[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85314-en":3,"doc-seo-85314-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},85314,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","HierCAD: Hierarchical Text-to-CAD Design via Structure Alignment and Parameter Grounding","Recent text-to-CAD methods using large language models face two limitations: structural consistency in complex designs and reliable geometric parameter grounding. HierCAD introduces a hierarchical text-to-CAD framework that reformulates CAD generation as progressive reasoning by decomposing CAD construction trees into object-level procedural reasoning and part-level topology reasoning. A unified Structure Alignment and Parameter Grounding (SAPG) strategy aligns topology trajectories with parametric CAD spans and reduces shortcut learning via structure-preserving perturbations and ranking supervision. Experiments show improved performance on CAD sequence generation and reconstructed CAD evaluation.","arXiv :2607 . 11339v1 [ cs .CV] 13 Jul 2026  \nHierCAD: Hierarchical Text-to-CAD Design via Structure Alignment and Parameter Grounding  \nJimin Xu, Tianbao Wang, Tao Jin, and Zhou Zhao (B)  \nCollege of Computer Science and Technology, Zhejiang University, Hangzhou, China  \n[zhaozhou@zju.edu.cn](zhaozhou@zju.edu.cn)  \nAbstract. Recent text-to-CAD approaches have shown promising results by leveraging large language models, but they often struggle with maintaining structural consistency in complex designs and accurately grounding geometric parameters. To address these issues, we propose HierCAD, a hierarchical text-to-CAD framework that improves both structural reasoning and parameter prediction. HierCAD reformulates CAD generation as progressive reasoning by decomposing CAD construction trees into object-level procedural reasoning and part-level topology reasoning trajectories. To further improve generation fidelity, we introduce a unified Structure Alignment and Parameter Grounding (SAPG) learning strategy. Structure alignment aligns topology reasoning trajectories with their corresponding parametric CAD spans, while parameter grounding mitigates shortcut learning through structure-preserving parameter perturbations and ranking-based supervision. Experiments demonstrate that HierCAD outperforms prior state-of-the-art methods on both CAD sequence generation and reconstructed CAD model evaluation. Our code is available at [https://github.com/Collab-Gen/HierCAD](https://github.com/Collab-Gen/HierCAD).  \nKeywords: Text-to-CAD · Large Language Models.  \n1 Introduction  \nComputer-Aided Design (CAD) plays a crucial role in industrial design, mechanical engineering, and digital manufacturing [8] . Recent text-to-CAD approaches have shown promising results by leveraging large language models. Text2CAD [13] introduces a large-scale annotation pipeline and a transformer architecture that predicts vectorized CAD sequences from textual prompts. CADmium [6] further demonstrates that strong code LLMs [9] can be fine-tuned to directly generate JSON-formatted CAD sequences in a text-to-text fashion, significantly narrowing the gap between natural language understanding and sequential CAD design. Together, these works establish text-to-CAD as a promising research direction and show that modern generative models can recover substantial portions of CAD construction histories from language alone. However, despite these advances, accurately generating complex CAD objects from text remains far from solved.  \nOur analysis of existing methods reveals two major bottlenecks. First, current language model based approaches usually formulate CAD generation as  \n2 J. Xu et al.  \nflat autoregressive sequence prediction. This representation entangles heterogeneous information, including object composition, loop topology, and continuous geometric parameters, inside a single token stream. As a result, long-horizon procedural dependencies are difficult to maintain, especially for multi-part objects and sketches with many loops. Second, even when the coarse topology is correct, parameter prediction remains fragile. We observe that autoregressive models often rely on shortcut statistics and spuriously reuse previously generated legal values, leading to inter-field parameter confusion and intra-field parameter collapse. These errors degrade geometric fidelity and mesh quality even when the symbolic structure of the CAD sequences is largely preserved.  \nTo address these challenges, we propose HierCAD, a hierarchical text-toCAD framework that improves both structural reasoning and parameter grounding. We first reformulate hierarchical supervision. Instead of learning a flat CAD sequence directly, we disentangle the CAD construction tree into multiple reasoning layers and supervise generation through two explicit trajectories: an object-level global procedural reasoning over parts and Boolean operations, and a part-level local topology reasoning over loop primitives. Th","cbCaiiotA5IK4gfE","https://ap.wps.com/l/cbCaiiotA5IK4gfE","pdf",871852,1,15,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What are the two main bottlenecks of existing text-to-CAD approaches discussed in the paper?\",\"answer\":\"The paper identifies structural inconsistency for complex designs and fragile parameter prediction, where models may rely on shortcuts that reuse legal values incorrectly, causing parameter confusion and collapse.\"},{\"question\":\"How does HierCAD change CAD generation compared with flat autoregressive sequence prediction?\",\"answer\":\"HierCAD reformulates generation as progressive reasoning by decomposing the CAD construction tree into object-level procedural reasoning (parts and Boolean operations) and part-level topology reasoning (loop primitives).\"},{\"question\":\"What does the SAPG strategy do to improve generation fidelity?\",\"answer\":\"Structure alignment links topology reasoning trajectories to corresponding parametric CAD spans, while parameter grounding mitigates shortcut learning through structure-preserving parameter perturbations and ranking-based supervision.\"}]",1784202428,38,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"hiercad-hierarchical-text-to-cad-design-via-structure-alignment-and-parameter-grounding","",{"@graph":35,"@context":84},[36,53,67],{"@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/hiercad-hierarchical-text-to-cad-design-via-structure-alignment-and-parameter-grounding/85314/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What are the two main bottlenecks of existing text-to-CAD approaches discussed in the paper?","Question",{"text":74,"@type":75},"The paper identifies structural inconsistency for complex designs and fragile parameter prediction, where models may rely on shortcuts that reuse legal values incorrectly, causing parameter confusion and collapse.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does HierCAD change CAD generation compared with flat autoregressive sequence prediction?",{"text":79,"@type":75},"HierCAD reformulates generation as progressive reasoning by decomposing the CAD construction tree into object-level procedural reasoning (parts and Boolean operations) and part-level topology reasoning (loop primitives).",{"name":81,"@type":72,"acceptedAnswer":82},"What does the SAPG strategy do to improve generation fidelity?",{"text":83,"@type":75},"Structure alignment links topology reasoning trajectories to corresponding parametric CAD spans, while parameter grounding mitigates shortcut learning through structure-preserving parameter perturbations and ranking-based supervision.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]