{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:37Z","timestamp":1778048497312,"version":"3.51.4"},"reference-count":81,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00570","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5886-5897","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation"],"prefix":"10.1109","author":[{"given":"Liu","family":"He","sequence":"first","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhi","family":"Song","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Albert Y. C.","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Xia","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shashwat","family":"Verma","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sankalp","family":"Dayal","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Hao","family":"Kuo","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Aliaga","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Anthropic. Claude v3.0","year":"2024"},{"key":"ref2","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref4","article-title":"Allava: Harnessing gpt4v-synthesized data for a lite vision-language model","author":"Chen","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref7","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref12","article-title":"What makes for good visual instructions? synthesizing complex visual reasoning instructions for visual instruction tuning","author":"Du","year":"2023"},{"key":"ref13","article-title":"Training on synthetic data beats real data in multimodal relation extraction","author":"Du","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00048"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41676-7_21"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3242284"},{"key":"ref24","article-title":"Kubrick: Multimodal agent collaborations for synthetic video generation","author":"He","year":"2024"},{"key":"ref25","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Mmigbench: Towards comprehensive and explainable evaluation of multi-modal image generation models","author":"Hua","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref31","article-title":"Learning action and reasoning-centric image editing from videos and simulations","author":"Krojer","year":"2024"},{"key":"ref32","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024"},{"key":"ref33","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref34","author":"Li","year":"2024","journal-title":"What if we recaption billions of web images with llama-3?"},{"key":"ref35","article-title":"Stablellava: Enhanced visual instruction tuning with synthesized image-dialogue data","author":"Li","year":"2023"},{"key":"ref36","article-title":"Longperceptu-althoughts: Distilling system-2 reasoning for system-1 perception","author":"Liao","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref41","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref43","article-title":"Synthvlm: High-efficiency and high-quality synthetic data for vision language models","author":"Liu","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref45","article-title":"Generating images with 3d annotations using diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ma"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref47","volume-title":"Llama 3.2 vision","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref49","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref50","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref51","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref55","article-title":"Synth2: Boosting visual-language models with synthetic captions and image embeddings","author":"Sharifzadeh","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref57","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"ref60","article-title":"Refine-by-align: Reference-guided artifacts refinement through semantic alignment","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Song"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.893"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i48.42385"},{"key":"ref63","article-title":"Generative ai for celanimation: A survey","author":"Tang","year":"2025"},{"key":"ref64","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref66","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref67","article-title":"To see is to believe: Prompting gpt-4v for better visual instruction tuning","author":"Wang","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00351"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836101"},{"issue":"1","key":"ref71","first-page":"1","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","volume":"9","author":"Yang","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00742"},{"key":"ref75","article-title":"Newtongen: Physicsconsistent and controllable text-to-video generation via neural newtonian dynamics","author":"Yuan","year":"2025"},{"key":"ref76","author":"Yuksekgonul","year":"2022","journal-title":"When and why visionlanguage models behave like bags-of-words, and what to do about it?"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref79","article-title":"Llavar: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023"},{"key":"ref80","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492722.pdf?arnumber=11492722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:07:46Z","timestamp":1778047666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00570","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}