The main challenge in lifelong imitation learning lies in the balance between mitigating catastrophic forgetting of previous skills while maintaining sufficient capacity for acquiring new ones. However, current approaches typically address these aspects in isolation, overlooking their internal correlation in lifelong skill acquisition. We address this limitation with a unified framework named Tokenized Skill Scaling (T2S). Specifically, by tokenizing the model parameters, the linear parameter mapping of the traditional transformer is transformed into cross-attention between input and learnable tokens, thereby enhancing model scalability through the easy extension of new tokens. Additionally, we introduce language-guided skill scaling to transfer knowledge across tasks efficiently and avoid linearly growing parameters. Extensive experiments across diverse tasks demonstrate that T2S: 1) effectively prevents catastrophic forgetting (achieving an average NBT of 1.0% across the three LIBERO task suites), 2) excels in new skill scaling with minimal increases in trainable parameters (needing only 8.0% trainable tokens in an average of lifelong tasks), and 3) enables efficient knowledge transfer between tasks (achieving an average FWT of 77.7% across the three LIBERO task suites), offering a promising solution for lifelong imitation learning.

This paper introduces Q8bot, an open-source, miniature quadruped designed for robotics research and education. We present the robot's novel zero-wire design methodology, which leads to its superior form factor, robustness, replicability, and high performance. With a size and weight similar to a modern smartphone, this standalone robot can walk for over an hour on a single battery charge and survive meter-high drops with simple repairs. Its 300-dollar bill of materials includes minimal off-the-shelf components, readily available custom electronics from online vendors, and structural parts that can be manufactured on hobbyist 3D printers. A preliminary user assembly study confirms that Q8bot can be easily replicated, with an average assembly time of under one hour by a single person. With heuristic open-loop control, Q8bot achieves a stable walking speed of 5.4 body lengths per second and a turning speed of 5 radians per second, along with other dynamic movements such as jumping and climbing moderate slopes.

Student mental health is an increasing concern in academic institutions, where stress can severely impact well-being and academic performance. Traditional assessment methods rely on subjective surveys and periodic evaluations, offering limited value for timely intervention. This paper introduces a context-aware machine learning framework for classifying student stress using two complementary survey-based datasets covering psychological, academic, environmental, and social factors. The framework follows a six-stage pipeline involving preprocessing, feature selection (SelectKBest, RFECV), dimensionality reduction (PCA), and training with six base classifiers: SVM, Random Forest, Gradient Boosting, XGBoost, AdaBoost, and Bagging. To enhance performance, we implement ensemble strategies, including hard voting, soft voting, weighted voting, and stacking. Our best models achieve 93.09% accuracy with weighted hard voting on the Student Stress Factors dataset and 99.53% with stacking on the Stress and Well-being dataset, surpassing previous benchmarks. These results highlight the potential of context-integrated, data-driven systems for early stress detection and underscore their applicability in real-world academic settings to support student well-being.

--Can we teach machines to assess the expertise of humans solving visual tasks automatically based on eye tracking features? This paper proposes AutoSIGHT, Automatic System for Immediate Grading of Human experTise, that classifies expert and non-expert performers, and builds upon an ensemble of features extracted from eye tracking data while the performers were solving a visual task. Results on the task of iris Presentation Attack Detection (PAD) used for this study show that with a small evaluation window of just 5 seconds, AutoSIGHT achieves an average average Area Under the ROC curve performance of 0.751 in subject-disjoint train-test regime, indicating that such detection is viable. Furthermore, when a larger evaluation window of up to 30 seconds is available, the Area Under the ROC curve (AUROC) increases to 0.8306, indicating the model is effectively leveraging more information at a cost of slightly delayed decisions. This work opens new areas of research on how to incorporate the automatic weighing of human and machine expertise into human-AI pairing setups, which need to react dynamically to nonstationary expertise distribution between the human and AI players ( e.g., when the experts need to be replaced, or the task at hand changes rapidly). Along with this paper, we offer the eye tracking data used in this study collected from 6 experts and 53 non-experts solving iris PAD visual task. As Artificial Intelligence (AI) systems become more commonplace in everyday tasks, companies and researchers alike understand that a lack of trust in a model or the validity of a model's decision is a major obstacle to wide-scale adoption [1]. This has led to the sub-field of Trustworthy Artificial Intelligence (T AI) that focuses on defining the core principles that AI systems should satisfy to increase trust and adoption. One such principle is that good models should generalize well to unseen data types (that is, operate well in an open set recognition regime). Another principle is that there should exist a seamless and effective collaboration between the AI and humans solving the tasks jointly, in which the capabilities of both sides are appropriately and automatically assessed, and incorporated into the decision-making process.

The rapid integration of generative artificial intelligence (AI) into postsecondary education and many other sectors resulted in a global reckoning with this new technology. This paper contributes to the study of the multifaceted influence of generative AI, with a particular focus on OpenAI's ChatGPT within academic settings during the first six months after the release in three specific ways . First, it scrutinize s the rise of ChatGPT as a transformative event construed through a study of mainstream discourses exhibiting AI hype. Second, i t discusses the perceived implications of generative AI for writing, teaching, and learning t hrough the lens of critical discourse analysis and critical AI studies . Third, i t encourages the necessity for best practices in the adoption of generative AI technologies in education.

Reinforcement learning (RL), driven by data-driven methods, has become an effective solution for robot leg motion control problems. However, the mainstream RL methods for bipedal robot terrain traversal, such as teacher-student policy knowledge distillation, suffer from long training times, which limit development efficiency. To address this issue, this paper proposes BarlowWalk, an improved Proximal Policy Optimization (PPO) method integrated with self-supervised representation learning. This method employs the Barlow Twins algorithm to construct a decoupled latent space, mapping historical observation sequences into low-dimensional representations and implementing self-supervision. Meanwhile, the actor requires only proprioceptive information to achieve self-supervised learning over continuous time steps, significantly reducing the dependence on external terrain perception. Simulation experiments demonstrate that this method has significant advantages in complex terrain scenarios. To enhance the credibility of the evaluation, this study compares BarlowWalk with advanced algorithms through comparative tests, and the experimental results verify the effectiveness of the proposed method.

In this paper, we introduce an AI-mediated framework that can provide intelligent feedback to augment human cognition. Specifically, we leverage deep reinforcement learning (DRL) to provide adaptive time pressure feedback to improve user performance in a math arithmetic task. Time pressure feedback could either improve or deteriorate user performance by regulating user attention and anxiety. Adaptive time pressure feedback controlled by a DRL policy according to users' real-time performance could potentially solve this trade-off problem. However, the DRL training and hyperparameter tuning may require large amounts of data and iterative user studies. Therefore, we propose a dual-DRL framework that trains a regulation DRL agent to regulate user performance by interacting with another simulation DRL agent that mimics user cognition behaviors from an existing dataset. Our user study demonstrates the feasibility and effectiveness of the dual-DRL framework in augmenting user performance, in comparison to the baseline group.

--The emergence of large language models (LLMs) has revolutionized artificial intelligence, offering unprecedented capabilities in reasoning, generalization, and zero-shot learning. These strengths open new frontiers in wireless communications, where increasing complexity and dynamics demand intelligent and adaptive solutions. This article explores the role of LLMs in transforming wireless systems across three key directions: adapting pretrained LLMs for core communication tasks, developing wireless-specific foundation models to balance versatility and efficiency, and enabling agentic LLMs with autonomous reasoning and coordination capabilities. We highlight recent advances, practical case studies, and the unique benefits of LLM-based approaches over traditional methods. Finally, we outline open challenges and research opportunities--including multimodal fusion, collaboration with lightweight models, and self-improving capabilities--charting a path toward intelligent, adaptive, and autonomous wireless networks of the future. The rapid advancement of large language models (LLMs) has transformed natural language processing, unlocking capabilities in reasoning, representation learning, and generalization from limited supervision. These models, built on transformer architectures and trained on large-scale text corpora, exhibit remarkable adaptability across tasks and domains. As such, their core strengths--sequence modeling, contextual understanding, and zero-shot inference--are increasingly being explored for applications far beyond language, to include robotics, software engineering, and, more recently, wireless communications. This article investigates how LLMs can be strategically repurposed to address key challenges in modern wireless networks, tracing a trajectory from task-specific model adaptation to the realization of autonomous, agent-driven communication systems. Next-generation wireless systems are characterized by growing complexity and variability.

The concept of the Web of Agents (WoA), which transforms the static, document-centric Web into an environment of autonomous agents acting on users' behalf, has attracted growing interest as large language models (LLMs) become more capable. However, research in this area is still fragmented across different communities. Contemporary surveys catalog the latest LLM-powered frameworks, while the rich histories of Multi-Agent Systems (MAS) and the Semantic Web are often treated as separate, legacy domains. This fragmentation obscures the intellectual lineage of modern systems and hinders a holistic understanding of the field's trajectory. We present the first comprehensive evolutionary overview of the WoA. We show that modern protocols like A2A and the MCP, are direct evolutionary responses to the well-documented limitations of earlier standards like FIPA standards and OWL-based semantic agents. To systematize this analysis, we introduce a four-axis taxonomy (semantic foundation, communication paradigm, locus of intelligence, discovery mechanism). This framework provides a unified analytical lens for comparing agent architectures across all generations, revealing a clear line of descent where others have seen a disconnect. Our analysis identifies a paradigm shift in the 'locus of intelligence': from being encoded in external data (Semantic Web) or the platform (MAS) to being embedded within the agent's core model (LLM). This shift is foundational to modern Agentic AI, enabling the scalable and adaptive systems the WoA has long envisioned. We conclude that while new protocols are essential, they are insufficient for building a robust, open, trustworthy ecosystem. Finally, we argue that the next research frontier lies in solving persistent socio-technical challenges, and we map out a new agenda focused on decentralized identity, economic models, security, and governance for the emerging WoA.

Scientific reasoning requires not only long-chain reasoning processes, but also knowledge of domain-specific terminologies and adaptation to updated findings. To deal with these challenges for scientific reasoning, we introduce RAISE, a step-by-step retrieval-augmented framework which retrieves logically relevant documents from in-the-wild corpus. RAISE is divided into three steps: problem decomposition, logical query generation, and logical retrieval. We observe that RAISE consistently outperforms other baselines on scientific reasoning benchmarks. We analyze that unlike other baselines, RAISE retrieves documents that are not only similar in terms of the domain knowledge, but also documents logically more relevant.