Quantum federated learning (QFL) is a combination of distributed quantum computing and federated machine learning, integrating the strengths of both to enable privacy-preserving decentralized learning with quantum-enhanced capabilities. It appears as a promising approach for addressing challenges in efficient and secure model training across distributed quantum systems. This paper presents a comprehensive survey on QFL, exploring its key concepts, fundamentals, applications, and emerging challenges in this rapidly developing field. Specifically, we begin with an introduction to the recent advancements of QFL, followed by discussion on its market opportunity and background knowledge. We then discuss the motivation behind the integration of quantum computing and federated learning, highlighting its working principle. Moreover, we review the fundamentals of QFL and its taxonomy. Particularly, we explore federation architecture, networking topology, communication schemes, optimization techniques, and security mechanisms within QFL frameworks. Furthermore, we investigate applications of QFL across several domains which include vehicular networks, healthcare networks, satellite networks, metaverse, and network security. Additionally, we analyze frameworks and platforms related to QFL, delving into its prototype implementations, and provide a detailed case study. Key insights and lessons learned from this review of QFL are also highlighted. We complete the survey by identifying current challenges and outlining potential avenues for future research in this rapidly advancing field.

Equilibrium Propagation (EP) is a biologically inspired local learning rule first proposed for convergent recurrent neural networks (CRNNs), in which synaptic updates depend only on neuron states from two distinct phases. EP estimates gradients that closely align with those computed by Backpropaga-tion Through Time (BPTT) while significantly reducing computational demands, positioning it as a potential candidate for on-chip training in neuromorphic architectures. However, prior studies on EP have been constrained to shallow architectures, as deeper networks suffer from the vanishing gradient problem, leading to convergence difficulties in both energy minimization and gradient computation. To address the vanishing gradient problem in deep EP networks, we propose a novel EP framework that incorporates intermediate error signals to enhance information flow and convergence of neuron dynamics. This is the first work to integrate knowledge distillation and local error signals into EP, enabling the training of significantly deeper architectures. Our proposed approach achieves state-of-the-art performance on the CIFAR-10 and CIFAR-100 datasets, showcasing its scalability on deep VGG architectures. These results represent a significant advancement in the scalability of EP, paving the way for its application in real-world systems.

In recent years, angle-resolved photoemission spectroscopy (ARPES) has advanced significantly in its ability to probe more observables and simultaneously generate multi-dimensional datasets. These advances present new challenges in data acquisition, processing, and analysis. Machine learning (ML) models can drastically reduce the workload of experimentalists; however, the lack of training data for ML -- and in particular deep learning -- is a significant obstacle. In this work, we introduce an open-source synthetic ARPES spectra simulator - aurelia - for the purpose of generating the large datasets necessary to train ML models. As a demonstration, we train a convolutional neural network to evaluate ARPES spectra quality -- a critical task performed during the initial sample alignment phase of the experiment. We benchmark the simulation-trained model against actual experimental data and find that it can assess the spectra quality more accurately than human analysis, and swiftly identify the optimal measurement region with high precision. Thus, we establish that simulated ARPES spectra can be an effective proxy for experimental spectra in training ML models.

Solving financial problems demands complex reasoning, multimodal data processing, and a broad technical understanding, presenting unique challenges for current large language models (LLMs). We introduce XFinBench, a novel benchmark with 4,235 examples designed to evaluate LLM's ability in solving complex, knowledge-intensive financial problems across diverse graduate-level finance topics with multi-modal context. We identify five core capabilities of LLMs using XFinBench, i.e, terminology understanding, temporal reasoning, future forecasting, scenario planning, and numerical modelling. Upon XFinBench, we conduct extensive experiments on 18 leading models. The result shows that o1 is the best-performing text-only model with an overall accuracy of 67.3%, but still lags significantly behind human experts with 12.5%, especially in temporal reasoning and scenario planning capabilities. We further construct a knowledge bank with 3,032 finance terms for knowledge augmentation analysis, and find that relevant knowledge to the question only brings consistent accuracy improvements to small open-source model. Additionally, our error analysis reveals that rounding errors during calculation and blindness to position and intersection of curves in the image are two primary issues leading to model's poor performance in calculating and visual-context questions, respectively. Code and dataset are accessible via GitHub: https://github.com/Zhihan72/XFinBench.

Language models are increasingly used in Brazil, but most evaluation remains English-centric. This paper presents Alvorada-Bench, a 4,515-question, text-only benchmark drawn from five Brazilian university entrance examinations. Evaluating twenty models under zero-shot, role-playing, and chain-of-thought prompting, producing 270,900 responses with structured self-reports of confidence, perceived difficulty, and Bloom level. The top models exceed 94% accuracy overall, but accuracy declines on Mathematics and on the engineering oriented IME and ITA exams, indicating persistent weaknesses in multi-step reasoning. Confidence is well calibrated and correlates with perceived difficulty, revealing that models can accurately assess their own certainty capabilities. A cost accuracy analysis shows that high accuracy is achievable at under $2 per 1K tokens. On ENEM 2024 the top model (O3) achieved perfect scores in Languages subject questions while even the weakest system (GPT-4.1 Nano) only underperforms humans in Mathematics. Through exams that distill decades of Brazilian educational priorities and assess millions of students yearly, Alvorada-Bench establishes whether language models can navigate the intersection of language, culture, and reasoning that defines academic readiness in Brazil.

Depression is a common mental health condition that can lead to hopelessness, loss of interest, self-harm, and even suicide. Early detection is challenging due to individuals not self-reporting or seeking timely clinical help. With the rise of social media, users increasingly express emotions online, offering new opportunities for detection through text analysis. While prior research has focused on languages such as English, no studies exist for Sorani Kurdish. This work presents a machine learning and Natural Language Processing (NLP) approach to detect depression in Sorani tweets. A set of depression-related keywords was developed with expert input to collect 960 public tweets from X (Twitter platform). The dataset was annotated into three classes: Shows depression, Not-show depression, and Suspicious by academics and final year medical students at the University of Kurdistan Hewlêr. Four supervised models, including Support Vector Machines, Multinomial Naive Bayes, Logistic Regression, and Random Forest, were trained and evaluated, with Random Forest achieving the highest performance accuracy and F1-score of 80%. This study establishes a baseline for automated depression detection in Kurdish language contexts.

Large language models (LLMs) often have a fixed knowledge cutoff, limiting their accuracy on emerging information. We present ALAS (Autonomous Learning Agent System), a modular pipeline that continuously updates an LLM's knowledge with minimal human intervention. ALAS autonomously generates a learning curriculum for a target domain, retrieves up-to-date information from the web (with citations), distills this into question-answer training data, and fine-tunes the model through supervised fine-tuning (SFT) and direct preference optimization (DPO). It iteratively evaluates performance and revises the curriculum, enabling long-term continual learning. We demonstrate ALAS's ability to self-improve a model on rapidly evolving domains (e.g., new Python releases, latest security CVEs, academic trends), significantly boosting post-cutoff question answering accuracy (from 15% to 90% on average) without manual dataset curation. The system emphasizes modularity and reproducibility: each component (planning, retrieval, distillation, memory, fine-tuning) is interchangeable and built on standard APIs. We discuss comparative baselines (e.g., retrieval-augmented generation vs. fine-tuning) and show that ALAS achieves 90% accuracy on knowledge-updated queries with minimal engineering overhead. Finally, we outline limitations (cost, dependency on source quality) and future directions for autonomous lifelong learning in LLMs.

Warning: This research studies AI persuasion and bias amplification that could be misused; all experiments are for safety evaluation. Large Language Models (LLMs) now generate convincing, human-like text and are widely used in content creation, decision support, and user interactions. Yet the same systems can spread information or misinformation at scale and reflect social biases that arise from data, architecture, or training choices. This work examines how persuasion and bias interact in LLMs, focusing on how imperfect or skewed outputs affect persuasive impact. Specifically, we test whether persona-based models can persuade with fact-based claims while also, unintentionally, promoting misinformation or biased narratives. We introduce a convincer-skeptic framework: LLMs adopt personas to simulate realistic attitudes. Skeptic models serve as human proxies; we compare their beliefs before and after exposure to arguments from convincer models. Persuasion is quantified with Jensen-Shannon divergence over belief distributions. We then ask how much persuaded entities go on to reinforce and amplify biased beliefs across race, gender, and religion. Strong persuaders are further probed for bias using sycophantic adversarial prompts and judged with additional models. Our findings show both promise and risk. LLMs can shape narratives, adapt tone, and mirror audience values across domains such as psychology, marketing, and legal assistance. But the same capacity can be weaponized to automate misinformation or craft messages that exploit cognitive biases, reinforcing stereotypes and widening inequities. The core danger lies in misuse more than in occasional model mistakes. By measuring persuasive power and bias reinforcement, we argue for guardrails and policies that penalize deceptive use and support alignment, value-sensitive design, and trustworthy deployment.

Therefore, in this pilot study, we try to focus and summarize exclusively on foundation models that have been pre-trained on large-scale non-EEG data and directly applied to EEG analysis tasks. Specifically, we exclude models fine-tuned on EEG datasets to focus exclusively on cross-domain transfer, and proposed a function-driven, modality-oriented taxonomy for involved foundation models. To this end, as concluded in T ABLE I, the existing research advances of the off-the-shelf foundation models applied in EEG analysis are categorized into five domains: native unimodal EEG decoding, EEG-to-text alignment and generation, EEG-to-vision reconstruction and retrieval, EEG-to-audio decoding and generation, and multi-modal EEG fusion. Within each category, we systematically review representative explorations, with the used models, new architecture characteristics, and application scenarios highlighted in the following sections. Our main contributions are: 1) This survey provides the first and latest comprehensive taxonomy of foundation models pre-trained on non-EEG data and applied to EEG analysis, where the progress of unimodal EEG decoding, EEG-to-text, EEG-to-vision, EEG-to-audio, and multi-modal EEG fusion under foundation models is clearly presented. Such the effort clarifies the latest EEG research application, and helps to explicitly express the rich connotation and practical value of the foundation model; 2) It elaborates in detail on the different roles played by the foundation model in the EEG decoding paradigm shift, including the noise-robust representation learning, cross-modal alignment mechanism, and zero-shot generalization strategies, providing a clear technical framework for newcomers and domain experts in the progress of foundation model reshaping the conventional EEG decoding; 3) We discussed the existing challenges and potential future research directions, aiming to provide clearer and more feasible guidance for the development of scalable, interpretable and widely applicable EEG decoding systems. The remainder of this paper is organized as follows: Section II VI describes the taxonomy of how foundation models can be adapted to classified EEG decoding applications, respectively. Section VII highlights current challenges and future directions, and the conclusion are given in Section VIII.

The increasing heterogeneity of student populations poses significant challenges for teachers, particularly in mathematics education, where cognitive, motivational, and emotional differences strongly influence learning outcomes. While AI-driven personalization tools have emerged, most remain performance-focused, offering limited support for teachers and neglecting broader pedagogical needs. This paper presents the FACET framework, a teacher-facing, large language model (LLM)-based multi-agent system designed to generate individualized classroom materials that integrate both cognitive and motivational dimensions of learner profiles. The framework comprises three specialized agents: (1) learner agents that simulate diverse profiles incorporating topic proficiency and intrinsic motivation, (2) a teacher agent that adapts instructional content according to didactical principles, and (3) an evaluator agent that provides automated quality assurance. We tested the system using authentic grade 8 mathematics curriculum content and evaluated its feasibility through a) automated agent-based assessment of output quality and b) exploratory feedback from K-12 in-service teachers. Results from ten internal evaluations highlighted high stability and alignment between generated materials and learner profiles, and teacher feedback particularly highlighted structure and suitability of tasks. The findings demonstrate the potential of multi-agent LLM architectures to provide scalable, context-aware personalization in heterogeneous classroom settings, and outline directions for extending the framework to richer learner profiles and real-world classroom trials.