{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:11:05Z","timestamp":1789031465749,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370129","type":"print"},{"value":"9783032370136","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37013-6_8","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:59:19Z","timestamp":1789030759000},"page":"133-151","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SplatReasoner: Enhancing Embodied Reasoning and\u00a0Grounding by\u00a0Novel View Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1774-5442","authenticated-orcid":false,"given":"Kim","family":"Yu-Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8125-284X","authenticated-orcid":false,"given":"Dahye","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7570-6508","authenticated-orcid":false,"given":"Kim","family":"Jun-Seong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-3770","authenticated-orcid":false,"given":"Nam","family":"Hyeon-Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0224-0060","authenticated-orcid":false,"given":"GeonU","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8818-4657","authenticated-orcid":false,"given":"Yongjin","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-157X","authenticated-orcid":false,"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8978-6702","authenticated-orcid":false,"given":"Jaesung","family":"Choe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0468-1571","authenticated-orcid":false,"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"8_CR1","unstructured":"An, H., et\u00a0al.: C3G: Learning compact 3D representations with 2K gaussians. In: CVPR (2026)"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: ScanQA: 3D question answering for spatial scene understanding. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"8_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. In: arXiv preprint arXiv:2511.21631 (2025)"},{"key":"8_CR4","unstructured":"Cangea, C., Belilovsky, E., Li\u00f2, P., Courville, A.: VideoNavQA: Bridging the gap between visual and embodied question answering. In: BMVC (2019)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Kukliansy, D., Szpektor, I., Chen, X., Ding, N., Soricut, R.: All you may need for VQA are image captions. In: North American Chapter of the Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.naacl-main.142"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: Scanrefer: 3D object localization in RGB-D scans using natural language. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"8_CR7","doi-asserted-by":"publisher","first-page":"135062","DOI":"10.52202\/079017-4293","volume":"37","author":"AC Cheng","year":"2024","unstructured":"Cheng, A.C., et al.: Spatialrgpt: grounded spatial reasoning in vision-language models. Adv. Neural. Inf. Process. Syst. 37, 135062\u2013135093 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: Richly-annotated 3D reconstructions of indoor scenes. In: CVPR, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Das, A., Datta, S., Gkioxari, G., Lee, S., Parikh, D., Batra, D.: Embodied question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00008"},{"key":"8_CR10","unstructured":"Ding, J., Liu, X., Pan, Z., Long, S., Li, G.: ExtrinSplat: Decoupling geometry and semantics for open-vocabulary understanding in 3D gaussian splatting. In: CVPR (2026)"},{"key":"8_CR11","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: International Conference on Knowledge Discovery and Data Mining (KDD) (1996)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Fan, Z., Wang, K., Wen, K., Zhu, Z., Xu, D., Wang, Z., et\u00a0al.: LightGaussian: Unbounded 3D Gaussian compression with 15x reduction and 200+ fps. In: NeurIPS (2024)","DOI":"10.52202\/079017-4447"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Ge, J., et al.: V2PE: Improving multimodal long-context capability of vision-language models with variable visual position encoding. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01958"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gu, Q., et al.: ConceptGraphs: Open-vocabulary 3D scene graphs for perception and planning. IEEE International Conference on Robotics and Automation (2024)","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Q., et al.: RegionGPT: Towards region understanding vision language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13796\u201313806 (2024)","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Halacheva, A.M., Zaech, J.N., Wang, X., Paudel, D.P., Van Gool, L.: GaussianVLM: Scene-centric 3D vision-language models using language-aligned gaussian splats for embodied reasoning and beyond. IEEE Robot. Autom. Letters (2025)","DOI":"10.1109\/LRA.2025.3623037"},{"key":"8_CR17","unstructured":"He, S., et al.: ReferSplat: Referring segmentation in 3D gaussian splatting. In: ICML (2025)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Hong, Y., et al.: 3D-LLM: Injecting the 3D world into large language models. In: NeurIPS (2023)","DOI":"10.52202\/075280-0900"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Huang, H., et\u00a0al.: Chat-scene: Bridging 3D scene and large language models with object identifiers. In: NeurIPS (2024)","DOI":"10.52202\/079017-3620"},{"key":"8_CR20","unstructured":"Huang, J., et al.: An embodied generalist agent in 3D world. In: ICML (2024)"},{"key":"8_CR21","unstructured":"Hurst, A., et al.: GPT-4o system card. In: arXiv preprint (2024). arXiv:2410.21276"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: FastLGS: Speeding up language embedded gaussians with feature grid mapping. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i4.32410"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Jun-Seong, K., Kim, G., Yu-Ji, K., Wang, Y.C.F., Choe, J., Oh, T.H.: Dr. splat: Directly referring 3D gaussian splatting via direct language embedding registration. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01319"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. In: ACM TOG (2023)","DOI":"10.1145\/3592433"},{"key":"8_CR25","unstructured":"Kim, N., Kwon, O., Yoo, H., Choi, Y., Park, J., Oh, S.: Topological semantic graph memory for image-goal navigation. In: Annual Conference on Robot Learning (2022)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Lee, M.J., Gong, D., Cho, M.: Video summarization with large language models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01768"},{"key":"8_CR28","unstructured":"Lee, M., Park, Y., Hwang, D., Kim, Y., Oh, S.J., Choe, J.: Enhancing multi-image understanding through delimiter token scaling. In: ICLR (2026)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Lee, S., Wang, Z., Wang, Y., Lee, G.H.: EmbodiedSplat: Online feed-forward semantic 3DGS for open-vocabulary 3D scene understanding. In: CVPR (2026)","DOI":"10.1109\/CVPR52734.2025.01318"},{"issue":"5","key":"8_CR30","doi-asserted-by":"publisher","first-page":"4108","DOI":"10.1109\/TPAMI.2025.3538496","volume":"47","author":"X Lei","year":"2025","unstructured":"Lei, X., Wang, M., Zhou, W., Li, H.: GaussNav: Gaussian splatting for visual navigation. IEEE Trans. Pattern Anal. Mach. Intell. 47(5), 4108\u20134121 (2025)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Liao, Y.H., Mahmood, R., Fidler, S., Acuna, D.: Can large vision-language models correct semantic grounding errors by themselves? In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01367"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"8_CR34","unstructured":"Ma, X., et al.: SQA3D: Situated question answering in 3D scenes. In: ICLR (2023)"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Majumdar, A., et al.: OpenEQA: Embodied question answering in the era of foundation models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Malzer, C., Baum, M.: A hybrid approach to hierarchical density-based cluster selection. In: 2020 IEEE International Conference on multisensor fusion and integration for intelligent systems (MFI), IEEE (2020)","DOI":"10.1109\/MFI49285.2020.9235263"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Marrie, J., M\u00e9n\u00e9gaux, R., Arbel, M., Larlus, D., Mairal, J.: LUDVIG: Learning-free uplifting of 2D visual features to gaussian splatting scenes. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00698"},{"key":"8_CR38","unstructured":"OpenAI: Gpt-4 technical report. https:\/\/arxiv.org\/abs\/2303.08774 (2023)"},{"key":"8_CR39","unstructured":"OpenAI: Gpt-4v(ision) system card. https:\/\/openai.com\/research\/gpt-4v-system-card (2023)"},{"key":"8_CR40","unstructured":"Park, Y., Lee, M., Chun, S., Choe, J.: Mitigating cross-image information leakage in lvlms for multi-image tasks. arXiv preprint arXiv:2508.13744 (2025)"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., Pfister, H.: LangSplat: 3D language gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20051\u201320060 (2024)","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"8_CR42","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"8_CR43","unstructured":"Ramakrishnan, S.K., et al.: Habitat-Matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI. In: Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2021)"},{"key":"8_CR44","unstructured":"Ranasinghe, K., Li, X., Kahatapitiya, K., Ryoo, M.S.: Understanding long videos with multimodal language models. In: ICLR (2025)"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3D semantic segmentation in the wild. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"8_CR46","unstructured":"Saxena, S., et al.: GraphEQA: Using 3D semantic scene graphs for real-time embodied question answering. In: Annual Conference on Robot Learning (2025)"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Sharma, A., Saxon, M., Wang, W.Y.: Losing visual needles in image haystacks: Vision language models are easily distracted in short and long contexts. In: Findings of the Association for Computational Linguistics: EMNLP 2024 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.312"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Shi, J.C., Wang, M., Duan, H.B., Guan, S.H.: Language embedded 3D gaussians for open-vocabulary scene understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00510"},{"key":"8_CR49","unstructured":"Singh, A., et\u00a0al.: Openai GPT-5 system card. In: arXiv preprint arXiv:2601.03267 (2025)"},{"key":"8_CR50","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Varghese, R., Sambath, M.: Yolov8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS) IEEE (2024)","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: MMLongBench: Benchmarking long-context vision-language models effectively and thoroughly. In: NeurIPS (2025)","DOI":"10.52202\/085713-3627"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Wu, Y., et\u00a0al.: OpenGaussian: Towards point-level 3D gaussian-based open vocabulary understanding. In: NeurIPS (2024)","DOI":"10.52202\/079017-0604"},{"key":"8_CR54","unstructured":"Xiong, B., Liu, R., Xu, K., Chen, M., Feng, A.: Splat feature solver. In: ICLR (2026)"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., Wang, T., Chen, Y., Pang, J., Lin, D.: PointLLM: Empowering large language models to understand point clouds. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"8_CR56","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: 3D-Mem: 3D scene memory for embodied exploration and reasoning. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01612"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: Segment and edit anything in 3D scenes. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"8_CR59","doi-asserted-by":"crossref","unstructured":"Yin, H., Xu, X., Wu, Z., Zhou, J., Lu, J.: SG-NAV: Online 3D scene graph prompting for LLM-based zero-shot object navigation. In: NeurIPS (2024)","DOI":"10.52202\/079017-0171"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et al.: Osprey: Pixel understanding with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"8_CR61","unstructured":"Zeng, A., et al.: Socratic models: Composing zero-shot multimodal reasoning with language. In: ICLR (2023)"},{"key":"8_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Open-vocabulary functional 3D scene graphs for real-world indoor spaces. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01807"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: R-tuning: Instructing large language models to say \u2018i don\u2019t know\u2019. In: North American Chapter of the Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.naacl-long.394"},{"key":"8_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Gong, Z., Chang, A.X.: Multi3drefer: Grounding text description to multiple 3D objects. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"8_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Feature 3DGS: Supercharging 3D gaussian splatting to enable distilled feature fields. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"Zwicker, M., Pfister, H., Van Baar, J., Gross, M.: EWA volume splatting. In: Proceedings Visualization, (2001) VIS\u201901. IEEE","DOI":"10.1145\/383259.383300"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37013-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:59:48Z","timestamp":1789030788000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37013-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370129","9783032370136"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37013-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}