Occupational Health and Safety Research

Derniers papiers

• A paired synthetic construction-site image dataset for robust computer vision under adverse conditions

  Viet Huy Duong, Ruoxin Xiong, Md Abdullah Al Forhad, Weishi Shi · 22 septembre 2026

  Computer-vision systems used for construction monitoring can degrade under adverse environmental and visual conditions, yet such conditions remain underrepresented in existing construction image datasets. We present ConSynth-X, a paired synthetic construction-site image dataset containing 34,199 ima…

• Cross-sector generalization of accident-process role classification in occupational accident narratives

  Aho Yapi, Pierre Latouche, Arnaud Guillin, Yan Bailly · 21 septembre 2026

  Occupational accident narratives contain valuable information about work situations, unfavourable conditions, accident events, and their consequences. Automatically structuring these narratives can facilitate large-scale accident analysis and support occupational risk prevention. However, the termin…

• GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes

  Yu Xie, Bangshu Xiong, Zhibo Rao, Rui Gan, Chongxuan Liu, Zechu Ouyang · 14 septembre 2026

  Hazardous-freight operations at petrochemical logistics nodes are safety-critical for intelligent transportation systems, yet existing vision benchmarks rarely address procedural compliance under realistic deployment constraints. In large infrastructure networks, cameras often operate under sparse r…

• Safe Learning Under Irreversible Dynamics via Asking for Help

  Benjamin Plaut, Juan Li\'evano-Karim, Hanlin Zhu, Stuart Russell · 10 septembre 2026

  Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that …

• GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI

  Zhesheng Zhang, Jiahao Lu, Wei Liu, Cong Pan, Jianhua Yang, Yixiang Chen, Hongyuan Yu, Mengqi Zhang, Kailin Lyu, Zhumin Chen, Keji He · 25 août 2026

  In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied safety by varying visual contexts or evaluating execution-time dynamics, but the complementary axis of fixing the scene and varying only the instruct…

• AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction

  Mason Smetana, Trevor Neece, Lev Khazanovich · 19 août 2026

  Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured narratives that are difficult to consult at the point of planning. A novel framework centered on large language models (LLMs) for highway construction…

• SafeSceneReason: A Multimodal Reasoning Benchmark Connecting Industrial Hazards with Accident Knowledge

  Yuanchi Zhu, Kang An, Tengyue Wang, Zhongyu Yang, Chenxu Du, Xinqi Yang, Hebao Zhu, Bokai Zhao, Tianyu Liang, Ziliang Wang, Faqiang Qian, Yunli Yang, Weiyang Shi, Qibing Ren · 11 août 2026

  Industrial-safety understanding requires more than detecting workers, equipment, and personal protective equipment. Models must also assess compliance, identify hazardous interactions, explain potential accident mechanisms, and recommend preventive actions. Existing safety datasets primarily focus o…

• ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives

  Hung Nguyen, Jaehoon Lee, Namgyun Kim, Kuan-Hao Huang · 10 août 2026

  Construction accident narratives contain rich causal information, but the evidence is often implicit, long-span, and distributed. We introduce ConstructCIE, a manually annotated dataset for Causal Information Extraction from OSHA construction accident reports. The dataset uses a hierarchical schema …

• MonitorVLM-v2: A Deployed Vision-Language Framework for Real-Time Safety Violation Detection

  Jiang Wu, Sichao Wu, Yinsong Ma, Lifang Zheng, Jingliang Duan · 4 août 2026

  Large vision--language models (VLMs) can reason step by step about complex visual scenes, but this open-ended, autoregressive chain-of-thought (CoT) approach is poorly suited to safety-critical, rule-governed settings such as industrial surveillance, where decisions must be bounded, deterministic, a…

• SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining

  Yi Cui, Zilin Wang, Yijie Xu, Qianyi Cai, Huizai Yao, Shuai Jiang, Bingzhuo Zhong, Hui Xiong · 30 juillet 2026

  Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only recognize common objects in curated images. Yet real inspection archives are redundant, long-tailed, and collected across changing sites and months. W…

• Benchmarking Large Language Models on Multi-Sensor Physical Hazard Assessment

  Faizan Iqbal · 24 juillet 2026

  We present an empirical benchmark evaluating how five large language models assess multisensor physical hazard data. Testing 60 scenarios across three categories - multi-sensor joint assessment, response proportionality, and pattern disambiguation - with 1,800 API calls at temperature 0.0, we find t…

• Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection

  Anshu Singh, Alejandro Seif · 21 juillet 2026

  Publicly shareable construction-video benchmarks remain scarce, especially for safety-critical hazards that are rare, dangerous to stage, and difficult to release. We study worker under suspended load, a relational hazard that depends on worker-load geometry and temporal persistence rather than obje…

• Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI

  Joshua A. Kroll, Andrew Smart, R. Stuart Geiger, Abigail Z. Jacobs · 17 juillet 2026

  As automated decision-making and data-driven technologies pervade society and are used to manage consequential outcomes, understanding the technology's capabilities, limitations, and attendant risks in context requires analysis of full sociotechnical systems. Sociotechnical analysis of risks in high…

• Multi-modal Rail Crossing Safety Analysis

  Paimon Goulart, Chansong Lim, N\'icolas Roque dos Santos, Yue Dong, Sheldon Peterson, Jia Chen, Evangelos E. Papalexakis · 3 juillet 2026

  Given one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is? Can we improve our ability to do so by introducing structured data (such as official accident reports) about the accident history of that crossing into our models? In this w…

• Schützen: Evaluating LLM Safety in Bulgarian and German Contexts

  Kiril Georgiev, Yuxia Wang, Dimitar Iliyanov Dimitrov, Preslav Nakov, Ivan Koychev · 11 juin 2026

  Large language models are increasingly deployed across professional domains, bringing hard-to-predict risks, including the generation of harmful or disrespectful content. Although substantial progress has been made in developing safety evaluation datasets, existing resources remain overwhelmingly En…

• Listening to the Workforce: Measuring Construction Worker Safety Attitudes from Social Media Discourse Using LLMs

  Farouq Sammour, Yuxin Zhang, Zhenyu Zhang · 4 juin 2026

  Worker safety attitudes are key determinants of whether protective practices are applied or bypassed on construction sites. Yet measuring them at scale has remained out of reach. Safety attitudes are multidimensional, vary across topics, and surface most candidly in workers' own conversations. This …

• From 3D Perception to Safety Reasoning: A Graph-Based Framework for Real-Time Underground Mine Monitoring

  Pasindu Ranasinghe, Simit Raval, Dibyayan Patra, Bikram Banerjee, Ismet Canbulat · 3 juin 2026

  Underground coal mining requires personnel and heavy equipment to operate within shared, confined, and poorly illuminated spaces where hazards such as equipment proximity violations, structural instabilities, and occluded blind spots are difficult to anticipate. Conventional monitoring systems, incl…

• AI-based Prediction of Independent Construction Safety Outcomes from Universal Attributes

  Henrietta Baker, Matthew R. Hallowell, Antoine J. -P. Tixier · 21 mai 2026

  This paper significantly improves on, and finishes to validate, an approach proposed in previous research in which safety outcomes were predicted from attributes with machine learning. Like in the original study, we use Natural Language Processing (NLP) to extract fundamental attributes from raw inc…

• Passive Construction Site Safety Monitoring via Persona-Scaffolded Adversarial Chain-of-Thought VLM Verification

  Ananth Sriram, Neel Mokaria, Rajveer Singh · 20 mai 2026

  Construction remains the deadliest industry sector in the United States, with 1,055 fatal worker injuries recorded in 2023, and the majority preventable. Existing monitoring approaches are expensive, require real-time human operators, or address only a narrow subset of violations. This paper present…

• Why Do Safety Guardrails Degrade Across Languages?

  Max Zhang, Ameen Patel, Sang T. Truong, Sanmi Koyejo · 19 mai 2026

  Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety failure. We introduce a latent variable model, a Multi-Group Item …

• Generative AI for Visualizing Highway Construction Hazards Through Synthetic Images and Temporal Sequences

  Trevor Neece, Mason Smetana, Lev Khazanovich · 13 mai 2026

  Highway construction workers face a high risk of serious injury or death. Image-based training materials depicting hazardous scenarios are essential for engaging safety instruction but remain scarce due to ethical and logistical barriers. This study develops and evaluates a generative AI methodology…

• Integrated Digital Management System for Railway Workshops: A Modular Multi-Workflow Architecture for Machine, Permit, Contract, and Incident Management

  Sharvari Kamble, Arjun Dangle, Gargi Khurud, Om Kendre, Swati Bhatt · 5 mai 2026

  Indian Railway workshops form a critical component of rolling stock maintenance infrastructure, employing more than 2.5 lakh personnel across 44 major workshops nationwide. However, safety management in many workshops still relies on fragmented manual processes, resulting in delayed approvals, incom…

• Enhancing Construction Worker Safety in Extreme Heat: A Machine Learning Approach Utilizing Wearable Technology for Predictive Health Analytics

  Syed Sajid Ullah, Amir Khan · 22 avril 2026

  Construction workers are highly vulnerable to heat stress, yet tools that translate real-time physiological data into actionable safety intelligence remain scarce. This study addresses this gap by developing and evaluating deep learning models, specifically a baseline Long Short-Term Memory (LSTM) n…

• Agentic Microphysics: A Manifesto for Generative AI Safety

  Federico Pierucci, Matteo Prandi, Marcantonio Bracale Syrnikov, Marcello Galisai, Piercosma Bisconti · 17 avril 2026

  This paper advances a methodological proposal for safety research in agentic AI. As systems acquire planning, memory, tool use, persistent identity, and sustained interaction, safety can no longer be analysed primarily at the level of the isolated model. Population-level risks arise from structured …

• Integration of Object Detection and Small VLMs for Construction Safety Hazard Identification

  Muhammad Adil, Mehmood Ahmed, Muhammad Aqib, Vicente A. Gonzalez, Gaang Lee, Qipei Mei · 8 avril 2026

  Accurate and timely identification of construction hazards around workers is essential for preventing workplace accidents. While large vision-language models (VLMs) demonstrate strong contextual reasoning capabilities, their high computational requirements limit their applicability in near real-time…