{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T17:03:38Z","timestamp":1790442218459,"version":"4.1.0"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369680","type":"print"},{"value":"9783032369697","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\/978-3-032-36969-7_21","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:18:10Z","timestamp":1789251490000},"page":"380-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Spatial Trace with\u00a0Reasoning in\u00a0Vision-Language Models for\u00a0Robotics"],"prefix":"10.1007","author":[{"given":"Enshen","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingkun","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanyu","family":"Rong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengzhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuheng","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huajie","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanghang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"21_CR1","unstructured":"Abdolmaleki, A., et al.: Gemini robotics 1.5: Pushing the frontier of generalist robots with advanced embodied reasoning, thinking, and motion transfer. arXiv preprint arXiv:2510.03342 (2025)"},{"key":"21_CR2","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv (2023)"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"An, J., et al.: Agfsync: Leveraging ai-generated feedback for preference optimization in text-to-image generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 1746\u20131754 (2025)","DOI":"10.1609\/aaai.v39i2.32168"},{"key":"21_CR4","unstructured":"Anthropic, A.: The claude 3 model family: Opus, sonnet, haiku. Claude-3 Model Card 1, \u00a01 (2024)"},{"key":"21_CR5","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv (2025)"},{"key":"21_CR6","unstructured":"Bai, S., et\u00a0al.: Latent reasoning vla: Latent thinking and prediction for vision-language-action models. arXiv preprint arXiv:2602.01166 (2026)"},{"key":"21_CR7","unstructured":"Bai, Y., et\u00a0al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv (2022)"},{"key":"21_CR8","unstructured":"Black, K., et\u00a0al.: $$\\pi _0$$: A vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Cai, W., et al.: Spatialbot: Precise spatial understanding with vision language models. In: ICRA (2025)","DOI":"10.1109\/ICRA55743.2025.11128671"},{"key":"21_CR10","unstructured":"Cai, Z., et al.: Depthlm: Metric depth from vision language models. arXiv preprint arXiv:2509.25413 (2025)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Spatialvlm: Endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Chen, P., et al.: Sd-vlm: Spatial measuring and understanding with depth-encoded vision-language models. arXiv preprint arXiv:2509.17664 (2025)","DOI":"10.52202\/085713-1140"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Chen, P., et al.: Sd-vlm: Spatial measuring and understanding with depth-encoded vision-language models (2025). https:\/\/arxiv.org\/abs\/2509.17664","DOI":"10.52202\/085713-1140"},{"key":"21_CR14","unstructured":"Chen, T., et\u00a0al.: Robotwin 2.0: A scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation. arXiv preprint arXiv:2506.18088 (2025)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Rh20t-p: A primitive-level robotic dataset towards composable generalization agents. arXiv preprint arXiv:2403.19622 (2024)","DOI":"10.1109\/IROS60139.2025.11246228"},{"key":"21_CR16","unstructured":"Chen, Z., et al.: Think with 3d: Geometric imagination grounded spatial reasoning from limited views. arXiv preprint arXiv:2510.18632 (2025)"},{"key":"21_CR17","unstructured":"Cheng, A.C., et al.: 3d aware region prompted vision language model. arXiv preprint arXiv:2509.13317 (2025)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: Spatialrgpt: Grounded spatial reasoning in vision language models. In: NeurIPS (2024)","DOI":"10.52202\/079017-4293"},{"key":"21_CR19","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":"21_CR20","unstructured":"contributors, A.W.C.: Agibot world colosseum. https:\/\/github.com\/OpenDriveLab\/AgiBot-World (2024)"},{"key":"21_CR21","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 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Daxberger, E., et al.: Mm-spatial: Exploring 3d spatial understanding in multimodal llms. arXiv (2025)","DOI":"10.1109\/ICCV51701.2025.00694"},{"key":"21_CR23","doi-asserted-by":"crossref","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 Computer Vision and Pattern Recognition Conference, pp. 91\u2013104 (2025)","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Du, M., Wu, B., Li, Z., Huang, X.J., Wei, Z.: Embspatial-bench: Benchmarking spatial understanding for embodied tasks with large vision-language models. In: ACL (Volume 2: Short Papers) (2024)","DOI":"10.18653\/v1\/2024.acl-short.33"},{"key":"21_CR25","unstructured":"Fan, Z., et\u00a0al.: Vlm-3r: Vision-language models augmented with instruction-aligned 3d reconstruction. arXiv preprint arXiv:2505.20279 (2025)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Blink: Multimodal large language models can see but not perceive. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"21_CR27","unstructured":"Han, Y., et al.: Tiger: Tool-integrated geometric reasoning in vision-language models for robotics. arXiv preprint arXiv:2510.07181 (2025)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Huang, C.P., Wu, Y.H., Chen, M.H., Wang, Y.C.F., Yang, F.E.: Thinkact: Vision-language-action reasoning via reinforced visual latent planning. arXiv:2507.16815 arXiv preprint (2025)","DOI":"10.52202\/085713-2773"},{"key":"21_CR29","unstructured":"Ji, Y., et\u00a0al.: Prm-as-a-judge: A dense evaluation paradigm for fine-grained robotic auditing. arXiv preprint arXiv:2603.21669 (2026)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Ji, Y., et\u00a0al.: Robobrain: A unified brain model for robotic manipulation from abstract to concrete. arXiv preprint arXiv:2502.21257 (2025)","DOI":"10.1109\/CVPR52734.2025.00168"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Kang, L., et al.: Viki-r: Coordinating embodied multi-agent cooperation via reinforcement learning. arXiv preprint arXiv:2506.09049 (2025)","DOI":"10.52202\/085713-3935"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Keetha, N., et al.: Mapanything: Universal feed-forward metric 3d reconstruction. arXiv preprint arXiv:2509.13414 (2025)","DOI":"10.1109\/3DV69130.2026.00054"},{"key":"21_CR33","unstructured":"Khazatsky, A., et al.: Droid: A large-scale in-the-wild robot manipulation dataset. arXiv preprint arXiv:2403.12945 (2024)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. IJCV (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Lazarow, J., Griffiths, D., Kohavi, G., Crespo, F., Dehghan, A.: Cubify anything: Scaling indoor 3d object detection. arXiv preprint arXiv:2412.04458 (2024)","DOI":"10.1109\/CVPR52734.2025.02070"},{"key":"21_CR36","unstructured":"Lee, J., et\u00a0al.: Molmoact: Action reasoning models that can reason in space. arXiv preprint arXiv:2508.07917 (2025)"},{"key":"21_CR37","unstructured":"Li, B., et al.: LLaVA-onevision: Easy visual task transfer. Trans. Mach. Learn. Res. (2025)"},{"key":"21_CR38","unstructured":"Li, Y., et\u00a0al.: Hamster: Hierarchical action models for open-world robot manipulation. arXiv preprint arXiv:2502.05485 (2025)"},{"key":"21_CR39","unstructured":"Li, Z., et\u00a0al.: Do you have freestyle? expressive humanoid locomotion via audio control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 956\u2013965 (2026)"},{"key":"21_CR40","unstructured":"Li, Z., et\u00a0al.: Robomirror: Understand before you imitate for video to humanoid locomotion. arXiv preprint arXiv:2512.23649 (2025)"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Liao, Y.H., Mahmood, R., Fidler, S., Acuna, D.: Reasoning paths with reference objects elicit quantitative spatial reasoning in large vision-language models (2024). https:\/\/arxiv.org\/abs\/2409.09788","DOI":"10.18653\/v1\/2024.emnlp-main.947"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Liu, F., Emerson, G., Collier, N.: Visual spatial reasoning. Trans. Assoc. Comput. Linguist. (2023)","DOI":"10.1162\/tacl_a_00566"},{"key":"21_CR43","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning. In: ICLR (2024)"},{"key":"21_CR44","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":"21_CR45","unstructured":"Liu, M., et al.: Sapave: Towards active perception and manipulation in vision-language action models for robotics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 37164\u201337174 (2026)"},{"key":"21_CR46","unstructured":"Liu, Y., et al.: Seg-zero: Reasoning-chain guided segmentation via cognitive reinforcement, arXiv (2025)"},{"key":"21_CR47","unstructured":"Liu, Z., et al.: Nvila: Efficient frontier visual language models. arXiv (2024)"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Visual-rft: Visual reinforcement fine-tuning. arXiv (2025)","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Lu, X., et al.: Is-bench: Evaluating interactive safety of vlm-driven embodied agents in daily household tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 35680\u201335688 (2026)","DOI":"10.1609\/aaai.v40i42.40880"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Lu, X., et al.: Homeguard: Vlm-based embodied safeguard for identifying contextual risk in household task. arXiv preprint arXiv:2603.14367 (2026)","DOI":"10.1007\/978-3-032-37577-3_26"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Mao, Y., et al.: Spatiallm: Training large language models for structured indoor modeling. arXiv preprint arXiv:2506.07491 (2025)","DOI":"10.52202\/085713-1504"},{"key":"21_CR52","unstructured":"Niu, D., et al.: Llarva: Vision-action instruction tuning enhances robot learning. arXiv preprint arXiv:2406.11815 (2024)"},{"key":"21_CR53","unstructured":"Qin, Y., et\u00a0al.: Worldsimbench: Towards video generation models as world simulators. arXiv preprint arXiv:2410.18072 (2024)"},{"key":"21_CR54","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: Mp5: A multi-modal open-ended embodied system in minecraft via active perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16307\u201316316 (2024)","DOI":"10.1109\/CVPR52733.2024.01543"},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: Your language model is secretly a reward model. In: NeurIPS (2023)","DOI":"10.52202\/075280-2338"},{"key":"21_CR56","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv (2024)"},{"key":"21_CR57","unstructured":"Shen, H., et\u00a0al.: Vlm-r1: A stable and generalizable r1-style large vision-language model. arXiv preprint arXiv:2504.07615 (2025)"},{"key":"21_CR58","doi-asserted-by":"crossref","unstructured":"Song, C.H., Blukis, V., Tremblay, J., Tyree, S., Su, Y., Birchfield, S.: Robospatial: Teaching spatial understanding to 2d and 3d vision-language models for robotics. CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"21_CR59","unstructured":"Sun, P., et\u00a0al.: Spacevista: All-scale visual spatial reasoning from mm to km. arXiv preprint arXiv:2510.09606 (2025)"},{"key":"21_CR60","unstructured":"Tan, H., et\u00a0al.: Roboos-next: A unified memory-based framework for lifelong, scalable, and robust multi-robot collaboration. arXiv preprint arXiv:2510.26536 (2025)"},{"key":"21_CR61","unstructured":"Tan, H., et\u00a0al.: Roboos: A hierarchical embodied framework for cross-embodiment and multi-agent collaboration. arXiv preprint arXiv:2505.03673 (2025)"},{"key":"21_CR62","doi-asserted-by":"crossref","unstructured":"Tan, H., et al.: Reason-rft: Reinforcement fine-tuning for visual reasoning. arXiv (2025)","DOI":"10.52202\/085713-0204"},{"key":"21_CR63","unstructured":"Tan, H., et\u00a0al.: Robobrain 2.5: Depth in sight, time in mind. arXiv preprint arXiv:2601.14352 (2026)"},{"key":"21_CR64","unstructured":"Team, B.R., et\u00a0al.: Robobrain 2.0 technical report. arXiv preprint arXiv:2507.02029 (2025)"},{"key":"21_CR65","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv (2023)"},{"key":"21_CR66","unstructured":"Team, G.R., et al.: Gemini robotics: Bringing ai into the physical world. arXiv (2025)"},{"key":"21_CR67","unstructured":"Team, Q.: Qwen3 technical report (2025). https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"21_CR68","doi-asserted-by":"crossref","unstructured":"Tong, P., et\u00a0al.: Cambrian-1: A fully open, vision-centric exploration of multimodal llms. In: NeurIPS (2024)","DOI":"10.52202\/079017-2771"},{"key":"21_CR69","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: Vggt: Visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"21_CR70","unstructured":"Wang, Y., et\u00a0al.: Towards cross-view point correspondence in vision-language models. arXiv preprint arXiv:2512.04686 (2025)"},{"key":"21_CR71","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv (2021)"},{"key":"21_CR72","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, F., Hung, Y.H., Duan, Y.: Spatial-mllm: Boosting mllm capabilities in visual-based spatial intelligence. arXiv preprint arXiv:2505.23747 (2025)","DOI":"10.52202\/085713-0457"},{"key":"21_CR73","unstructured":"Xu, R., et\u00a0al.: A0: An affordance-aware hierarchical model for general robotic manipulation. arXiv preprint arXiv:2504.12636 (2025)"},{"key":"21_CR74","unstructured":"Yang, G., et\u00a0al.: Vlaser: Vision-language-action model with synergistic embodied reasoning. arXiv preprint arXiv:2510.11027 (2025)"},{"key":"21_CR75","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Magma: A foundation model for multimodal ai agents. arXiv (2025)","DOI":"10.1109\/CVPR52734.2025.01325"},{"key":"21_CR76","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: R1-onevision: Advancing generalized multimodal reasoning through cross-modal formalization. arXiv (2025)","DOI":"10.1109\/ICCV51701.2025.00229"},{"key":"21_CR77","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"21_CR78","unstructured":"Yuan, W., et al.: Robopoint: A vision-language model for spatial affordance prediction for robotics. arXiv preprint arXiv:2406.10721 (2024)"},{"key":"21_CR79","unstructured":"Yuan, Y., et al.: From seeing to doing: Bridging reasoning and decision for robotic manipulation. arXiv preprint arXiv:2505.08548 (2025)"},{"key":"21_CR80","unstructured":"Yuan, Y., et al.: Embodied-r1: Reinforced embodied reasoning for general robotic manipulation. arXiv preprint arXiv:2508.13998 (2025)"},{"key":"21_CR81","unstructured":"Yuan, Y., et al.: Embodied-r1: Reinforced embodied reasoning for general robotic manipulation (2025). https:\/\/arxiv.org\/abs\/2508.13998"},{"key":"21_CR82","unstructured":"Zhan, Y., et al.: Vision-r1: Evolving human-free alignment in large vision-language models via vision-guided reinforcement learning. arXiv (2025)"},{"key":"21_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, J., Chen, K., Lu, Z., Zhou, E., Yu, Q., Zhang, J.: Prune4web: Dom tree pruning programming for web agent. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a040, pp. 34710\u201334718 (2026)","DOI":"10.1609\/aaai.v40i41.40772"},{"key":"21_CR84","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: R1-vl: Learning to reason with multimodal large language models via step-wise group relative policy optimization. arXiv (2025)","DOI":"10.1109\/ICCV51701.2025.00181"},{"key":"21_CR85","unstructured":"Zhang, Z., et\u00a0al.: Think3d: Thinking with space for spatial reasoning. arXiv preprint arXiv:2601.13029 (2026)"},{"key":"21_CR86","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Li, Y., Wang, L.: Learning from videos for 3d world: Enhancing mllms with 3d vision geometry priors. arXiv preprint arXiv:2505.24625 (2025)","DOI":"10.52202\/085713-0693"},{"key":"21_CR87","unstructured":"Zheng, R., et al.: Tracevla: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies. arXiv preprint arXiv:2412.10345 (2024)"},{"key":"21_CR88","doi-asserted-by":"crossref","unstructured":"Zhou, C., et\u00a0al.: Lima: Less is more for alignment. In: NeurIPS (2023)","DOI":"10.52202\/075280-2400"},{"key":"21_CR89","doi-asserted-by":"crossref","unstructured":"Zhou, E., et\u00a0al.: Roborefer: Towards spatial referring with reasoning in vision-language models for robotics. arXiv preprint arXiv:2506.04308 (2025)","DOI":"10.52202\/085713-0957"},{"key":"21_CR90","unstructured":"Zhou, E., et al.: Minedreamer: Learning to follow instructions via chain-of-imagination for simulated-world control. arXiv preprint arXiv:2403.12037 (2024)"},{"key":"21_CR91","doi-asserted-by":"crossref","unstructured":"Zhou, E., et al.: Chain-of-imagination for reliable instruction following in decision making. In: 2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10010\u201310017. IEEE (2025)","DOI":"10.1109\/IROS60139.2025.11246335"},{"key":"21_CR92","doi-asserted-by":"crossref","unstructured":"Zhou, E., et al.: Code-as-monitor: Constraint-aware visual programming for reactive and proactive robotic failure detection. arXiv preprint arXiv:2412.04455 (2024)","DOI":"10.1109\/CVPR52734.2025.00649"}],"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\/978-3-032-36969-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:18:22Z","timestamp":1789251502000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36969-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369680","9783032369697"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36969-7_21","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":"13 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"}}]}}