{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:07:04Z","timestamp":1788937624884,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375940","type":"print"},{"value":"9783032375957","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\/978-3-032-37595-7_31","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:35:38Z","timestamp":1788935738000},"page":"564-580","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Marcel","family":"Gr\u00f6pl","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaewoo","family":"Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungryong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunghwan","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"31_CR1","unstructured":"An, H., et\u00a0al.: C3g: learning compact 3d representations with 2k gaussians. arXiv preprint arXiv:2512.04021 (2025)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"An, H., et al.: Cross-view completion models are zero-shot correspondence estimators. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1103\u20131115 (2025)","DOI":"10.1109\/CVPR52734.2025.00111"},{"key":"31_CR3","unstructured":"An, X., et al.: LLAVA-onevision-1.5: fully open framework for democratized multimodal training (2025). https:\/\/arxiv.org\/abs\/2509.23661"},{"key":"31_CR4","unstructured":"Bai, J., et al.: QWEN-VL: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"31_CR5","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"31_CR6","unstructured":"Chen, Z.,et al.: Prose: training-free egocentric scene registration with vision-language models (2026). arXiv:2606.16569 arXiv preprint"},{"issue":"6","key":"31_CR7","doi-asserted-by":"publisher","first-page":"7174","DOI":"10.1109\/TPAMI.2022.3218727","volume":"45","author":"S Cho","year":"2022","unstructured":"Cho, S., Hong, S., Kim, S.: Cats++: boosting cost aggregation with convolutions and transformers. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7174\u20137194 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR8","unstructured":"Deitke, M., et al.: Molmo and pixmo: open weights and open data for state-of-the-art multimodal models. arXiv preprint arXiv:2409.17146 (2024)"},{"key":"31_CR9","unstructured":"Gurbuz, A.S., Hong, S., Nassar, A., Pollefeys, M., Staar, P.: Moving beyond sparse grounding with complete screen parsing supervision, (2026). arXiv:2602.14276 arXiv preprint"},{"key":"31_CR10","unstructured":"Gurbuz, A.S., Hong, S., Nassar, A., Pollefeys, M., Staar, P.: Screenparse: moving beyond sparse grounding with complete screen parsing supervision (2026). arXiv:2602.14276 arXiv preprint"},{"key":"31_CR11","unstructured":"Han, J., et al.: Emergent outlier view rejection in visual geometry grounded transformers (2025). arXiv:2512.04012 arXiv preprint"},{"key":"31_CR12","unstructured":"Han, J., et al.: Geometric action model for robot policy learning (2026). arXiv:2606.17046 arXiv preprint"},{"key":"31_CR13","unstructured":"Hong, S., Cho, S., Kim, S., Lin, S.: Unifying feature and cost aggregation with transformers for semantic and visual correspondence (2024). arXiv:2403.11120 arXiv preprint"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Hong, S., Kim, S.: Deep matching prior: test-time optimization for dense correspondence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9907\u20139917 (2021)","DOI":"10.1109\/ICCV48922.2021.00976"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Hong, S., et al.: Neural matching fields: Implicit representation of matching fields for visual correspondence. Adv. Neural. Inf. Process. Syst. 35, 13512\u201313526 (2022)","DOI":"10.52202\/068431-0982"},{"key":"31_CR16","doi-asserted-by":"publisher","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6693\u20136702 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00686","DOI":"10.1109\/CVPR.2019.00686"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: Token-efficient VLM: high-resolution image understanding via dynamic region proposal. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 24147\u201324158 (2025)","DOI":"10.1109\/ICCV51701.2025.02238"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Kaduri, O., Bagon, S., Dekel, T.: What\u2019s in the image? a deep-dive into the vision of vision language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14549\u201314558 (2025)","DOI":"10.1109\/CVPR52734.2025.01356"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Kang, S., Kim, J., Kim, J., Hwang, S.J.: Your large vision-language model only needs a few attention heads for visual grounding (2025). https:\/\/arxiv.org\/abs\/2503.06287","DOI":"10.1109\/CVPR52734.2025.00872"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Kim, C., et al.: Seg4diff: unveiling open-vocabulary segmentation in text-to-image diffusion transformers. arXiv preprint arXiv:2509.18096 (2025)","DOI":"10.52202\/085713-2408"},{"key":"31_CR21","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), pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"31_CR22","unstructured":"Li, B., et al.: Llava-onevision: easy visual task transfer. Trans. Mach. Learn. Res. (2024)"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/openreview.net\/forum?id=xozJw0kZXF","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2024). https:\/\/arxiv.org\/abs\/2310.03744","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"31_CR25","unstructured":"Liu, H., Li, C., Li, Y., Li, B., Zhang, Y., Shen, S., Lee, Y.J.: Llava-next: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection (2024). https:\/\/arxiv.org\/abs\/2303.05499","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"31_CR27","unstructured":"Mathew, M., Bagal, V., Tito, R.P., Karatzas, D., Valveny, E., Jawahar, C.V.: Infographicvqa (2021). https:\/\/arxiv.org\/abs\/2104.12756"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: Docvqa: a dataset for VQA on document images (2021). https:\/\/arxiv.org\/abs\/2007.00398","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection (2016). https:\/\/arxiv.org\/abs\/1506.02640","DOI":"10.1109\/CVPR.2016.91"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Satopaa, V., Albrecht, J., Irwin, D., Raghavan, B.: Finding a \u201ckneedle\u201d in a haystack: detecting knee points in system behavior. In: 2011 31st International Conference on Distributed Computing Systems Workshops, pp. 166\u2013171. IEEE (2011)","DOI":"10.1109\/ICDCSW.2011.20"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"31_CR32","doi-asserted-by":"publisher","unstructured":"Shen, H., et al.: ZoomEye: enhancing multimodal LLMs with human-like zooming capabilities through tree-based image exploration. In: Christodoulopoulos, C., Chakraborty, T., Rose, C., Peng, V. (eds.) Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 6602\u20136618. Association for Computational Linguistics, Suzhou, China (2025). https:\/\/doi.org\/10.18653\/v1\/2025.emnlp-main.335. https:\/\/aclanthology.org\/2025.emnlp-main.335\/","DOI":"10.18653\/v1\/2025.emnlp-main.335"},{"key":"31_CR33","doi-asserted-by":"publisher","first-page":"9153","DOI":"10.52202\/079017-0290","volume":"37","author":"H Shin","year":"2024","unstructured":"Shin, H., Kim, C., Hong, S., Cho, S., Arnab, A., Seo, P.H., Kim, S.: Towards open-vocabulary semantic segmentation without semantic labels. Adv. Neural. Inf. Process. Syst. 37, 9153\u20139177 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"31_CR35","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a070, pp. 3319\u20133328. PMLR (2017). https:\/\/proceedings.mlr.press\/v70\/sundararajan17a.html"},{"key":"31_CR36","unstructured":"Wang, W., et al.: Internvl3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency (2025). arXiv:2508.18265 arXiv preprint"},{"key":"31_CR37","unstructured":"Wu, P., Xie, S.: V: guided visual search as a core mechanism in multimodal LLMs (2023). https:\/\/arxiv.org\/abs\/2312.14135"},{"key":"31_CR38","doi-asserted-by":"publisher","unstructured":"Wu, S., Jin, S., Zhang, W., Xu, L., Liu, W., Li, W., Loy, C.C.: F-LMM: grounding frozen large multimodal models. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24710\u201324721 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.02301","DOI":"10.1109\/CVPR52734.2025.02301"},{"key":"31_CR39","unstructured":"XAI: realworldqa dataset (2024). https:\/\/huggingface.co\/datasets\/xai-org\/RealworldQA. (Accessed 28 Feb 2026)"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Xie, Y., et al.: Region-based cluster discrimination for visual representation learning. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00175"},{"key":"31_CR41","unstructured":"Yoon, H., et\u00a0al.: Visual representation alignment for multimodal large language models. arXiv preprint arXiv:2509.07979 (2025)"},{"key":"31_CR42","unstructured":"Zhang, J., Khayatkhoei, M., Chhikara, P., Ilievski, F.: MLLMs know where to look: training-free perception of small visual details with multimodal LLMs (2025). https:\/\/arxiv.org\/abs\/2502.17422"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yadav, S., Han, F., Shutova, E.: Cross-modal information flow in multimodal large language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19781\u201319791 (2025)","DOI":"10.1109\/CVPR52734.2025.01842"}],"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\/978-3-032-37595-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:35:45Z","timestamp":1788935745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37595-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375940","9783032375957"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37595-7_31","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"}}]}}