{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:10:31Z","timestamp":1789038631036,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374639","type":"print"},{"value":"9783032374646","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\/978-3-032-37464-6_3","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:38:13Z","timestamp":1789036693000},"page":"41-59","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Paying More Attention to\u00a0Visual Tokens in\u00a0Self-evolving Large Multimodal Models"],"prefix":"10.1007","author":[{"given":"Shravan","family":"Venkatraman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ritesh","family":"Thawkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omkar","family":"Thawakar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: Nocaps: novel object captioning at scale. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8948\u20138957 (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"3_CR2","unstructured":"Bai, S., et al.: Qwen3-VL technical report (2025). https:\/\/arxiv.org\/abs\/2511.21631"},{"key":"3_CR3","unstructured":"Chen, X., et\u00a0al.: C2-evo: co-evolving multimodal data and model for self-improving reasoning. arXiv preprint arXiv:2507.16518 (2025)"},{"key":"3_CR4","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: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, (vol. 2: Short Papers), pp. 346\u2013355 (2024)","DOI":"10.18653\/v1\/2024.acl-short.33"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"3_CR6","unstructured":"He, Y., Huang, C., Li, Z., Huang, J., Yang, Y.: Visplay: self-evolving vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26274\u201326284 (2026)"},{"key":"3_CR7","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: European Conference on Computer Vision, pp. 235\u2013251. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"3_CR10","unstructured":"Kornblith, S., Norouzi, M., Lee, H., Hinton, G.: Similarity of neural network representations revisited. In: International Conference on Machine Learning, pp. 3519\u20133529 (2019). PMLR"},{"key":"3_CR11","unstructured":"Li, T., Sun, Z., Wei, J., He, C., Wu, L., Tan, C.: Decouple to generalize: context-first self-evolving learning for data-scarce vision-language reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 29357\u201329366 (2026)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 292\u2013305 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft CoCo: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3_CR14","unstructured":"Liu, J., et al.: Agent0-VL: exploring self-evolving agent for tool-integrated vision-language reasoning (2025). arXiv:2511.19900 arXiv preprint"},{"key":"3_CR15","unstructured":"Liu, W., Li, J., Zhang, X., Zhou, F., Cheng, Y., He, J.: Diving into self-evolving training for multimodal reasoning (2024). arXiv:2412.17451 arXiv preprint"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? In: European Conference on Computer Vision, pp. 216\u2013233. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"3_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). arXiv:1711.05101 arXiv preprint"},{"key":"3_CR18","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.52202\/068431-0182","volume":"35","author":"P Lu","year":"2022","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. Adv. Neural. Inf. Process. Syst. 35, 2507\u20132521 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Masry, A., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: InfoGraphicVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: FlickR30k Entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"3_CR24","doi-asserted-by":"publisher","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4035\u20134045. Association for Computational Linguistics, Brussels, Belgium (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1437, https:\/\/aclanthology.org\/D18-1437\/","DOI":"10.18653\/v1\/D18-1437"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8429\u20138438 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00852","DOI":"10.1109\/ICCV.2019.00852"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Sidorov, O., Hu, R., Rohrbach, M., Singh, A.: TextCaps: a dataset for image captioning with reading comprehension. In: European Conference on Computer Vision, pp. 742\u2013758. Springer (2020)","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"3_CR27","unstructured":"Singh, A., et al.: Beyond human data: scaling self-training for problem-solving with language models (2023). arXiv:2312.06585 arXiv preprint"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Sunil, M., Venmathimaran, M., Kavitha, M.S.: Ireasoner: trajectory-aware intrinsic reasoning supervision for self-evolving large multimodal models (2026). arXiv:2601.05877 arXiv preprint","DOI":"10.18653\/v1\/2026.findings-acl.1468"},{"key":"3_CR29","unstructured":"Thawakar, O., et al.: EvolMM: self-evolving large multimodal models with continuous rewards. arXiv preprint arXiv:2511.16672 (2025)"},{"key":"3_CR30","unstructured":"Wang, Q., et al.: Vision-zero: scalable VLM self-evolution via multi-agent self-play. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=s00SNXREV6"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Wang, X., et\u00a0al.: Enhancing visual-language modality alignment in large vision language models via self-improvement. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 268\u2013282 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.15"},{"key":"3_CR32","unstructured":"xAI, visheratin: Realworldqa. https:\/\/huggingface.co\/datasets\/visheratin\/realworldqa (2024). https:\/\/huggingface.co\/datasets\/visheratin\/realworldqa"},{"key":"3_CR33","unstructured":"Yang, S., et al.: CaptionQA: is your caption as useful as the image itself? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23741\u201323750 (2026)"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, K., et\u00a0al.: LMMS-Eval: reality check on the evaluation of large multimodal models. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 881\u2013916 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.51"}],"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\/978-3-032-37464-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:38:29Z","timestamp":1789036709000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37464-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374639","9783032374646"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37464-6_3","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"}}]}}