{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:18Z","timestamp":1788937578457,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","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\/978-3-032-37359-5_2","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:55Z","timestamp":1788934075000},"page":"20-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeCoPatch: Revealing Causal Latent Subspaces in\u00a0Vision-Language Models for\u00a0GUI Grounding"],"prefix":"10.1007","author":[{"given":"Yongkang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjia","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhimin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duo","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"2_CR1","unstructured":"Agrawal, P., et al.: Pixtral 12b. arXiv preprint arXiv:2410.07073 (2024)"},{"key":"2_CR2","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond (2023). https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"2_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"2_CR4","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"2_CR5","unstructured":"Chen, L., et\u00a0al.: Ui-ins: enhancing gui grounding with multi-perspective instruction-as-reasoning. arXiv preprint arXiv:2510.20286 (2025)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites (2024). https:\/\/arxiv.org\/abs\/2404.16821","DOI":"10.1007\/s11432-024-4231-5"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Cheng, K., et al.: Seeclick: harnessing gui grounding for advanced visual gui agents. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 9313\u20139332. Association for Computational Linguistics, Bangkok (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.505. https:\/\/aclanthology.org\/2024.acl-long.505\/","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"2_CR8","doi-asserted-by":"publisher","unstructured":"Dai, D., Dong, L., Hao, Y., Sui, Z., Chang, B., Wei, F.: Knowledge neurons in pretrained transformers. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 8493\u20138502. Association for Computational Linguistics, Dublin (2022).https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.581. https:\/\/aclanthology.org\/2022.acl-long.581\/","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"2_CR9","unstructured":"Du, Y., et al.: Test-time reinforcement learning for gui grounding via region consistency. arXiv preprint arXiv:2508.05615 (2025)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Y., Zhao, H., Zhang, R., Shen, Y., Wang, X.E., Wu, G.: Gui-bee: align gui action grounding to novel environments via autonomous exploration. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 33249\u201333266 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1688"},{"key":"2_CR11","unstructured":"Fang, J., et al.: Alphaedit: null-space constrained model editing for language models. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=HvSytvg3Jh"},{"key":"2_CR12","unstructured":"Gao, C., Chen, H., Xiao, C., Chen, Z., Liu, Z., Sun, M.: H-neurons: on the existence, impact, and origin of hallucination-associated neurons in llms (2025). https:\/\/arxiv.org\/abs\/2512.01797"},{"key":"2_CR13","unstructured":"Gao, M., et al.: Generalist virtual agents: a survey on autonomous agents across digital platforms. arXiv preprint arXiv:2411.10943 (2024)"},{"key":"2_CR14","unstructured":"Gou, B., et al.: Navigating the digital world as humans do: universal visual grounding for GUI agents. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=kxnoqaisCT"},{"key":"2_CR15","unstructured":"Gu, Z., et\u00a0al.: Ui-venus technical report: building high-performance ui agents with rft. arXiv preprint arXiv:2508.10833 (2025)"},{"key":"2_CR16","unstructured":"Hong, W., et al.: Glm-4.5 v and glm-4.1 v-thinking: towards versatile multimodal reasoning with scalable reinforcement learning. arXiv preprint arXiv:2507.01006 (2025)"},{"key":"2_CR17","unstructured":"Hu, X., et al.: Os agents: a survey on mllm-based agents for general computing devices use. arXiv preprint arXiv:2508.04482 (2025)"},{"key":"2_CR18","unstructured":"Kang, L., et al.: Learning with challenges: adaptive difficulty-aware data generation for mobile gui agent training. arXiv preprint arXiv:2601.22781 (2026)"},{"key":"2_CR19","unstructured":"Leung, H.F., Xi, X., Zuo, F.: Androidcontrol-curated: revealing the true potential of gui agents through benchmark purification (2025). https:\/\/arxiv.org\/abs\/2510.18488"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Screenspot-pro: gui grounding for professional high-resolution computer use. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 8778\u20138786 (2025)","DOI":"10.1145\/3746027.3755688"},{"key":"2_CR21","unstructured":"Li, W., et al.: How auxiliary reasoning unleashes gui grounding in vlms. arXiv preprint arXiv:2509.11548 (2025)"},{"key":"2_CR22","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023). https:\/\/arxiv.org\/abs\/2304.08485"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhang, X., Zhang, Z., Lu, Y.: Ui-e2i-synth: advancing gui grounding with large-scale instruction synthesis. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 15668\u201315684 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.809"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Luo, T., Logeswaran, L., Johnson, J., Lee, H.: Visual test-time scaling for gui agent grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19989\u201319998 (2025)","DOI":"10.1109\/ICCV51701.2025.01859"},{"key":"2_CR25","unstructured":"Qin, Y., et\u00a0al.: Ui-tars: pioneering automated gui interaction with native agents. arXiv preprint arXiv:2501.12326 (2025)"},{"key":"2_CR26","unstructured":"Rawles, C., et al.: Androidworld: a dynamic benchmarking environment for autonomous agents. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=il5yUQsrjC"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., Wen, K., Zhang, Z., Hou, L., Liu, Z., Li, J.: Finding skill neurons in pre-trained transformer-based language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 11132\u201311152 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.765"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Wu, Q., et\u00a0al.: Gui-actor: coordinate-free visual grounding for gui agents. arXiv preprint arXiv:2506.03143 (2025)","DOI":"10.52202\/085713-0508"},{"key":"2_CR29","unstructured":"Wu, Z., et al.: OS-ATLAS: a foundation action model for generalist GUI agents (2024). https:\/\/arxiv.org\/abs\/2410.23218"},{"issue":"3","key":"2_CR30","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1109\/TPAMI.2025.3630635","volume":"48","author":"L Xiao","year":"2026","unstructured":"Xiao, L., Yang, X., Lan, X., Wang, Y., Xu, C.: Toward visual grounding: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 48(3), 2749\u20132771 (2026). https:\/\/doi.org\/10.1109\/TPAMI.2025.3630635","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Xie, T., et al.: Scaling computer-use grounding via user interface decomposition and synthesis. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2025). https:\/\/openreview.net\/forum?id=FS0voKxELr","DOI":"10.52202\/085713-0817"},{"key":"2_CR32","unstructured":"Yang, J., Zhang, H., Li, F., Zou, X., Li, C., Gao, J.: Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V (2023). https:\/\/arxiv.org\/abs\/2310.11441"},{"key":"2_CR33","unstructured":"Yang, J., Xiong, T., Qian, S., Nahrstedt, K., Wu, M.: Circuit tracing in vision-language models: understanding the internal mechanisms of multimodal thinking. arXiv preprint arXiv:2602.20330 (2026)"},{"key":"2_CR34","unstructured":"Yang, Q., Bi, W., Shen, H., Guo, Y., Ma, Y.: Pixelweb: the first web gui dataset with pixel-wise labels. arXiv preprint arXiv:2504.16419 (2025)"},{"key":"2_CR35","unstructured":"Yang, Y., et\u00a0al.: Gta1: Gui test-time scaling agent. arXiv preprint arXiv:2507.05791 (2025)"},{"key":"2_CR36","doi-asserted-by":"publisher","unstructured":"You, K., et al.: Ferret-ui: grounded mobile ui understanding with multimodal llms. In: European Conference on Computer Vision, pp. 240\u2013255. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73039-9_14","DOI":"10.1007\/978-3-031-73039-9_14"},{"key":"2_CR37","unstructured":"Yu, Z., Lee, Y.J.: How multimodal llms solve image tasks: a lens on visual grounding, task reasoning, and answer decoding. arXiv preprint arXiv:2508.20279 (2025)"},{"key":"2_CR38","unstructured":"Zhang, C., et\u00a0al.: Large language model-brained gui agents: a survey. arXiv preprint arXiv:2411.18279 (2024)"},{"key":"2_CR39","unstructured":"Zhang, F., Nanda, N.: Towards best practices of activation patching in language models: metrics and methods. In: International Conference on Learning Representations, vol. 2024, pp. 1651\u20131678 (2024)"},{"key":"2_CR40","doi-asserted-by":"publisher","unstructured":"Zhang, H., et\u00a0al.: Llava-grounding: grounded visual chat with large multimodal models. In: European Conference on Computer Vision. pp. 19\u201335. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72775-7_2","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"2_CR41","unstructured":"Zhang, S., et\u00a0al.: Hyperclick: advancing reliable gui grounding via uncertainty calibration. arXiv preprint arXiv:2510.27266 (2025)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Mpdrive: improving spatial understanding with marker-based prompt learning for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12089\u201312099 (2025)","DOI":"10.1109\/CVPR52734.2025.01129"},{"key":"2_CR43","unstructured":"Zheng, B., Gou, B., Kil, J., Sun, H., Su, Y.: Gpt-4v (ision) is a generalist web agent, if grounded. In: Proceedings of the 41st International Conference on Machine Learning, pp. 61349\u201361385 (2024)"},{"key":"2_CR44","doi-asserted-by":"publisher","unstructured":"Zhu, K., et al.: Guiding medical vision-language models with diverse visual prompts: framework design and comprehensive exploration of prompt variations. In: Chiruzzo, L., Ritter, A., Wang, L. (eds.) Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1: Long Papers, pp. 11726\u201311739. Association for Computational Linguistics, Albuquerque (2025). https:\/\/doi.org\/10.18653\/v1\/2025.naacl-long.587. https:\/\/aclanthology.org\/2025.naacl-long.587\/","DOI":"10.18653\/v1\/2025.naacl-long.587"}],"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\/978-3-032-37359-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:08:05Z","timestamp":1788934085000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_2","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":"10 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"}}]}}