In this supplementary material, we first give additional details about the method in Sec. 1. Queries used for zero-shot semantic segmentation. We do this for all the annotated classes in the dataset (second column). One can see that, for example, class name'manmade' lacks descriptive specificity. In the text description of this class, we can find "... buildings, walls, guard rails, fences, poles, street signs, traffic lights ..." and more. Table 1: Queries used for zero-shot semantic segmentation.

Image generation models frequently encode social biases, including stereotypes tied to gender, race, and profession. Existing methods for analyzing these biases in diffusion models either focus narrowly on predefined categories or depend on manual interpretation of latent directions. These constraints limit scalability and hinder the discovery of subtle or unanticipated patterns. W e introduce SCALEX, a framework for scalable and automated exploration of diffusion model latent spaces. SCALEX extracts semantically meaningful directions from H-space using only natural language prompts, enabling zero-shot interpretation without retraining or labelling. This allows systematic comparison across arbitrary concepts and large-scale discovery of internal model associations. W e show that SCALEX detects gender bias in profession prompts, ranks semantic alignment across identity descriptors, and reveals clustered conceptual structure without supervision. By linking prompts to latent directions directly, SCALEX makes bias analysis in diffusion models more scalable, interpretable, and extensible than prior approaches.

Our obsession with deadly game shows--from "The Running Man" and "Squid Game" to MrBeast's real-life reënactments--reflects a shift in the national mood to something increasingly zero-sum. It seems we can't get enough of game shows in which the losers die. "The Hunger Games" became a multibillion-dollar media franchise over the past decade, with audiences returning to the theatre, time and time again, to watch adolescents try to kill one another in an enormous arena--a contest devised by the leaders of a society rife with inequality. Netflix's " Squid Game " followed four hundred and fifty-six desperate individuals into an underworld where they play lethal versions of children's games in the hope of winning a life-changing amount of money. Four weeks after its release, the show had become Netflix's most-watched series ever; to date, the first season has been viewed more than two hundred and sixty-five million times.

In this supplementary material, we first give additional details about the method in Sec. 1. Queries used for zero-shot semantic segmentation. We do this for all the annotated classes in the dataset (second column). One can see that, for example, class name'manmade' lacks descriptive specificity. In the text description of this class, we can find "... buildings, walls, guard rails, fences, poles, street signs, traffic lights ..." and more. Table 1: Queries used for zero-shot semantic segmentation.

While recent advancements in deep neural networks (DNNs) have substantially enhanced visual AI's capabilities, the challenge of inadequate data diversity and volume remains, particularly in construction domain. This study presents a novel image synthesis methodology tailored for construction worker detection, leveraging the generative-AI platform Midjourney. The approach entails generating a collection of 12,000 synthetic images by formulating 3000 different prompts, with an emphasis on image realism and diversity. These images, after manual labeling, serve as a dataset for DNN training. Evaluation on a real construction image dataset yielded promising results, with the model attaining average precisions (APs) of 0.937 and 0.642 at intersection-over-union (IoU) thresholds of 0.5 and 0.5 to 0.95, respectively. Notably, the model demonstrated near-perfect performance on the synthetic dataset, achieving APs of 0.994 and 0.919 at the two mentioned thresholds. These findings reveal both the potential and weakness of generative AI in addressing DNN training data scarcity.

Human-robot collaboration (HRC) refers to scenarios Various psychophysiological-based methods have in which humans and robots work collaboratively toward a been employed to interpret psychological phenomena within common goal, sharing tasks and responsibilities in a way the context of HRC by measuring the brain and physiological that capitalizes on the strengths of both parties [3]. As activity of workers, such as electroencephalography construction tasks become increasingly complex and timesensitive, (EEG) for brain activity [73], photoplethysmography (PPG), the integration of collaborative robots, or cobots, electrocardiography (ECG) for cardiac activity [7], and into the construction industry has emerged as a solution to electrodermal activity (EDA) for skin response [8]. Given all enhance efficiency and simultaneously mitigate operational the merits of these technologies, some initial endeavors on risks [86, 90]. However, real-world deployment of HRC psychophysiological methods for HRC in construction have in construction confronts multifaceted challenges, such as been made. For instance, real-time feedback from individual's trust in robotic capabilities [21], frequent reconfigurations physiological responses [21] and cognitive load [50] of working conditions [43], and communication in noisy has been used to allow cobots to adjust their behavior (e.g., and unstructured environments [24]. These challenges are accelerate, stop, slow down) in response to the changing exacerbated by the reliability and safety issues inherent in workers' conditions. However, studies on wearable-based complicated and dynamic construction activities and environments psychophysiological methods for the construction industry (e.g., human dynamics, non-deterministic features, to date are still limited and embryonic, primarily focusing and the presence of various materials) [49, 50]. To address on interpreting a specific dimension of worker status. While these limitations, the development of HRC is shifting these methods hold promise for advancing human-centric from performance-oriented approaches to human-centrality robot collaboration in construction, their potential has not yet paradigms, emphasizing a comprehensive interpretation of been fully explored, and current applications remain largely collaborative behaviors between humans and their robot experimental.

In the construction sector, workers often endure prolonged periods of high-intensity physical work and prolonged use of tools, resulting in injuries and illnesses primarily linked to postural ergonomic risks, a longstanding predominant health concern. To mitigate these risks, researchers have applied various technological methods to identify the ergonomic risks that construction workers face. However, traditional ergonomic risk assessment (ERA) techniques do not offer interactive feedback. The rapidly developing vision-language models (VLMs), capable of generating textual descriptions or answering questions about ergonomic risks based on image inputs, have not yet received widespread attention. This research introduces an interactive visual query system tailored to assess the postural ergonomic risks of construction workers. The system's capabilities include visual question answering (VQA), which responds to visual queries regarding workers' exposure to postural ergonomic risks, and image captioning (IC), which generates textual descriptions of these risks from images. Additionally, this study proposes a dataset designed for training and testing such methodologies. Systematic testing indicates that the VQA functionality delivers an accuracy of 96.5%. Moreover, evaluations using nine metrics for IC and assessments from human experts indicate that the proposed approach surpasses the performance of a method using the same architecture trained solely on generic datasets. This study sets a new direction for future developments in interactive ERA using generative artificial intelligence (AI) technologies. Keywords: Generative Artificial Intelligence; Vision-Language Model; Large language model; Ergonomic Risk Assessment; Construction Safety 1 Introduction Prompt and effective identification and mitigation of workplace hazards are essential for maintaining safety, health, and productivity within the work environment. In the construction industry, workers are often subject to conditions that require awkward body postures, repetitive motions, and intense physical effort, which can detrimentally impact their health [1]. Such conditions in construction tasks usually lead to the emergence of work-related musculoskeletal disorders (WMSDs). Statistics from the United States Bureau of Labor Statistics show that the construction industry's injuries and illnesses caused by WMSDs ranked fifth among all industries. Moreover, in the same year, WMSDs represented 30% of all occupational injuries and illnesses [1]. According to the Association of Workers' Compensation Boards of Canada, the manufacturing and construction sectors reported the second and third-highest rates of losttime injury claims in 2021, representing 13.6% and 10.4% of claims, respectively [2]. European Agency for Safety and Health at Work indicated that the construction and manufacturing sectors reported the highest sick leave rates due to WMSDs [3].

This paper studies gender bias in machine translation through the lens of Large Language Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs, comparing their translation quality and gender bias against state-of-the-art Neural Machine Translation (NMT) models for English to Catalan (En $\rightarrow$ Ca) and English to Spanish (En $\rightarrow$ Es) translation directions. Our findings reveal pervasive gender bias across all models, with base LLMs exhibiting a higher degree of bias compared to NMT models. To combat this bias, we explore prompting engineering techniques applied to an instruction-tuned LLM. We identify a prompt structure that significantly reduces gender bias by up to 12% on the WinoMT evaluation dataset compared to more straightforward prompts. These results significantly reduce the gender bias accuracy gap between LLMs and traditional NMT systems.

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwears. The recommended approach uses the YOLO v7 (You Only Look Once) object detection algorithm to precisely locate these safety items. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a mAP@0.5 score of 87.7\%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research makes a contribution to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry

In the construction industry, where work environments are complex, unstructured and often dangerous, the implementation of Human-Robot Collaboration (HRC) is emerging as a promising advancement. This underlines the critical need for intuitive communication interfaces that enable construction workers to collaborate seamlessly with robotic assistants. This study introduces a conversational Virtual Reality (VR) interface integrating multimodal interaction to enhance intuitive communication between construction workers and robots. By integrating voice and controller inputs with the Robot Operating System (ROS), Building Information Modeling (BIM), and a game engine featuring a chat interface powered by a Large Language Model (LLM), the proposed system enables intuitive and precise interaction within a VR setting. Evaluated by twelve construction workers through a drywall installation case study, the proposed system demonstrated its low workload and high usability with succinct command inputs. The proposed multimodal interaction system suggests that such technological integration can substantially advance the integration of robotic assistants in the construction industry.