As generative AI models become increasingly integrated into high-stakes domains, the need for robust methods to evaluate their ethical reasoning becomes increasingly important. This paper introduces a five-dimensional audit model -- assessing Analytic Quality, Breadth of Ethical Considerations, Depth of Explanation, Consistency, and Decisiveness -- to evaluate the ethical logic of leading large language models (LLMs). Drawing on traditions from applied ethics and higher-order thinking, we present a multi-battery prompt approach, including novel ethical dilemmas, to probe the models' reasoning across diverse contexts. We benchmark seven major LLMs finding that while models generally converge on ethical decisions, they vary in explanatory rigor and moral prioritization. Chain-of-Thought prompting and reasoning-optimized models significantly enhance performance on our audit metrics. This study introduces a scalable methodology for ethical benchmarking of AI systems and highlights the potential for AI to complement human moral reasoning in complex decision-making contexts.

Abstract--T o jointly tackle the challenges of data and node heterogeneity in decentralized learning, we propose a dist ributed strong lottery ticket hypothesis (DSL TH), based on which a communication-efficient personalized learning algorithm is developed. In the proposed method, each local model is represente d as the Hadamard product of global real-valued parameters and a personalized binary mask for pruning. The local model is lea rned by updating and fusing the personalized binary masks while the real-valued parameters are fixed among different agents . T o further reduce the complexity of hardware implementatio n, we incorporate a group sparse regularization term in the los s function, enabling the learned local model to achieve struc - tured sparsity. Then, a binary mask aggregation algorithm i s designed by introducing an intermediate aggregation tenso r and adding a personalized fine-tuning step in each iteration, wh ich constrains model updates towards the local data distributi on. The proposed method effectively leverages the relativity a mong agents while meeting personalized requirements in heterog eneous node conditions. We also provide a theoretical proof for the DSL TH, establishing it as the foundation of the proposed met hod. Numerical simulations confirm the validity of the DSL TH and demonstrate the effectiveness of the proposed algorithm. Index T erms--Distributed learning, personalized learning, data and node heterogeneity, communication efficiency. As one of the most promising applications in 6G era, Artificial Intelligence of Things (AIoT) combines the artifi cial intelligence technologies with the Internet of Things (IoT) infrastructure, resembling the transformation from "conn ected things" to "connected intelligence" . This work was supported in part by National Natural Science F oundation of China under Grants 62394292 and U20A20158, Ministry of In dustry and Information Technology under Grant TC220H07E, Zhejiang Pr ovincial Key R&D Program under Grant 2023C01021, the Fundamental Resear ch Funds for the Central Universities No. 226-2024-00069, and the EU-SN S 6G CENTRIC Project. Z. Tian (email: dankotian@zju.edu.cn) was with the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China and now is with the Center for Wireless Communications, University of Oulu, Oulu 90014, Finland. Z. Zhang (Corresponding Author, email: ning ming@zju.edu.cn) is with the College of Information Science and Electronic Engineer ing, Zhejiang University, Hangzhou 310027, China, and with the State Key L aboratory of Industrial Control Technology, Hangzhou 310027, China, and also with Zhejiang Provincial Key Laboratory of Multimodal Communic ation Networks and Intelligent Information Processing, Hangzhou 310027, China.

Developing lifelong learning agents is crucial for artificial general intelligence. However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where neural networks gradually lose their ability to adapt during training. Despite its significance, this field lacks unified benchmarks and evaluation protocols. We introduce Plasticine, the first open-source framework for benchmarking plasticity optimization in deep RL. Plasticine provides single-file implementations of over 13 mitigation methods, 10 evaluation metrics, and learning scenarios with increasing non-stationarity levels from standard to open-ended environments. This framework enables researchers to systematically quantify plasticity loss, evaluate mitigation strategies, and analyze plasticity dynamics across different contexts. Our documentation, examples, and source code are available at https://github.com/

Active learning (AL) reduces human annotation costs for machine learning systems by strategically selecting the most informative unlabeled data for annotation, but performing it individually may still be insufficient due to restricted data diversity and annotation budget. Federated Active Learning (FAL) addresses this by facilitating collaborative data selection and model training, while preserving the confidentiality of raw data samples. Yet, existing FAL methods fail to account for the heterogeneity of data distribution across clients and the associated fluctuations in global and local model parameters, adversely affecting model accuracy. To overcome these challenges, we propose CHASe (Client Heterogeneity-Aware Data Selection), specifically designed for FAL. CHASe focuses on identifying those unlabeled samples with high epistemic variations (EVs), which notably oscillate around the decision boundaries during training. To achieve both effectiveness and efficiency, \model{} encompasses techniques for 1) tracking EVs by analyzing inference inconsistencies across training epochs, 2) calibrating decision boundaries of inaccurate models with a new alignment loss, and 3) enhancing data selection efficiency via a data freeze and awaken mechanism with subset sampling. Experiments show that CHASe surpasses various established baselines in terms of effectiveness and efficiency, validated across diverse datasets, model complexities, and heterogeneous federation settings.

Unsupervised machine learning techniques, such as topic modeling and clustering, are often used to identify latent patterns in unstructured text data in fields such as political science and sociology. These methods overcome common concerns about reproducibility and costliness involved in the labor-intensive process of human qualitative analysis. However, two major limitations of topic models are their interpretability and their practicality for answering targeted, domain-specific social science research questions. In this work, we investigate opportunities for using LLM-generated text augmentation to improve the usefulness of topic modeling output. We use a political science case study to evaluate our results in a domain-specific application, and find that topic modeling using GPT-4 augmentations creates highly interpretable categories that can be used to investigate domain-specific research questions with minimal human guidance.

In social learning, a network of agents assigns probability scores (beliefs) to some hypotheses of interest, which rule the generation of local streaming data observed by each agent. Belief formation takes place by means of an iterative two-step procedure where: i) the agents update locally their beliefs by using some likelihood model; and ii) the updated beliefs are combined with the beliefs of the neighboring agents, using a pooling rule. This procedure can fail to perform well in the presence of dynamic drifts, leading the agents to incorrect decision making. Here, we focus on the fully online setting where both the true hypothesis and the likelihood models can change over time. This goal is achieved by exploiting two adaptation stages: i) a stochastic gradient descent update to learn and track the drifts in the decision model; ii) and an adaptive belief update to track the true hypothesis changing over time. These stages are controlled by two adaptation parameters that govern the evolution of the error probability for each agent. We show that all agents learn consistently for sufficiently small adaptation parameters, in the sense that they ultimately place all their belief mass on the true hypothesis. Index T erms Social learning, belief formation, decision making, distributed optimization, online leaerning, opinion diffusion over graphs. Marco Carpentiero and Vincenzo Matta are with the Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, via Giovanni Paolo II, I-84084, Fisciano (SA), Italy, and Vincenzo Matta is also with the National Inter-University Consortium for Telecommunications (CNIT), Italy (e-mails: { mcarpentiero, vmatta }@unisa.it). Matta was partially supported by the European Union under the Italian National Recovery and Resilience Plan (NRRP) of NextGenerationEU, partnership on "Telecommunications of the Future" (PE00000001 - program "REST ART"). This work was produced while Virginia Bordignon was a post-doc with the Ecole Polytechnique F ed erale de Lausanne EPFL, School of Engineering, CH-1015 Lausanne, Switzerland (e-mail: virginia.bordignon@alumni.epfl.ch).

Despite significant interest and advancements in humanoid robotics, most existing commercially available hardware remains high-cost, closed-source, and non-transparent within the robotics community. This lack of accessibility and customization hinders the growth of the field and the broader development of humanoid technologies. To address these challenges and promote democratization in humanoid robotics, we demonstrate Berkeley Humanoid Lite, an open-source humanoid robot designed to be accessible, customizable, and beneficial for the entire community. The core of this design is a modular 3D-printed gearbox for the actuators and robot body. All components can be sourced from widely available e-commerce platforms and fabricated using standard desktop 3D printers, keeping the total hardware cost under $5,000 (based on U.S. market prices). The design emphasizes modularity and ease of fabrication. To address the inherent limitations of 3D-printed gearboxes, such as reduced strength and durability compared to metal alternatives, we adopted a cycloidal gear design, which provides an optimal form factor in this context. Extensive testing was conducted on the 3D-printed actuators to validate their durability and alleviate concerns about the reliability of plastic components. To demonstrate the capabilities of Berkeley Humanoid Lite, we conducted a series of experiments, including the development of a locomotion controller using reinforcement learning. These experiments successfully showcased zero-shot policy transfer from simulation to hardware, highlighting the platform's suitability for research validation. By fully open-sourcing the hardware design, embedded code, and training and deployment frameworks, we aim for Berkeley Humanoid Lite to serve as a pivotal step toward democratizing the development of humanoid robotics. All resources are available at https://lite.berkeley-humanoid.org.

LLMs are increasingly explored for bundle generation, thanks to their reasoning capabilities and knowledge. However, deploying large-scale LLMs introduces significant efficiency challenges, primarily high computational costs during fine-tuning and inference due to their massive parameterization. Knowledge distillation (KD) offers a promising solution, transferring expertise from large teacher models to compact student models. This study systematically investigates knowledge distillation approaches for bundle generation, aiming to minimize computational demands while preserving performance. We explore three critical research questions: (1) how does the format of KD impact bundle generation performance? (2) to what extent does the quantity of distilled knowledge influence performance? and (3) how do different ways of utilizing the distilled knowledge affect performance? We propose a comprehensive KD framework that (i) progressively extracts knowledge (patterns, rules, deep thoughts); (ii) captures varying quantities of distilled knowledge through different strategies; and (iii) exploits complementary LLM adaptation techniques (in-context learning, supervised fine-tuning, combination) to leverage distilled knowledge in small student models for domain-specific adaptation and enhanced efficiency. Extensive experiments provide valuable insights into how knowledge format, quantity, and utilization methodologies collectively shape LLM-based bundle generation performance, exhibiting KD's significant potential for more efficient yet effective LLM-based bundle generation.

--Learning grinding skills from human craftsmen by imitation learning has emerged as a prominent research topic in the field of robotic machining. Given their robust trajectory generalization ability and resilience to various external disturbances and environmental changes, Dynamical Movement Primitives (DMPs) provide a promising skills learning solution for the robotic grinding. However, challenges arise when directly applying DMPs to grinding tasks, including low orientation accuracy, inaccurate synchronization of position, orientation, and force, and the inability to generalize surface trajectories. T o address these issues, this paper proposes a robotic grinding skills learning method based on geodesic length DMPs (Geo-DMPs). First, a normalized two-dimensional weighted Gaussian kernel function and intrinsic mean clustering algorithm are proposed to extract surface geometric features from multiple demonstration trajectories. Then, an orientation manifold distance metric is introduced to exclude the time factor from the classical orientation DMPs, thereby constructing Geo-DMPs for the orientation learning to improve the orientation trajectory generation accuracy. On this basis, a synchronization encoding framework for position, orientation, and force skills is established, using a phase function related to geodesic length. This framework enables the generation of robotic grinding actions between any two points on the surface. Finally, experiments on robotic chamfer grinding and free-form surface grinding demonstrate that the proposed method exhibits high geometric accuracy and good generalization capabilities in encoding and generating grinding skills. This method holds significant implications for learning and promoting robotic grinding skills. T o the best of our knowledge, this may be the first attempt to use DMPs to generate grinding skills for position, orientation, and force on model-free surfaces, thereby presenting a novel approach to robotic grinding skills learning.

Unresolved questions about how autonomous vehicles (AVs) should meet the informational needs of riders hinder real-world adoption. Complicating our ability to satisfy rider needs is that different people, goals, and driving contexts have different criteria for what constitutes interaction success. Unfortunately, most human-AV research and design today treats all people and situations uniformly. It is crucial to understand how an AV should communicate to meet rider needs, and how communications should change when the human-AV complex system changes. I argue that understanding the relationships between different aspects of the human-AV system can help us build improved and adaptable AV communications. I support this argument using three empirical studies. First, I identify optimal communication strategies that enhance driving performance, confidence, and trust for learning in extreme driving environments. Findings highlight the need for task-sensitive, modality-appropriate communications tuned to learner cognitive limits and goals. Next, I highlight the consequences of deploying faulty communication systems and demonstrate the need for context-sensitive communications. Third, I use machine learning (ML) to illuminate personal factors predicting trust in AVs, emphasizing the importance of tailoring designs to individual traits and concerns. Together, this dissertation supports the necessity of transparent, adaptable, and personalized AV systems that cater to individual needs, goals, and contextual demands. By considering the complex system within which human-AV interactions occur, we can deliver valuable insights for designers, researchers, and policymakers. This dissertation also provides a concrete domain to study theories of human-machine joint action and situational awareness, and can be used to guide future human-AI interaction research. [shortened for arxiv]