As modern computers evolve to have better performance and larger computation power, new modes of interaction emerge along with novel designs of devices. Augmented Reality (AR), which allows users to interact with common objects via virtual interfaces, establishes a new space of designs and development and hence poses a significant challenge to machines' spatial perception of the complex real-world environment. Pose estimation of 3D objects, as one of the most commonplace and important tasks in 3D perception, is still a challenging task for modern algorithms, especially in complex real environments with alternating scene properties and irregular object geometries. Our project is at the forefront of addressing critical challenges in human-robot interaction within dynamic mobile AR environments. We focus on exploring the potential ways of interacting with robots in space, especially in a non-intrusive manner. This interaction is made possible by integrating three key components: a non-intrusive head-mounted device serving as a user interface, voice control to enable astronauts to manipulate the interface and interact with robots using verbal commands, and a robot tracking algorithm that accurately localizes the robot's position in 3D space. Enabled by these technologies, we proposed URSA, an LLM-driven immersive AR user interface for robotics and space exploration, and participated in the 2023 NASA Spacesuit User Interface Technologies for Students (NASA SUITS) [1]. This project aims to develop solutions for future spaceflight needs, particularly for the Artemis missions, which seek to establish a sustained human presence on the Moon and Mars.

An abstractive summary of a news article contains its most important information in a condensed version. The evaluation of automatically generated summaries by generative language models relies heavily on human-authored summaries as gold references, by calculating overlapping units or similarity scores. News articles report events, and ideally so should the summaries. In this work, we propose to evaluate the quality of abstractive summaries by calculating overlapping events between generated summaries, reference summaries, and the original news articles. We experiment on a richly annotated Norwegian dataset comprising both events annotations and summaries authored by expert human annotators. Our approach provides more insight into the event information contained in the summaries.

Despite the recent strides in large language models, studies have underscored the existence of social biases within these systems. In this paper, we delve into the validation and comparison of the ethical biases of LLMs concerning globally discussed and potentially sensitive topics, hypothesizing that these biases may arise from language-specific distinctions. Introducing the Multilingual Sensitive Questions & Answers Dataset (MSQAD), we collected news articles from Human Rights Watch covering 17 topics, and generated socially sensitive questions along with corresponding responses in multiple languages. We scrutinized the biases of these responses across languages and topics, employing two statistical hypothesis tests. The results showed that the null hypotheses were rejected in most cases, indicating biases arising from cross-language differences. It demonstrates that ethical biases in responses are widespread across various languages, and notably, these biases were prevalent even among different LLMs. By making the proposed MSQAD openly available, we aim to facilitate future research endeavors focused on examining cross-language biases in LLMs and their variant models.

AI agents are autonomous systems designed to perceive, reason, and act within dynamic environments. With the rapid advancements in generative AI (GenAI), large language models (LLMs) and multimodal large language models (MLLMs) have significantly improved AI agents' capabilities in semantic comprehension, complex reasoning, and autonomous decision-making. At the same time, the rise of Agentic AI highlights adaptability and goal-directed autonomy in dynamic and complex environments. LLMs-based AI Agents (LLM-Agents), MLLMs-based AI Agents (MLLM-Agents), and Agentic AI contribute to expanding AI's capabilities in information processing, environmental perception, and autonomous decision-making, opening new avenues for smart manufacturing. However, the definitions, capability boundaries, and practical applications of these emerging AI paradigms in smart manufacturing remain unclear. To address this gap, this study systematically reviews the evolution of AI and AI agent technologies, examines the core concepts and technological advancements of LLM-Agents, MLLM-Agents, and Agentic AI, and explores their potential applications in and integration into manufacturing, along with the potential challenges they may face. Preprint submitted to Journal of Manufacturing System July 3, 2025 1. Introduction As a complex and data-intensive domain, manufacturing faces increasing challenges due to the increasing demand for customization, shorter product life cycles, and intense global competition [1, 2]. Traditional automated systems, reliant on fixed rules, struggle to adapt to evolving customer needs.

Aligning Large Language Models (LLMs) and Large Multimodal Models (LMMs) to human preferences is a central challenge in improving the quality of the models' generative outputs for real-world applications. A common approach is to use reward modeling to encode preferences, enabling alignment via post-training using reinforcement learning. However, traditional reward modeling is not easily adaptable to new preferences because it requires a separate reward model, commonly trained on large preference datasets. To address this, we introduce Activation Reward Models (Activation RMs) -- a novel few-shot reward modeling method that leverages activation steering to construct well-aligned reward signals using minimal supervision and no additional model finetuning. Activation RMs outperform existing few-shot reward modeling approaches such as LLM-as-a-judge with in-context learning, voting-based scoring, and token probability scoring on standard reward modeling benchmarks. Furthermore, we demonstrate the effectiveness of Activation RMs in mitigating reward hacking behaviors, highlighting their utility for safety-critical applications. Toward this end, we propose PreferenceHack, a novel few-shot setting benchmark, the first to test reward models on reward hacking in a paired preference format. Finally, we show that Activation RM achieves state-of-the-art performance on this benchmark, surpassing even GPT-4o.

The \textit{Nordisk familjebok} is a Swedish encyclopedia from the 19th and 20th centuries. It was written by a team of experts and aimed to be an intellectual reference, stressing precision and accuracy. This encyclopedia had four main editions remarkable by their size, ranging from 20 to 38 volumes. As a consequence, the \textit{Nordisk familjebok} had a considerable influence in universities, schools, the media, and society overall. As new editions were released, the selection of entries and their content evolved, reflecting intellectual changes in Sweden. In this paper, we used digitized versions from \textit{Project Runeberg}. We first resegmented the raw text into entries and matched pairs of entries between the first and second editions using semantic sentence embeddings. We then extracted the geographical entries from both editions using a transformer-based classifier and linked them to Wikidata. This enabled us to identify geographic trends and possible shifts between the first and second editions, written between 1876-1899 and 1904-1926, respectively. Interpreting the results, we observe a small but significant shift in geographic focus away from Europe and towards North America, Africa, Asia, Australia, and northern Scandinavia from the first to the second edition, confirming the influence of the First World War and the rise of new powers. The code and data are available on GitHub at https://github.com/sibbo/nordisk-familjebok.

Large language models (LLMs) and vision-language models (VLMs) have the potential to transform biological research by enabling autonomous experimentation. Yet, their application remains constrained by rigid protocol design, limited adaptability to dynamic lab conditions, inadequate error handling, and high operational complexity. Here we introduce BioMARS (Biological Multi-Agent Robotic System), an intelligent platform that integrates LLMs, VLMs, and modular robotics to autonomously design, plan, and execute biological experiments. BioMARS uses a hierarchical architecture: the Biologist Agent synthesizes protocols via retrieval-augmented generation; the Technician Agent translates them into executable robotic pseudo-code; and the Inspector Agent ensures procedural integrity through multimodal perception and anomaly detection. The system autonomously conducts cell passaging and culture tasks, matching or exceeding manual performance in viability, consistency, and morphological integrity. It also supports context-aware optimization, outperforming conventional strategies in differentiating retinal pigment epithelial cells. A web interface enables real-time human-AI collaboration, while a modular backend allows scalable integration with laboratory hardware. These results highlight the feasibility of generalizable, AI-driven laboratory automation and the transformative role of language-based reasoning in biological research.

Large language models (LLMs) can simulate clinical reasoning based on natural language prompts, but their utility in ophthalmology is largely unexplored. This study evaluated GPT-4's ability to interpret structured textual descriptions of retinal fundus photographs and simulate clinical decisions for diabetic retinopathy (DR) and glaucoma screening, including the impact of adding real or synthetic clinical metadata. We conducted a retrospective diagnostic validation study using 300 annotated fundus images. GPT-4 received structured prompts describing each image, with or without patient metadata. The model was tasked with assigning an ICDR severity score, recommending DR referral, and estimating the cup-to-disc ratio for glaucoma referral. Performance was evaluated using accuracy, macro and weighted F1 scores, and Cohen's kappa. McNemar's test and change rate analysis were used to assess the influence of metadata. GPT-4 showed moderate performance for ICDR classification (accuracy 67.5%, macro F1 0.33, weighted F1 0.67, kappa 0.25), driven mainly by correct identification of normal cases. Performance improved in the binary DR referral task (accuracy 82.3%, F1 0.54, kappa 0.44). For glaucoma referral, performance was poor across all settings (accuracy ~78%, F1 <0.04, kappa <0.03). Metadata inclusion did not significantly affect outcomes (McNemar p > 0.05), and predictions remained consistent across conditions. GPT-4 can simulate basic ophthalmic decision-making from structured prompts but lacks precision for complex tasks. While not suitable for clinical use, LLMs may assist in education, documentation, or image annotation workflows in ophthalmology.

We present Locality-aware Parallel Decoding (LPD) to accelerate autoregressive image generation. Traditional autoregressive image generation relies on next-patch prediction, a memory-bound process that leads to high latency. Existing works have tried to parallelize next-patch prediction by shifting to multi-patch prediction to accelerate the process, but only achieved limited parallelization. To achieve high parallelization while maintaining generation quality, we introduce two key techniques: (1) Flexible Parallelized Autoregressive Modeling, a novel architecture that enables arbitrary generation ordering and degrees of parallelization. It uses learnable position query tokens to guide generation at target positions while ensuring mutual visibility among concurrently generated tokens for consistent parallel decoding. (2) Locality-aware Generation Ordering, a novel schedule that forms groups to minimize intra-group dependencies and maximize contextual support, enhancing generation quality. With these designs, we reduce the generation steps from 256 to 20 (256$\times$256 res.) and 1024 to 48 (512$\times$512 res.) without compromising quality on the ImageNet class-conditional generation, and achieving at least 3.4$\times$ lower latency than previous parallelized autoregressive models.

Traditional Data+AI systems utilize data-driven techniques to optimize performance, but they rely heavily on human experts to orchestrate system pipelines, enabling them to adapt to changes in data, queries, tasks, and environments. For instance, while there are numerous data science tools available, developing a pipeline planning system to coordinate these tools remains challenging. This difficulty arises because existing Data+AI systems have limited capabilities in semantic understanding, reasoning, and planning. Fortunately, we have witnessed the success of large language models (LLMs) in enhancing semantic understanding, reasoning, and planning abilities. It is crucial to incorporate LLM techniques to revolutionize data systems for orchestrating Data+AI applications effectively. To achieve this, we propose the concept of a 'Data Agent' - a comprehensive architecture designed to orchestrate Data+AI ecosystems, which focuses on tackling data-related tasks by integrating knowledge comprehension, reasoning, and planning capabilities. We delve into the challenges involved in designing data agents, such as understanding data/queries/environments/tools, orchestrating pipelines/workflows, optimizing and executing pipelines, and fostering pipeline self-reflection. Furthermore, we present examples of data agent systems, including a data science agent, data analytics agents (such as unstructured data analytics agent, semantic structured data analytics agent, data lake analytics agent, and multi-modal data analytics agent), and a database administrator (DBA) agent. We also outline several open challenges associated with designing data agent systems.