[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85233-en":3,"doc-seo-85233-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85233,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","WasteAssistant Regulation-Guided Visual Question Answering Framework for Intelligent Waste Segregation and Sustainable Management","Efficient waste segregation is essential for sustainable urban management and environmental governance, yet existing automation struggles with single-modality vision, limited contextual understanding, and weak alignment with regulations. WasteAssistant introduces a language-guided vision-AI framework combining vision-language models and multimodal large language models to perform regulation-aligned visual question answering. A new WasteVQA dataset is built with 13,500 question-answer pairs over 21 waste categories. Experiments show BLIP-based performance using BLEU and BERTScore metrics, improving source-level segregation accuracy and enabling scalable, regulatory-compliant municipal and citizen deployments.","arXiv :2607 . 10610v1 [ cs .CV] 12 Jul 2026  \nWasteAssistant: Regulation-Guided Visual Question Answering Framework for Intelligent Waste Segregation and Sustainable Management  \nKhush Katarukaa , Harshit Mauryaa , Anuja Vatsb , Murari Mandalc , Kiran Rajab , Praveen Kumar Chandaliyaa,∗  \na Sardar Vallabhbhai National Institute of Technology, Surat, 395007, Gujarat, India  \nb Norwegian University of Science and Technology, Gjøvik, Norway  \nc Kalinga Institute of Industrial Technology, Bhubaneswar, Odisha, India  \nAbstract  \nEfficient waste segregation is critical for sustainable urban management and environmental governance. Existing automated systems are limited by single-modality visual processing, insufficient contextual understanding, and weak regulatory alignment. To address these issues, we propose a language-guided vision-AI framework that integrates vision-language models and multimodal large language models for joint visual-linguistic reasoning. This framework implements a visual question answering paradigm aligned with India’s Solid Waste Management Rules 2016. We construct a new WasteVQA dataset with 13,500 question-answer pairs across 21 waste categories. Experiments show that the BLIP-based model achieves a BLEU score of 0.8291 and a BERTScore of 0.9273, outperforming traditional CNN-based methods. This work improves source-level segregation accuracy, ensures regulatory compliance, and supports scalable deployment for municipal and citizen-facing waste management, promoting multimodal AI in sustainable urban infrastructure. The source code and dataset are available at: [https:](https:)//[github.com/Khushkataruka/WasteAssistant](github.com/Khushkataruka/WasteAssistant)  \nKeywords: Vision–Language Models, Multimodal Large Language Models, Visual Question Answering, Waste Segregation, Sustainable Smart Cities  \n1. Introduction  \nEffective solid waste management has become a critical global challenge, with the world generating over 2 billion tons of municipal solid waste annually (Kaza et al., 2018) . This figure is projected to increase by 70% to 3 . 8 billion tons by 2050 (Kaza et al., 2018; UNEP, 2024) . This escalating waste crisis poses a significant threat to the environment, public health, and economic development. Improperly managed waste contributes to air, water, and soil pollution and is a major source of methane, a potent greenhouse gas. Furthermore, it can lead to the spread of diseases and respiratory problems, particularly in low-income countries where over 90%  \n∗ Corresponding author  \nEmail addresses: [u23ai112@coed.svnit.ac.in](u23ai112@coed.svnit.ac.in) (Khush Kataruka), [u23ai122@coed.svnit.ac.in](u23ai122@coed.svnit.ac.in) (Harshit Maurya), [anuja.vats@ntnu.no](anuja.vats@ntnu.no) (Anuja Vats), [murari.mandalfcs@kiit.ac.in](murari.mandalfcs@kiit.ac.in) (Murari Mandal), [kiran.raja@ntnu.no](kiran.raja@ntnu.no) (Kiran Raja), [pkc@ai.svnit.ac.in](pkc@ai.svnit.ac.in)[ ](pkc@ai.svnit.ac.in)(Praveen Kumar Chandaliya)  \n1 Source code and WasteVQA dataset are publicly available at: [https://github.com/Khushkataruka/WasteAssistant](https://github.com/Khushkataruka/WasteAssistant)  \nof waste is often disposed of in unregulated dumps or openly burned. The economic consequences are also severe, with the cost of inaction projected to exceed USD 600 billion per year by 2050 (Kaza et al., 2018) . A major contributor to this crisis is inefficient waste classification, which undermines recycling efforts, accelerates environmental degradation, and endangers both wildlife and human communities (Cheng et al., 2023) . Animals frequently ingest or come into contact with hazardous materials due to misclassified waste, leading to life-threatening health effects. Moreover, manual sorting methods are labour-intensive, error-prone, and unable to scale with growing urban demands (Gundupalliet al., 2017) .  \nTo address the pressing challenges of modern waste management, automated waste classification systems leveraging deep ","cbCair69IYbzvHhy","https://ap.wps.com/l/cbCair69IYbzvHhy","pdf",3541754,3,1,12,"English","en",105,"# Introduction\n## Problem and motivation\n## Proposed approach\n# Abstract","[{\"question\":\"What problem does WasteAssistant target in intelligent waste management?\",\"answer\":\"It targets limitations in automated waste segregation systems, especially weak contextual understanding and poor alignment with regulatory requirements.\"},{\"question\":\"How does the framework answer waste-related questions?\",\"answer\":\"It uses a language-guided vision-AI approach that combines vision-language models with multimodal large language models for joint visual-linguistic reasoning under a visual question answering setup.\"},{\"question\":\"What dataset and evaluation results are reported?\",\"answer\":\"The paper introduces the WasteVQA dataset with 13,500 question-answer pairs across 21 waste categories and reports BLEU and BERTScore results, where a BLIP-based model outperforms traditional CNN-based methods.\"}]",1784201905,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"wasteassistant-regulation-guided-visual-question-answering-framework-for-intelligent-waste-segregation-and-sustainable-management","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/wasteassistant-regulation-guided-visual-question-answering-framework-for-intelligent-waste-segregation-and-sustainable-management/85233/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does WasteAssistant target in intelligent waste management?","Question",{"text":75,"@type":76},"It targets limitations in automated waste segregation systems, especially weak contextual understanding and poor alignment with regulatory requirements.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the framework answer waste-related questions?",{"text":80,"@type":76},"It uses a language-guided vision-AI approach that combines vision-language models with multimodal large language models for joint visual-linguistic reasoning under a visual question answering setup.",{"name":82,"@type":73,"acceptedAnswer":83},"What dataset and evaluation results are reported?",{"text":84,"@type":76},"The paper introduces the WasteVQA dataset with 13,500 question-answer pairs across 21 waste categories and reports BLEU and BERTScore results, where a BLIP-based model outperforms traditional CNN-based methods.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]