms in the past two decades. However, their limitations in detecting only known anomalies prompt the exploration of alternative approaches. Motivated by the success of self-supervised learning in computer vision, there is a rising interest in adapting this paradigm for network intrusion detection. While prior research mainly delved into contrastive self-supervised methods, the efficacy of non-contrastive methods, in conjunction with encoder architectures serving as the representation learning backbone and augmentation strategies that determine what is learned, remains unclear for effective attack detection. This paper compares the performance of five non-contrastive self-supervised learning methods using three encoder architectures and six augmentation strategies. Ninety experiments are systematically conducted on two network intrusion detection datasets, UNSW-NB15 and 5G-NIDD. For each self-supervised model, the combination of encoder architecture and augmentation method yielding the highest average precision, recall, F1-score, and AUCROC is reported.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes a simple latent factor model for one-shot learning with continuous outputs where very few observations are available. Specifically, it derives risk approximations in an asymptotic regime where the number of training examples is fixed and the number of features in the X space diverges. Based on principal component regression (PCR) estimator, two estimators including the bias-corrected estimator and the so-called oracle estimator are proposed and the bounds for the risks of these estimators are derived. These bounds provide insights into the significance of various parameters relevant to one-shot learning.

We consider the simplest possible case that still allows for nonlinear dynamics.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper develops a model for multifurcating trees with edge lengths and observed data at the tree leaves; the model is based on the beta coalescent from the probability literature. The authors develop an MCMC inference scheme for their model, in which they draw on existing work that uses belief propagation to perform inference for the Kingman coalescent (an edge case of the beta coalescent in which all trees are binary). The particular challenge for inference here is that there are many more possible parent-child node relationships when parents can have multiple children (not just two). The authors seem to use a Dirichlet Process mixture model (DPMM) at each node to narrow down the space of possible children subsets to consider. As the authors note, even inference with the Kingman coalescent is a hard problem. In experiments, they compare to the Kingman coalescent and hierarchical agglomerative clustering. The Kingman coalescent is a popular modeling tool, so it is great to see a practical extension of the Kingman coalescent to the multifurcating case being explored for inference.