arXiv Computer Science @arxiv_cs@qoto.org

Multi-head attention powers Transformer networks, the primary deep learning architecture behind the success of large language models (LLMs). Yet, the theoretical advantages of multi-head versus single-head attention, beyond mere parallel processing, remain underexplored. In this paper, we reframe multi-head attention as a system of potentially synergistic computational graphs, where each head functions as a feedforward directed acyclic graph (DAG) with a common sink state. We provide intuition and preliminary theoretical analysis of mixing time and minimax fidelity in this framework. Our results show that multi-head attention can synergistically enhance information propagation, yielding faster mixing times and minimax fidelity amplification under specific head-diversity conditions. Finally, we train single-head and multi-head Transformers, each with the same total number of parameters, on sequence manipulation tasks and empirically verify the predicted effects.

While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and synaptic operations (SynOps) to facilitate the edge deployment of SNNs, among which search-based pruning methods search for the SNNs structure after pruning. However, existing search-based methods fail to directly use SynOps as the constraint because it will dynamically change in the searching process, resulting in the final searched network violating the expected SynOps target. In this paper, we introduce a novel SNN pruning framework called SPEAR, which leverages reinforcement learning (RL) technique to directly use SynOps as the searching constraint. To avoid the violation of SynOps requirements, we first propose a SynOps prediction mechanism called LRE to accurately predict the final SynOps after search. Observing SynOps cannot be explicitly calculated and added to constrain the action in RL, we propose a novel reward called TAR to stabilize the searching. Extensive experiments show that our SPEAR framework can effectively compress SNN under specific SynOps constraint.

Major depressive disorder represents one of the most significant global health challenges of the 21st century, affecting millions of people worldwide and creating substantial economic and social burdens. While conventional antidepressant therapies have provided relief for many individuals, their limitations including delayed onset of action, significant side effects, and treatment resistance in a substantial portion of patients have prompted researchers and healthcare providers to explore alternative therapeutic approaches (Kasneci et al.). African traditional medicine, with its rich heritage of plant-based remedies developed over millennia, offers a valuable resource for developing novel antidepressant treatments that may address some of these limitations. This paper examines the integration of large language models with African natural products for depression support, combining traditional knowledge with modern artificial intelligence technology to create accessible, evidence-based mental health support systems. The research presented here encompasses a comprehensive analysis of African medicinal plants with documented antidepressant properties, their pharmacological mechanisms, and the development of an AI-powered support system that leverages DeepSeek's advanced language model capabilities. The system provides evidence-based information about African herbal medicines, their clinical applications, safety considerations, and therapeutic protocols while maintaining scientific rigor and appropriate safety standards. Our findings demonstrate the potential for large language models to serve as bridges between traditional knowledge and modern healthcare, offering personalized, culturally appropriate depression support that honors both traditional wisdom and contemporary medical understanding.

Autonomous driving has seen significant progress, driven by extensive real-world data. However, in long-tail scenarios, accurately predicting the safety of the ego vehicle's future motion remains a major challenge due to uncertainties in dynamic environments and limitations in data coverage. In this work, we aim to explore whether it is possible to enhance the motion risk prediction capabilities of Vision-Language Models (VLM) by synthesizing high-risk motion data. Specifically, we introduce a Bird's-Eye View (BEV) based motion simulation method to model risks from three aspects: the ego-vehicle, other vehicles, and the environment. This allows us to synthesize plug-and-play, high-risk motion data suitable for VLM training, which we call DriveMRP-10K. Furthermore, we design a VLM-agnostic motion risk estimation framework, named DriveMRP-Agent. This framework incorporates a novel information injection strategy for global context, ego-vehicle perspective, and trajectory projection, enabling VLMs to effectively reason about the spatial relationships between motion waypoints and the environment. Extensive experiments demonstrate that by fine-tuning with DriveMRP-10K, our DriveMRP-Agent framework can significantly improve the motion risk prediction performance of multiple VLM baselines, with the accident recognition accuracy soaring from 27.13% to 88.03%. Moreover, when tested via zero-shot evaluation on an in-house real-world high-risk motion dataset, DriveMRP-Agent achieves a significant performance leap, boosting the accuracy from base_model's 29.42% to 68.50%, which showcases the strong generalization capabilities of our method in real-world scenarios.

As Large Language Models (LLMs) continue to advance, Retrieval-Augmented Generation (RAG) has emerged as a vital technique to enhance factual accuracy by integrating external knowledge into the generation process. However, LLMs often fail to faithfully integrate retrieved evidence into their generated responses, leading to factual inconsistencies. To quantify this gap, we introduce Entity-Context Divergence (ECD), a metric that measures the extent to which retrieved information is accurately reflected in model outputs. We systematically evaluate contemporary LLMs on their ability to preserve factual consistency in retrieval-augmented settings, a capability we define as RAG-ability. Our empirical analysis reveals that RAG-ability remains low across most LLMs, highlighting significant challenges in entity retention and context fidelity. This paper introduces Radiant (Retrieval AugmenteD entIty-context AligNmenT), a novel framework that merges RAG with alignment designed to optimize the interplay between retrieved evidence and generated content. Radiant extends Direct Preference Optimization (DPO) to teach LLMs how to integrate provided additional information into subsequent generations. As a behavior correction mechanism, Radiant boosts RAG performance across varied retrieval scenarios, such as noisy web contexts, knowledge conflicts, and hallucination reduction. This enables more reliable, contextually grounded, and factually coherent content generation.

The accessibility of long-duration recorders, adapted to sometimes demanding field conditions, has enabled the deployment of extensive animal population monitoring campaigns through ecoacoustics. The effectiveness of automatic signal detection methods, increasingly based on neural approaches, is frequently evaluated solely through machine learning metrics, while acoustic analysis of performance remains rare. As part of the acoustic monitoring of Rock Ptarmigan populations, we propose here a simple method for acoustic analysis of the detection system's performance. The proposed measure is based on relating the signal-to-noise ratio of synthetic signals to their probability of detection. We show how this measure provides information about the system and allows optimisation of its training. We also show how it enables modelling of the detection distance, thus offering the possibility of evaluating its dynamics according to the sound environment and accessing an estimation of the spatial density of calls.

Simulation of fluid flows is crucial for modeling physical phenomena like meteorology, aerodynamics, and biomedicine. Classical numerical solvers often require fine spatiotemporal grids to satisfy stability, consistency, and convergence conditions, leading to substantial computational costs. Although machine learning has demonstrated better efficiency, they typically suffer from issues of interpretability, generalizability, and data dependency. Hence, we propose a learnable and differentiable finite volume solver, called LDSolver, designed for efficient and accurate simulation of fluid flows on spatiotemporal coarse grids. LDSolver comprises two key components: (1) a differentiable finite volume solver, and (2) an learnable module providing equivalent approximation for fluxes (derivatives and interpolations), and temporal error correction on coarse grids. Even with limited training data (e.g., only a few trajectories), our model could accelerate the simulation while maintaining a high accuracy with superior generalizability. Experiments on different flow systems (e.g., Burgers, decaying, forced and shear flows) show that LDSolver achieves state-of-the-art performance, surpassing baseline models with notable margins.

Synthetic network traffic generation has emerged as a promising alternative for various data-driven applications in the networking domain. It enables the creation of synthetic data that preserves real-world characteristics while addressing key challenges such as data scarcity, privacy concerns, and purity constraints associated with real data. In this survey, we provide a comprehensive review of synthetic network traffic generation approaches, covering essential aspects such as data types, generation models, and evaluation methods. With the rapid advancements in AI and machine learning, we focus particularly on deep learning-based techniques while also providing a detailed discussion of statistical methods and their extensions, including commercially available tools. Furthermore, we highlight open challenges in this domain and discuss potential future directions for further research and development. This survey serves as a foundational resource for researchers and practitioners, offering a structured analysis of existing methods, challenges, and opportunities in synthetic network traffic generation.

Social media broadly refers to digital platforms and applications that simulate social interactions online. This study investigates the impact of social media platforms and their algorithms on political interest among users. As social media usage continues to rise, platforms like Facebook and X (formerly Twitter) play increasingly pivotal roles in shaping political discourse. By employing statistical analyses on data collected from over 3,300 participants, this research identifies significant differences in how various social media platforms influence political interest. Findings reveal that moderate Facebook users demonstrate decreased political engagement, whereas even minimal engagement with X significantly boosts political interest. The study further identifies demographic variations, noting that males, older individuals, Black or African American users, those with higher incomes show greater political interest. The demographic analysis highlights that Republicans are particularly active on social media - potentially influencing their social media engagement patterns. However, the study acknowledges a crucial limitation - the lack of direct data regarding the content users are exposed to which is shaping their social media experiences. Future research should explore these influences and consider additional popular platforms to enhance the understanding of social media's political impact. Addressing these gaps can provide deeper insights into digital political mobilization, aiding policymakers, educators, and platform designers in fostering healthier democratic engagement.

Accurate traffic demand forecasting enables transportation management departments to allocate resources more effectively, thereby improving their utilization efficiency. However, complex spatiotemporal relationships in traffic systems continue to limit the performance of demand forecasting models. To improve the accuracy of spatiotemporal traffic demand prediction, we propose a new graph convolutional network structure called DKGCM. Specifically, we first consider the spatial flow distribution of different traffic nodes and propose a novel temporal similarity-based clustering graph convolution method, DK-GCN. This method utilizes Dynamic Time Warping (DTW) and K-means clustering to group traffic nodes and more effectively capture spatial dependencies. On the temporal scale, we integrate the Fast Fourier Transform (FFT) within the bidirectional Mamba deep learning framework to capture temporal dependencies in traffic demand. To further optimize model training, we incorporate the GRPO reinforcement learning strategy to enhance the loss function feedback mechanism. Extensive experiments demonstrate that our model outperforms several advanced methods and achieves strong results on three public datasets.

Amid a tidal wave of misinformation flooding social media during elections and crises, extensive research has been conducted on misinformation detection, primarily focusing on text-based or image-based approaches. However, only a few studies have explored multimodal feature combinations, such as integrating text and images for building a classification model to detect misinformation. This study investigates the effectiveness of different multimodal feature combinations, incorporating text, images, and social features using an early fusion approach for the classification model. This study analyzed 1,529 tweets containing both text and images during the COVID-19 pandemic and election periods collected from Twitter (now X). A data enrichment process was applied to extract additional social features, as well as visual features, through techniques such as object detection and optical character recognition (OCR). The results show that combining unsupervised and supervised machine learning models improves classification performance by 15% compared to unimodal models and by 5% compared to bimodal models. Additionally, the study analyzes the propagation patterns of misinformation based on the characteristics of misinformation tweets and the users who disseminate them.

As AI models outpace the capabilities of single processors, interconnects across chips have become a critical enabler for scalable computing. These processors exchange massive amounts of data at cache-line granularity, prompting the adoption of new interconnect protocols like CXL, NVLink, and UALink, designed for high bandwidth and small payloads. However, the increasing transfer rates of these protocols heighten susceptibility to errors. While mechanisms like Cyclic Redundancy Check (CRC) and Forward Error Correction (FEC) are standard for reliable data transmission, scaling chip interconnects to multi-node configurations introduces new challenges, particularly in managing silently dropped flits in switching devices. This paper introduces Implicit Sequence Number (ISN), a novel mechanism that ensures precise flit drop detection and in-order delivery without adding header overhead. Additionally, we propose Reliability Extended Link (RXL), an extension of CXL that incorporates ISN to support scalable, reliable multi-node interconnects while maintaining compatibility with the existing flit structure. By elevating CRC to a transport-layer mechanism for end-to-end data and sequence integrity, and relying on FEC for link-layer error correction and detection, RXL delivers robust reliability and scalability without compromising bandwidth efficiency.

Despite advancements, Radio Access Networks (RAN) still account for over 50\% of the total power consumption in 5G networks. Existing RAN split options do not fully harness data potential, presenting an opportunity to reduce operational expenditures. This paper addresses this opportunity through a twofold approach. First, highly accurate network traffic and user predictions are achieved using the proposed Curated Collaborative Learning (CCL) framework, which selectively collaborates with relevant correlated data for traffic forecasting. CCL optimally determines whom, when, and what to collaborate with, significantly outperforming state-of-the-art approaches, including global, federated, personalized federated, and cyclic institutional incremental learnings by 43.9%, 39.1%, 40.8%, and 31.35%, respectively. Second, the Distributed Unit Pooling Scheme (DUPS) is proposed, leveraging deep reinforcement learning and prediction inferences from CCL to reduce the number of active DU servers efficiently. DUPS dynamically redirects traffic from underutilized DU servers to optimize resource use, improving energy efficiency by up to 89% over conventional strategies, translating into substantial monetary benefits for operators. By integrating CCL-driven predictions with DUPS, this paper demonstrates a transformative approach for minimizing energy consumption and operational costs in 5G RANs, significantly enhancing efficiency and cost-effectiveness.

Recent research has demonstrated the effectiveness of Artificial Intelligence (AI), and more specifically, Large Language Models (LLMs), in supporting network configuration synthesis and automating network diagnosis tasks, among others. In this preliminary work, we restrict our focus to the application of AI agents to network troubleshooting and elaborate on the need for a standardized, reproducible, and open benchmarking platform, where to build and evaluate AI agents with low operational effort.

Selecting relevant features is an important and necessary step for intelligent machines to maximize their chances of success. However, intelligent machines generally have no enough computing resources when faced with huge volume of data. This paper develops a new method based on sampling techniques and rough set theory to address the challenge of feature selection for massive data. To this end, this paper proposes using the ratio of discernible object pairs to all object pairs that should be distinguished to measure the discriminatory ability of a feature set. Based on this measure, a new feature selection method is proposed. This method constructs positive region preserved samples from massive data to find a feature subset with high discriminatory ability. Compared with other methods, the proposed method has two advantages. First, it is able to select a feature subset that can preserve the discriminatory ability of all the features of the target massive data set within an acceptable time on a personal computer. Second, the lower boundary of the probability of the object pairs that can be discerned using the feature subset selected in all object pairs that should be distinguished can be estimated before finding reducts. Furthermore, 11 data sets of different sizes were used to validate the proposed method. The results show that approximate reducts can be found in a very short period of time, and the discriminatory ability of the final reduct is larger than the estimated lower boundary. Experiments on four large-scale data sets also showed that an approximate reduct with high discriminatory ability can be obtained in reasonable time on a personal computer.

Smart homes that integrate Internet of Things (IoT) devices face increasing cybersecurity risks, posing significant challenges to these environments. The study explores security threats in smart homes ecosystems, categorizing them into vulnerabilities at the network layer, device level, and those from cloud-based and AI-driven systems. Research findings indicate that post-quantum encryption, coupled with AI-driven anomaly detection, is highly effective in enhancing security; however, computational resource demands present significant challenges. Blockchain authentication together with zero-trust structures builds security resilience, although they need changes to existing infrastructure. The specific security strategies show their effectiveness through ANOVA, Chi-square tests, and Monte Carlo simulations yet lack sufficient scalability according to the results. The research demonstrates the requirement for improvement in cryptographic techniques, alongside AI-enhanced threat detection and adaptive security models which must achieve a balance between performance and efficiency and real-time applicability within smart home ecosystems.

Multi-agent systems, which consist of multiple AI models interacting within a shared environment, are increasingly used for persona-based interactions. However, if not carefully designed, these systems can reinforce implicit biases in large language models (LLMs), raising concerns about fairness and equitable representation. We present MALIBU, a novel benchmark developed to assess the degree to which LLM-based multi-agent systems implicitly reinforce social biases and stereotypes. MALIBU evaluates bias in LLM-based multi-agent systems through scenario-based assessments. AI models complete tasks within predefined contexts, and their responses undergo evaluation by an LLM-based multi-agent judging system in two phases. In the first phase, judges score responses labeled with specific demographic personas (e.g., gender, race, religion) across four metrics. In the second phase, judges compare paired responses assigned to different personas, scoring them and selecting the superior response. Our study quantifies biases in LLM-generated outputs, revealing that bias mitigation may favor marginalized personas over true neutrality, emphasizing the need for nuanced detection, balanced fairness strategies, and transparent evaluation benchmarks in multi-agent systems.

Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit harmful responses. As such, we present AutoAdv, a novel framework that automates adversarial prompt generation to systematically evaluate and expose vulnerabilities in LLM safety mechanisms. Our approach leverages a parametric attacker LLM to produce semantically disguised malicious prompts through strategic rewriting techniques, specialized system prompts, and optimized hyperparameter configurations. The primary contribution of our work is a dynamic, multi-turn attack methodology that analyzes failed jailbreak attempts and iteratively generates refined follow-up prompts, leveraging techniques such as roleplaying, misdirection, and contextual manipulation. We quantitatively evaluate attack success rate (ASR) using the StrongREJECT (arXiv:2402.10260 [cs.CL]) framework across sequential interaction turns. Through extensive empirical evaluation of state-of-the-art models--including ChatGPT, Llama, and DeepSeek--we reveal significant vulnerabilities, with our automated attacks achieving jailbreak success rates of up to 86% for harmful content generation. Our findings reveal that current safety mechanisms remain susceptible to sophisticated multi-turn attacks, emphasizing the urgent need for more robust defense strategies.

Artificial intelligence (AI) technologies have fundamentally transformed numerical-based high-performance computing (HPC) applications with data-driven approaches and endeavored to address existing challenges, e.g. high computational intensity, in various scientific domains. In this study, we explore the scenarios of coupling HPC and AI (HPC-AI) in the context of emerging scientific applications, presenting a novel methodology that incorporates three patterns of coupling: surrogate, directive, and coordinate. Each pattern exemplifies a distinct coupling strategy, AI-driven prerequisite, and typical HPC-AI ensembles. Through case studies in materials science, we demonstrate the application and effectiveness of these patterns. The study highlights technical challenges, performance improvements, and implementation details, providing insight into promising perspectives of HPC-AI coupling. The proposed coupling patterns are applicable not only to materials science but also to other scientific domains, offering valuable guidance for future HPC-AI ensembles in scientific discovery.