{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:03Z","timestamp":1788894423165,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","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\/978-3-032-37044-0_17","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:16:55Z","timestamp":1788891415000},"page":"300-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EGM: Efficient Visual Grounding Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7339-2070","authenticated-orcid":false,"given":"Guanqi","family":"Zhan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1325-2755","authenticated-orcid":false,"given":"Changye","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3632-9986","authenticated-orcid":false,"given":"Zhijian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9057-5817","authenticated-orcid":false,"given":"Yi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-7618","authenticated-orcid":false,"given":"Song","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6969-1706","authenticated-orcid":false,"given":"Ligeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"17_CR1","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"17_CR2","unstructured":"Alibaba: Qwen3-vl (2025)"},{"key":"17_CR3","unstructured":"Anthropic: Claude-4.5 (2025)"},{"key":"17_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"17_CR5","unstructured":"Beyer, L., et al.: Paligemma: a versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"issue":"2","key":"17_CR6","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1111\/j.1468-0114.2011.01393.x","volume":"92","author":"RE Briscoe","year":"2011","unstructured":"Briscoe, R.E.: Mental imagery and the varieties of amodal perception. Pac. Philos. Q. 92(2), 153\u2013173 (2011)","journal-title":"Pac. Philos. Q."},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Chen, K., Ramanan, D., Khurana, T.: Using diffusion priors for video amodal segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.02131"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"17_CR9","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"17_CR10","unstructured":"Deitke, M., et al.: Molmo and pixmo: open weights and open data for state-of-the-art vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Evans, T., Parthasarathy, N., Merzic, H., Henaff, O.J.: Data curation via joint example selection further accelerates multimodal learning. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) (2024)","DOI":"10.52202\/079017-4485"},{"key":"17_CR12","unstructured":"Gemini Robotics Team: Gemini robotics: bringing AI into the physical world. arXiv preprint arXiv:2503.20020 (2025)"},{"key":"17_CR13","unstructured":"Grattafiori, A., et al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"17_CR14","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"17_CR15","unstructured":"Hsieh, C.Y., Khurana, T., Dave, A., Ramanan, D.: Tracking any object amodally. arXiv preprint arXiv:2312.12433 (2023)"},{"key":"17_CR16","unstructured":"Hurst, A., et al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"issue":"2","key":"17_CR17","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s00426-023-01878-w","volume":"88","author":"B Kaup","year":"2024","unstructured":"Kaup, B., et al.: Modal and amodal cognition: an overarching principle in various domains of psychology. Psychol. Res. 88(2), 307\u2013337 (2024)","journal-title":"Psychol. Res."},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with paged attention. In: Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"17_CR21","unstructured":"Li, B., et\u00a0al.: Llava-onevision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Li, K., Malik, J.: Amodal instance segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46475-6_42"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Li, Z., Lavreniuk, M., Shi, J., Bhat, S.F., Wonka, P.: Amodal depth anything: amodal depth estimation in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)","DOI":"10.1109\/ICCV51701.2025.00902"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Ye, W., Jiang, T., Huang, T.: 2D amodal instance segmentation guided by 3D shape prior. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19818-2_10"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Li, Z., Ye, W., Jiang, T., Huang, T.: Gin: generative invariant shape prior for amodal instance segmentation. IEEE Trans. Multimedia (MM) (2023)","DOI":"10.1109\/TMM.2023.3318075"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Muva: a new large-scale benchmark for multi-view amodal instance segmentation in the shopping scenario. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.02148"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., Han, S.: Vila: on pretraining for visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Qiao, L., Chu, X., Ma, L., Jiang, T.: Towards efficient foundation model for zero-shot amodal segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.01886"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Nvila: efficient frontier visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.00390"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Lu, R., et al.: Taco: taming diffusion for in-the-wild video amodal completion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)","DOI":"10.1109\/ICCV51701.2025.01266"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"17_CR32","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Sheng, G., et al.: Hybridflow: a flexible and efficient RLHF framework. In: Proceedings of the Twentieth European Conference on Computer Systems (2025)","DOI":"10.1145\/3689031.3696075"},{"key":"17_CR34","unstructured":"Tan, H., et al.: Gtpo and grpo-s: token and sequence-level reward shaping with policy entropy. arXiv preprint arXiv:2508.04349 (2025)"},{"key":"17_CR35","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"17_CR36","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"17_CR37","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"17_CR38","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"17_CR39","unstructured":"Wang, P., et\u00a0al.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"17_CR40","unstructured":"Wang, W., et al.: Internvl3. 5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Wu, T., Zheng, C., Guan, F., Vedaldi, A., Cham, T.J.: Amodal3r: Amodal 3D reconstruction from occluded 2D images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)","DOI":"10.1109\/ICCV51701.2025.00858"},{"key":"17_CR42","unstructured":"xAI: Grok-4 (2025)"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Xu, K., Zhang, L., Shi, J.: Amodal completion via progressive mixed context diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00869"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Yu, Q., et\u00a0al.: Dapo: an open-source LLM reinforcement learning system at scale. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/085713-3775"},{"key":"17_CR45","unstructured":"Zhan, G., et al.: EGM: efficient visual grounding language models. arXiv preprint arXiv:2601.13633 (2026)"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Zhan, G., Liu, Y., Han, K., Xie, W., Zisserman, A.: ELIP: enhanced visual-language foundation models for image retrieval. In: Proceedings of the IEEE International Conference on Content-Based Multimedia Indexing (CBMI) (2025)","DOI":"10.1109\/CBMI66578.2025.11339290"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Zhan, G., Zheng, C., Xie, W., Zisserman, A.: Amodal ground truth and completion in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02645"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Zhan, X., Pan, X., Dai, B., Liu, Z., Lin, D., Loy, C.C.: Self-supervised scene deocclusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00384"},{"key":"17_CR49","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Tian, Y., Metaxas, D., Doll\u00e1r, P.: Semantic amodal segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.320"}],"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\/978-3-032-37044-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:17:04Z","timestamp":1788891424000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_17","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":"9 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"}}]}}