User-generated content (UGC) communities, especially those featuring multimodal content, improve user experiences by integrating visual and textual information into results (or items). The challenge of improving user experiences in complex systems with search and recommendation (S\&R) services has drawn significant attention from both academia and industry these years. However, the lack of high-quality datasets has limited the research progress on multimodal S\&R. To address the growing need for developing better S\&R services, we present a novel multimodal information retrieval dataset in this paper, namely Qilin. The dataset is collected from Xiaohongshu, a popular social platform with over 300 million monthly active users and an average search penetration rate of over 70\%. In contrast to existing datasets, \textsf{Qilin} offers a comprehensive collection of user sessions with heterogeneous results like image-text notes, video notes, commercial notes, and direct answers, facilitating the development of advanced multimodal neural retrieval models across diverse task settings. To better model user satisfaction and support the analysis of heterogeneous user behaviors, we also collect extensive APP-level contextual signals and genuine user feedback. Notably, Qilin contains user-favored answers and their referred results for search requests triggering the Deep Query Answering (DQA) module. This allows not only the training \& evaluation of a Retrieval-augmented Generation (RAG) pipeline, but also the exploration of how such a module would affect users' search behavior. Through comprehensive analysis and experiments, we provide interesting findings and insights for further improving S\&R systems. We hope that \textsf{Qilin} will significantly contribute to the advancement of multimodal content platforms with S\&R services in the future.

This paper aims to present new alarming trends in the field of child sexual abuse through imagery, as part of SafeLine's research activities in the field of cybercrime, child sexual abuse material and the protection of children's rights to safe online experiences. It focuses primarily on the phenomenon of AI-generated CSAM, sophisticated ways employed for its production which are discussed in dark web forums and the crucial role that the open-source AI models play in the evolution of this overwhelming phenomenon. The paper's main contribution is a correlation analysis between the hotline's reports and domain names identified in dark web forums, where users' discussions focus on exchanging information specifically related to the generation of AI-CSAM. The objective was to reveal the close connection of clear net and dark web content, which was accomplished through the use of the ATLAS dataset of the Voyager system. Furthermore, through the analysis of a set of posts' content drilled from the above dataset, valuable conclusions on forum members' techniques employed for the production of AI-generated CSAM are also drawn, while users' views on this type of content and routes followed in order to overcome technological barriers set with the aim of preventing malicious purposes are also presented. As the ultimate contribution of this research, an overview of the current legislative developments in all country members of the INHOPE organization and the issues arising in the process of regulating the AI- CSAM is presented, shedding light in the legal challenges regarding the regulation and limitation of the phenomenon.

Processing long contexts has become a critical capability for modern large language models (LLMs). However, serving long-context LLMs comes with significant inference costs due to the high memory overhead of the key-value (KV) cache. Existing work leverages dynamic sparse attention algorithms (DSAes) to mitigate the KV cache overhead, but these algorithms rely on top-$k$ KV cache selection, which results in a trade-off between accuracy and efficiency. A larger $k$ improves accuracy but decreases efficiency, while a smaller $k$ boosts efficiency but compromises accuracy. To overcome this trade-off, this paper presents PSA, a $\underline{P}$rogressive $\underline{S}$parse $\underline{A}$ttention mechanism that integrates algorithmic innovations with system co-design to achieve both high inference accuracy and improved efficiency in LLM serving. The PSA algorithm adaptively adjusts the KV cache budget of different tokens and layers according to their real attention weight distributions, rather than relying on a fixed budget $k$. This enables high accuracy while minimizing KV cache usage. To further enhance execution efficiency, we introduce a pipelined iteration scheme that reduces CPU-GPU interleaving and synchronization overhead during PSA computation. Additionally, we implement unified GPU memory management that optimizes PSA's memory utilization by accounting for uneven memory requirements across different model layers. Extensive experimental results demonstrate that PSA reduces KV cache usage for attention computation by up to 2.4$\times$ and 8.8$\times$, and increases end-to-end serving throughput by up to 1.4$\times$ and 2.0$\times$, compared to state-of-the-art DSAes and systems without sparse attention, respectively.

Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. However, most RM research is centered on English and relies heavily on synthetic resources, which leads to limited and less reliable datasets and benchmarks for Chinese. To address this gap, we introduce CheemsBench, a fully human-annotated RM evaluation benchmark within Chinese contexts, and CheemsPreference, a large-scale and diverse preference dataset annotated through human-machine collaboration to support Chinese RM training. We systematically evaluate open-source discriminative and generative RMs on CheemsBench and observe significant limitations in their ability to capture human preferences in Chinese scenarios. Additionally, based on CheemsPreference, we construct an RM that achieves state-of-the-art performance on CheemsBench, demonstrating the necessity of human supervision in RM training. Our findings reveal that scaled AI-generated data struggles to fully capture human preferences, emphasizing the importance of high-quality human supervision in RM development.

Laplacian matrices are commonly employed in many real applications, encoding the underlying latent structural information such as graphs and manifolds. The use of the normalization terms naturally gives rise to random matrices with dependency. It is well-known that dependency is a major bottleneck of new random matrix theory (RMT) developments. To this end, in this paper, we formally introduce a class of generalized (and regularized) Laplacian matrices, which contains the Laplacian matrix and the random adjacency matrix as a specific case, and suggest the new framework of the asymptotic theory of eigenvectors for latent embeddings with generalized Laplacian matrices (ATE-GL). Our new theory is empowered by the tool of generalized quadratic vector equation for dealing with RMT under dependency, and delicate high-order asymptotic expansions of the empirical spiked eigenvectors and eigenvalues based on local laws. The asymptotic normalities established for both spiked eigenvectors and eigenvalues will enable us to conduct precise inference and uncertainty quantification for applications involving the generalized Laplacian matrices with flexibility. We discuss some applications of the suggested ATE-GL framework and showcase its validity through some numerical examples.

Despite the rising prevalence of neural language models, recent empirical evidence suggests their deficiency in compositional generalization. One of the current de-facto solutions to this problem is compositional data augmentation, which aims to introduce additional compositional inductive bias. However, existing handcrafted augmentation strategies offer limited improvement when systematic generalization of neural language models requires multi-grained compositional bias (i.e., not limited to either lexical or structural biases alone) or when training sentences have an imbalanced difficulty distribution. To address these challenges, we first propose a novel compositional augmentation strategy called Component Substitution (CompSub), which enables multi-grained composition of substantial substructures across the entire training set. Furthermore, we introduce the Learning Component Substitution (LCS) framework. This framework empowers the learning of component substitution probabilities in CompSub in an end-to-end manner by maximizing the loss of neural language models, thereby prioritizing challenging compositions with elusive concepts and novel contexts. We extend the key ideas of CompSub and LCS to the recently emerging in-context learning scenarios of pre-trained large language models (LLMs), proposing the LCS-ICL algorithm to enhance the few-shot compositional generalization of state-of-the-art (SOTA) LLMs. Theoretically, we provide insights into why applying our algorithms to language models can improve compositional generalization performance. Empirically, our results on four standard compositional generalization benchmarks(SCAN, COGS, GeoQuery, and COGS-QL) demonstrate the superiority of CompSub, LCS, and LCS-ICL, with improvements of up to 66.5%, 10.3%, 1.4%, and 8.8%, respectively.

A surrogate model for particle-in-cell plasma simulations based on a graph neural network is presented. The graph is constructed in such a way as to enable the representation of electromagnetic fields on a fixed spatial grid. The model is applied to simulate beams of electrons in one dimension over a wide range of temperatures, drift momenta and densities, and is shown to reproduce two-stream instabilities - a common and fundamental plasma instability. Qualitatively, the characteristic phase-space mixing of counterpropagating electron beams is observed. Quantitatively, the model's performance is evaluated in terms of the accuracy of its predictions of number density distributions, the electric field, and their Fourier decompositions, particularly the growth rate of the fastest-growing unstable mode, as well as particle position, momentum distributions, energy conservation and run time. The model achieves high accuracy with a time step longer than conventional simulation by two orders of magnitude. This work demonstrates that complex plasma dynamics can be learned and shows promise for the development of fast differentiable simulators suitable for solving forward and inverse problems in plasma physics.

ABSTRACT Natural gas (NG) is relatively a clean source of energy, particularly compared to fossil fuels, and worldwide consumption of NG has been increasing almost linearly in the last two decades. A similar trend can also be seen in Turkey, while another similarity is the high dependence on impor ts for the continuous NG supply. It is crucial to accurately forecast future NG demand (NGD) in Turkey, especially, for import contracts; in this respect, forecasts of monthly NGD for the following year are of utmost importance. In the current study, the h istorical monthly NG consumption data between 2014 and 2024 provided by SOCAR, the local residential NG distribution company for two cities in Turkey, Bursa and Kayseri, was used to determine out - of - sample monthly NGD forecasts for a period of one year and nine months using various time series models, including SARIMA and ETS models, and a novel proposed machine learning method. The proposed method, named Just - in - Time - Learning - Gaussia n Process Regression (JITL - GPR), uses a novel feature representation for t he past NG demand values; instead of using past demand values as column - wise separate features, they are placed on a two - dimensional (2 - D) grid of year - month values. For each test point, a kernel function, tailored for the NGD predictions, is used in GPR t o predict the query point. Since a model is constructed separately for each test point, the proposed method is, indeed, an example of JITL. The JITL - GPR method is easy to use and optimize, and offers a reduction in forecast errors compared to traditional t ime series methods and a state - of - the - art combinat ion model; therefore, it is a promising tool for NGD forecasting in similar settings. INTRODUCTION In the last few decades, there has been a shift in energy sources from fossil fuels to cleaner energy sources, such as wind and solar energy, mainly due to environmental concerns and related government regulations . However, these latter sources are depend ent on w eather conditions and require integration with grid technologies for continuous power generation. Natural gas (NG), typically, consists of (up to) ~95% of methane and 2 - 2.5% ethane - hexane+, with the remain der consist ing of nitrogen, CO NG p ower plants are easy to build and highly reliable, mak ing them invaluable for "clean" energy production. On the other hand, m ost countries depend on imports to maintain t heir NG supplies, and there is a delicate balance between import s and domestic demand . S toring excess import ed gas above actual demand is difficult and would result in economic losses, while import ing less than actual demand could result in a nationwide sh ortage.

Quantum federated learning (QFL) merges the privacy advantages of federated systems with the computational potential of quantum neural networks (QNNs), yet its vulnerability to adversarial attacks remains poorly understood. This work pioneers the integration of adversarial training into QFL, proposing a robust framework, quantum federated adversarial learning (QFAL), where clients collaboratively defend against perturbations by combining local adversarial example generation with federated averaging (FedAvg). We systematically evaluate the interplay between three critical factors: client count (5, 10, 15), adversarial training coverage (0-100%), and adversarial attack perturbation strength (epsilon = 0.01-0.5), using the MNIST dataset. Our experimental results show that while fewer clients often yield higher clean-data accuracy, larger federations can more effectively balance accuracy and robustness when partially adversarially trained. Notably, even limited adversarial coverage (e.g., 20%-50%) can significantly improve resilience to moderate perturbations, though at the cost of reduced baseline performance. Conversely, full adversarial training (100%) may regain high clean accuracy but is vulnerable under stronger attacks. These findings underscore an inherent trade-off between robust and standard objectives, which is further complicated by quantum-specific factors. We conclude that a carefully chosen combination of client count and adversarial coverage is critical for mitigating adversarial vulnerabilities in QFL. Moreover, we highlight opportunities for future research, including adaptive adversarial training schedules, more diverse quantum encoding schemes, and personalized defense strategies to further enhance the robustness-accuracy trade-off in real-world quantum federated environments.

Temporal networks have gained significant prominence in the past decade for modelling dynamic interactions within complex systems. A key challenge in this domain is Temporal Link Prediction (TLP), which aims to forecast future connections by analysing historical network structures across various applications including social network analysis. While existing surveys have addressed specific aspects of TLP, they typically lack a comprehensive framework that distinguishes between representation and inference methods. This survey bridges this gap by introducing a novel taxonomy that explicitly examines representation and inference from existing methods, providing a novel classification of approaches for TLP. We analyse how different representation techniques capture temporal and structural dynamics, examining their compatibility with various inference methods for both transductive and inductive prediction tasks. Our taxonomy not only clarifies the methodological landscape but also reveals promising unexplored combinations of existing techniques. This taxonomy provides a systematic foundation for emerging challenges in TLP, including model explainability and scalable architectures for complex temporal networks.