Intelligent agents navigating real-world environments must continuously learn, adapting to new information while retaining prior knowledge [14]. This ability, known as continual or lifelong learning, poses a significant challenge in modern machine learning. Most artificial neural systems struggle with catastrophic forgetting [5], where training on new tasks or data distributions abruptly erases previously learned information. This phenomenon stems from the shared nature of representations in standard neural networks, where updating weights for new data can overwrite information critical for past tasks. Overcoming catastrophic forgetting is crucial for developing robust, adaptable systems that can learn incrementally from data streams, rather than being retrained from scratch. Numerous approaches have been proposed to mitigate catastrophic forgetting, ranging from regularization techniques and memory replay to architectural modifications. However, many state-of-the-art solutions, despite showing promising results, require substantial changes to model structure or training procedures. This often limits their compatibility with widely used and well-understood machine learning frameworks.

Adversarial Robustness Distillation (ARD) has emerged as an effective method to enhance the robustness of lightweight deep neural networks against adversarial attacks. Current ARD approaches have leveraged a large robust teacher network to train one robust lightweight student. However, due to the diverse range of edge devices and resource constraints, current approaches require training a new student network from scratch to meet specific constraints, leading to substantial computational costs and increased CO2 emissions. This paper proposes Progressive Adversarial Robustness Distillation (ProARD), enabling the efficient one-time training of a dynamic network that supports a diverse range of accurate and robust student networks without requiring retraining. We first make a dynamic deep neural network based on dynamic layers by encompassing variations in width, depth, and expansion in each design stage to support a wide range of architectures. Then, we consider the student network with the largest size as the dynamic teacher network. ProARD trains this dynamic network using a weight-sharing mechanism to jointly optimize the dynamic teacher network and its internal student networks. However, due to the high computational cost of calculating exact gradients for all the students within the dynamic network, a sampling mechanism is required to select a subset of students. We show that random student sampling in each iteration fails to produce accurate and robust students.

While Large Language Models (LLMs) are increasingly applied in student-facing educational tools, their potential to directly support educators through locally deployable and customizable solutions remains underexplored. Many existing approaches rely on proprietary, cloud-based systems that raise significant cost, privacy, and control concerns for educational institutions. To address these barriers, we introduce an end-to-end, open-source framework that empowers educators using small (3B-7B parameter), locally deployable LLMs. Our system is designed for comprehensive teacher support, including customized teaching material generation and AI-assisted assessment. The framework synergistically combines Retrieval-Augmented Generation (RAG) and Context-Augmented Generation (CAG) to produce factually accurate, pedagogically-styled content. A core feature is an interactive refinement loop, a teacher-in-the-loop mechanism that ensures educator agency and precise alignment of the final output. To enhance reliability and safety, an auxiliary verifier LLM inspects all generated content. We validate our framework through a rigorous evaluation of its content generation capabilities and report on a successful technical deployment in a college physics course, which confirms its feasibility on standard institutional hardware. Our findings demonstrate that carefully engineered, self-hosted systems built on small LLMs can provide robust, affordable, and private support for educators, achieving practical utility comparable to much larger models for targeted instructional tasks. This work presents a practical blueprint for the development of sovereign AI tools tailored to the real-world needs of educational institutions.

Large Language Models (LLMs) exhibit impressive capabilities, but remain susceptible to a growing spectrum of safety risks, including jailbreaks, toxic content, hallucinations, and bias. Existing defenses often address only a single threat type or resort to rigid outright rejection, sacrificing user experience and failing to generalize across diverse and novel attacks. This paper introduces Adversarial Scenario Extrapolation (ASE), a novel inference-time computation framework that leverages Chain-of-Thought (CoT) reasoning to simultaneously enhance LLM robustness and seamlessness. ASE guides the LLM through a self-generative process of contemplating potential adversarial scenarios and formulating defensive strategies before generating a response to the user query. Comprehensive evaluation on four adversarial benchmarks with four latest LLMs shows that ASE achieves near-zero jailbreak attack success rates and minimal toxicity, while slashing outright rejections to <4%. ASE outperforms six state-of-the-art defenses in robustness-seamlessness trade-offs, with 92-99% accuracy on adversarial Q&A and 4-10x lower bias scores. By transforming adversarial perception into an intrinsic cognitive process, ASE sets a new paradigm for secure and natural human-AI interaction.

Large Language Models (LLMs) have demonstrated the ability to tackle increasingly complex tasks through advanced reasoning, long-form content generation, and tool use. Solving these tasks often involves long inference-time computations. In human problem solving, a common strategy to expedite work is collaboration: by dividing the problem into sub-tasks, exploring different strategies concurrently, etc. Recent research has shown that LLMs can also operate in parallel by implementing explicit cooperation frameworks, such as voting mechanisms or the explicit creation of independent sub-tasks that can be executed in parallel. However, each of these frameworks may not be suitable for all types of tasks, which can hinder their applicability. In this work, we propose a different design approach: we run LLM "workers" in parallel , allowing them to synchronize via a concurrently-updated attention cache and prompt these workers to decide how best to collaborate. Our approach allows the LLM instances to come up with their own collaboration strategy for the problem at hand, all the while "seeing" each other's memory in the concurrent KV cache. We implement this approach via Hogwild! Inference: a parallel LLM inference engine where multiple instances of the same LLM run in parallel with the same attention cache, with "instant" access to each other's memory. Hogwild! Inference takes advantage of Rotary Position Embeddings (RoPE) to avoid recomputation while improving parallel hardware utilization. We find that modern reasoning-capable LLMs can perform inference with shared Key-Value cache out of the box, without additional fine-tuning.

Abstract--High-quality personalized question banks are crucial for supporting adaptive learning and individualized assessment. Manually designing questions is time-consuming and often fails to meet diverse learning needs, making automated question generation a crucial approach to reduce teachers' workload and improve the scalability of educational resources. However, most existing question generation methods rely on single-agent or rule-based pipelines, which still produce questions with unstable quality, limited diversity, and insufficient alignment with educational goals. T o address these challenges, we propose EduAgentQG, a multi-agent collaborative framework for generating high-quality and diverse personalized questions. The framework consists of five specialized agents and operates through an iterative feedback loop: the Planner generates structured design plans and multiple question directions to enhance diversity; the Writer produces candidate questions based on the plan and optimizes their quality and diversity using feedback from the Solver and Educator; the Solver and Educator perform binary scoring across multiple evaluation dimensions and feed the evaluation results back to the Writer; the Checker conducts final verification, including answer correctness and clarity, ensuring alignment with educational goals. Through this multi-agent collaboration and iterative feedback loop, EduAgentQG generates questions that are both high-quality and diverse, while maintaining consistency with educational objectives. Experiments on two mathematics question datasets demonstrate that EduAgentQG outperforms existing single-agent and multi-agent methods in terms of question diversity, goal consistency, and overall quality. High-quality personalized question banks are crucial for supporting adaptive learning and individualized assessment [1], [2], [3]. In practical teaching, experienced educators can often determine the specific educational goals a student needs to achieve based on observation and prior knowledge [4], [5], [6]. Teachers typically engage in iterative cycles of planning, drafting, validation, and optimization to design questions that are both diagnostically effective and pedagogically meaningful, balancing knowledge coverage, cognitive skill development, and difficulty levels [7], [8]. Existing question banks may not always contain suitable questions, and even when relevant questions are available, they may have been previously attempted by students [9], [10], [11].

Technological systems increasingly mediate human information exchange, spanning interactions among humans as well as between humans and artificial agents. The unprecedented scale and reliance on information disseminated through these systems substantially expand the scope of information-based influence that can both enable and undermine sound decision-making. Consequently, understanding and protecting decision-making today faces growing challenges, as individuals and organizations must navigate evolving opportunities and information-based threats across varied domains and information environments. While these risks are widely recognized, research remains fragmented: work evaluating information-based threat phenomena has progressed largely in isolation from foundational studies of human information processing. In this review, we synthesize insights from both domains to identify shared cognitive mechanisms that mediate vulnerability to information-based threats and shape behavioral outcomes. Finally, we outline directions for future research aimed at integrating these perspectives, emphasizing the importance of such integration for mitigating human vulnerabilities and aligning human-machine representations.

Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization due to non-identical data distributions across clients. Personalized Fine-Tuning (PFT), a popular post-hoc solution, fine-tunes the final global model locally but often overfits to skewed client distributions or fails under domain shifts. We propose adapting Linear Probing followed by full Fine-Tuning (LP-FT), a principled centralized strategy for alleviating feature distortion (Kumar et al., 2022), to the FL setting. Through systematic evaluation across seven datasets and six PFT variants, we demonstrate LP-FT's superiority in balancing personalization and generalization. Our analysis uncovers federated feature distortion, a phenomenon where local fine-tuning destabilizes globally learned features, and theoretically characterizes how LP-FT mitigates this via phased parameter updates. We further establish conditions (e.g., partial feature overlap, covariate-concept shift) under which LP-FT outperforms standard fine-tuning, offering actionable guidelines for deploying robust personalization in FL.

When you purchase through links in our articles, we may earn a small commission. Google's new AI service turns into your own private tutor With Guided Learning, Google Gemini turns into your own educational tutor. When ChatGPT launched three years ago, it shook the academic world to its core. Suddenly, students could have AI answer questions and even write essays. And because ChatGPT is so articulate, spotting cheaters became increasingly difficult.

Barron Trump's mystery words to Joe Biden after his father's fierce inauguration speech are finally revealed Republican representative blasts Trump's Epstein investigation as a'smokescreen' while survivors beg Congress to finally reveal the hidden files: Live updates This is the simple weight loss trick I'd recommend to any woman over 50 who wants to burn calories and tone up - without working out or eating less: KERRY POTTER She runs the anonymous real-life Gossip Girl account outing Hollywood scandals now we expose HER identity and the secret life she's desperate to hide Keith Urban breaks his silence following split with Nicole Kidman - after admitting he's been'completely lonely and miserable' Olivia Nuzzi says Robert F. Kennedy Jr. didn't have a'brain worm' after all I was blackmailed and forced to do the unthinkable. DEAR JANE, how do I hide it from my wife? Trump turns to Epstein's lawyer to prove he has'nothing to hide' as he orders GOP to vote on releasing ALL documents to avert MAGA mutiny Terrifying rise of'taboo cancer': Doctors reveal subtle signs ALL women must know... the most common cause... and a game-changer shot that could save your life Jeff Bezos's ex MacKenzie Scott contributes more than $700MILLION to'historically black colleges' So many single men are taking this new drug cocktail before dates. The results in the bedroom are startling... as I discovered during one marathon session: JANA HOCKING I felt so ill I thought I was dying... but it was a gut condition doctors often wrongly dismiss as IBS: It's so common and there's misinformation about how to treat it, says Nicola... but this is what really works Boy, 9, accused of raping and brutally attacking girl, 5, is allowed home with ankle monitor... despite victim's mom pleading with judge Meghan's ex-husband's reaction to finding out she was dating Prince Harry is revealed by his pal Bethenny Frankel Trump wades into the most explosive debate in right wing media: 'People must decide' My Montecito mole tells me why Me-Me-Meghan'threw a fit' after Kris Jenner's birthday party... this Kardashian drama just won't go away: KENNEDY If I had to start over, here's how I'd make millions again! KEVIN O'LEARY reveals best investments, the career with soaring salaries and worst mistake he made Nigerian gunmen abduct'dozens' of girls from boarding school after killing deputy head teacher in chilling echo of Chibok kidnappings Conor McGregor's friend Dillon Danis slapped with LIFETIME ban by UFC chief Dana White after being involved in ringside brawl READ MORE: Here's what happens in football fans' brains when their team loses Scientists have unveiled the most detailed map of the brain ever created.