{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:57Z","timestamp":1784268417451,"version":"3.55.0"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B6013"],"award-info":[{"award-number":["U24B6013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202406020139"],"award-info":[{"award-number":["202406020139"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01305","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14061-14072","source":"Crossref","is-referenced-by-count":4,"title":["MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh"],"prefix":"10.1109","author":[{"given":"Shuangkang","family":"Fang","sequence":"first","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I-Chao","family":"Shen","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Hsuan","family":"Tsai","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"StepFun"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuchang","family":"Zhou","sequence":"additional","affiliation":[{"name":"StepFun"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenrui","family":"Ding","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeo","family":"Igarashi","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"UC Merced"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Polydiff: Generating 3d polygonal meshes with diffusion models","author":"Alliegro","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Palm 2 technical report","author":"Anil","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Deepseek 1lm: Scaling opensource language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3080"},{"key":"ref9","article-title":"Meshanything: Artist-created mesh generation with autoregressive transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Meshany-thing v2: Artist-created mesh generation with adjacent mesh tokenization","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Grounded 3d-llm with referent tokens","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"issue":"240","key":"ref13","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00572"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.183"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01315"},{"key":"ref19","first-page":"3499","article-title":"Efficient implicit sdf and color reconstruction via shared feature field","volume-title":"In Proceedings of the Asian Conference on Computer Vision","author":"Fang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_12"},{"key":"ref21","article-title":"Scene-llm: Extending language model for 3d visual understanding and reasoning","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681488"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref24","first-page":"arXiv2407","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref25","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"3dgen: Triplane latent diffusion for textured mesh generation","author":"Gupta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301126"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413889"},{"key":"ref31","article-title":"Meshtron: High-fidelity, artist-like 3d mesh generation at scale","author":"Hao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref35","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Scaling laws for neural language models","author":"Kaplan","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-4399-5_13"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3533375"},{"key":"ref40","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"In Text Summarization Branches out"},{"key":"ref41","article-title":"Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447027"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"ref48","first-page":"1","article-title":"Using an 11 m to help with code understanding","volume-title":"In Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering","author":"Nam"},{"key":"ref49","first-page":"7220","article-title":"Polygen: An autoregressive generative model of 3d meshes","volume-title":"In International Conference on Machine Learning","author":"Nash"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref53","article-title":"Can large language models understand symbolic graphics programs?","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Qiu"},{"issue":"8","key":"ref54","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International Conference on Machine Learning","author":"Radford"},{"key":"ref56","volume-title":"Improved aesthetic predictor","author":"Schuhmann","year":"2022"},{"key":"ref57","article-title":"Llasm: Large language and speech model","author":"Shu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref59","article-title":"Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"Sun","year":"2021","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref64","article-title":"Llama-mesh: Unifying 3d mesh generation with language models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Pivotmesh: Generic 3d mesh generation via pivot vertices guidance","author":"Weng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01036"},{"key":"ref67","article-title":"Bloom: A 176b-parameter open-access multilingual language model","volume-title":"arXiv preprint","author":"Workshop","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02206"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref70","article-title":"Sampart3d: Segment any part in 3d objects","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3535389"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.213"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445454.pdf?arnumber=11445454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:28:04Z","timestamp":1777530484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01305","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}