[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82058-en":3,"doc-seo-82058-105":29,"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82058,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","GReFEM Multimodal LLMs as Zero Shot Semantic Assistants for Physics Guided 3D Mesh Refinement","Adaptive volumetric finite element meshing determines computational cost by concentrating resolution where physical fields vary most. Conventional workflows rely on iterative PDE solvers for error indicators or require highly supervised surrogate models trained on large simulation datasets. This study examines whether multimodal large language models can semantically ground stress critical regions in a zero shot manner using physics guided textual prompts. GReFEM localizes regions via MLLM driven view reasoning and anchors them into 3D through orthoViews, enabling mesh refinement without PDE solvers or CAD annotations.","GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement  \nKartik Bali  \nInstitute of Material Systems Modeling Helmholtz Zentrum Hereon Max-Planck-Straße 1, 21502 Geesthacht [kartik.bali@hereon.de](kartik.bali@hereon.de)  \nMahish K.Guru  \nInstitute of Material and Process Design Helmholtz Zentrum Hereon Max-Planck-Straße 1, 21502 Geesthacht [mahish.guru@hereon.de](mahish.guru@hereon.de)  \narXiv :2607 .08798v 1 [ cs .GR] 8 Jul 2026  \nChristian J Cyron  \nInstitute of Material Systems Modeling  \nHelmholtz Zentrum Hereon  \nMax-Planck-Straße 1, 21502 Geesthacht  \n[christian.cyron@hereon.de](christian.cyron@hereon.de)  \nRoland Aydin  \nData-Driven Simulation and Analysis in Materials Science German Research Center for Artificial Intelligence Campus D3 2, 66123 Saarbrücken  \n[roland.aydin@dfki.de](roland.aydin@dfki.de)  \nAbstract  \nAdaptive volumetric finite element meshing is a critical step in computer-aided engineering and analysis that dictates the computational budget of a given problem. It traditionally requires iterative PDE solvers or heavily supervised, data-driven surrogates trained on large-scale simulation data. While Multimodal Large Language Models (MLLMs) excel in 2D visual tasks, their zero-shot capability to semantically ground regions based on geometric understanding and physics remains an open question. Overall, this study explores a significant question: can the high-level semantic understanding of off-the-shelf MLLMs serve as a viable, zero-shot geometric proxy for finite element mesh refinement? To investigate this, we introduce GReFEM (Geometric Reasoning Enhanced Multimodal LLMs for Finite Element Meshing), a framework that utilizes MLLMs to visually localize stress-critical regions based on physics-guided textual prompts. To bridge the gap between 2DMLLM pre-training and 3D geometries, we introduce orthoViews, a view-selection module that maximizes the observability of key geometric features. We conduct an in-depth empirical evaluation across diverse CAD geometries, loading cases, and SOTA MLLMs, comparing them against a tuned geometric heuristic under a strict, matched refinement budget. Our findings reveal that MLLMs demonstrate robust zero-shot capacity to accurately follow complex spatial-physical instructions, isolating stress-relevant features with higher precision than blind heuristics. By mapping both the successes and current limitations of MLLMs in physical grounding, this study defines the frontier of foundation models as semantic assistants in automated simulation workflows.  \nPreprint.  \nFigure 1: GReFEM Pipeline: We process the top views V ∗ , via the Region Proposal and Feature Detection Pipelines. Once the points Q are obtained on the views, we use our Surface Projection (2D to 3D) pipeline to obtain anchor points P for mesh generation.  \n1 Introduction  \nRecent large language models (LLMs) have demonstrated strong capabilities in reasoning and visual perception, enabling their application across scientific domains that require structured spatial understanding. In particular, recent work has explored the use of LLMs for 3D CAD modeling, object generation, and geometric reasoning, leading to notable advances in design automation and shape synthesis Kienle et al. [2025], Zhou et al. [2025], Yang et al. [2023] .  \nDespite these advances, the role of LLMs in fine-grained numerical simulation workflows remains largely unexplored. High-fidelity finite element simulation fundamentally relies on discretization of the problem domain, where mesh resolution must be adaptively concentrated in regions of high physical variation. While existing approaches adapt LLMs to reason about surface meshes Wang et al.[2024], Fang et al. [2025] and CAD representations Wu et al. [2023], Alrashedy et al. [2024] of 3D objects, comparatively little work investigates their effectiveness in guiding volumetric discretization required to resolve localized physical phenomena while controll","cbCaipJVFD5WBEhW","https://ap.wps.com/l/cbCaipJVFD5WBEhW","pdf",19521071,1,35,"English","en",105,"# Abstract\n# Introduction\n## Problem motivation\n## Limitations of existing adaptive meshing and LLM adaptations\n## Proposed approach: GReFEM and orthoViews","[{\"question\":\"What problem does GReFEM address in finite element meshing?\",\"answer\":\"It addresses how to guide adaptive volumetric mesh refinement to stress critical regions without relying on PDE solver based error indicators or explicit CAD annotations.\"},{\"question\":\"How does GReFEM use multimodal LLMs for geometry and physics grounding?\",\"answer\":\"GReFEM uses multimodal large language models to visually localize stress critical regions based on physics guided textual prompts, then projects 2D inferences back into 3D as refinement anchors.\"},{\"question\":\"Why is orthoViews introduced in the framework?\",\"answer\":\"orthoViews selects views to maximize observability of key geometric features, helping bridge 2D MLLM pre training and 3D geometries for more reliable grounding and projection.\"}]",1784177884,88,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"grefem-multimodal-llms-as-zero-shot-semantic-assistants-for-physics-guided-3d-mesh-refinement","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/grefem-multimodal-llms-as-zero-shot-semantic-assistants-for-physics-guided-3d-mesh-refinement/82058/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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 GReFEM address in finite element meshing?","Question",{"text":75,"@type":76},"It addresses how to guide adaptive volumetric mesh refinement to stress critical regions without relying on PDE solver based error indicators or explicit CAD annotations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does GReFEM use multimodal LLMs for geometry and physics grounding?",{"text":80,"@type":76},"GReFEM uses multimodal large language models to visually localize stress critical regions based on physics guided textual prompts, then projects 2D inferences back into 3D as refinement anchors.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is orthoViews introduced in the framework?",{"text":84,"@type":76},"orthoViews selects views to maximize observability of key geometric features, helping bridge 2D MLLM pre training and 3D geometries for more reliable grounding and projection.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]