{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:30:54Z","timestamp":1789083054872,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372314","type":"print"},{"value":"9783032372321","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\/978-3-032-37232-1_16","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:56:42Z","timestamp":1788933402000},"page":"287-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Staying VIGILant: Mitigating Visual Laziness via\u00a0Counterfactual Visual Alignment in\u00a0MLLMs"],"prefix":"10.1007","author":[{"given":"Xi","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chih-Ting","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunbei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qizhen","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janet","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muchao","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Allen-Zhu, Z., Li, Y.: Physics of language models: Part 3. 3, knowledge capacity scaling laws. In: International Conference on Learning Representations (2025)","DOI":"10.2139\/ssrn.5250617"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bai, T., et al.: Hallucination at a glance: controlled visual edits and fine-grained multimodal learning. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-4517"},{"key":"16_CR3","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, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"issue":"240","key":"16_CR4","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR5","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"16_CR6","unstructured":"Dao, T.: Flashattention-2: faster attention with better parallelism and work partitioning. In: International Conference on Learning Representations, vol. 2024, pp. 35549\u201335562 (2024)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Gandhi, M., Gul, M.O., Prakash, E., Grunde-McLaughlin, M., Krishna, R., Agrawala, M.: Measuring compositional consistency for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5046\u20135055 (2022)","DOI":"10.1109\/CVPR52688.2022.00499"},{"issue":"8081","key":"16_CR8","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo, D., et al.: Deepseek-r1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645(8081), 633\u2013638 (2025)","journal-title":"Nature"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"He, Y., et al.: Mitigating object hallucination in large vision-language models via visual attention direct preference optimization. In: 2025 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2025)","DOI":"10.1109\/ICME59968.2025.11209127"},{"key":"16_CR10","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: International Conference on Learning Representations (2021)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., et\u00a0al.: OpenRLHF: an easy-to-use, scalable and high-performance RLHF framework. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (2025)","DOI":"10.18653\/v1\/2025.emnlp-demos.48"},{"key":"16_CR12","unstructured":"Hu, X., Ni, H., Zhang, Y., Hamm, J., Li, Z., Ding, Z.: Seeing clearly, reasoning confidently: plug-and-play remedies for vision language model blindness. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2026)"},{"key":"16_CR13","unstructured":"Kang, W., Kuen, J., Ren, M., Wei, Z., Yan, Y., Liu, K.: Vgent: visual grounding via modular design for disentangling reasoning and prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 41160\u201341170 (2026)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Leng, S., et al.: Mitigating object hallucinations in large vision-language models through visual contrastive decoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13872\u201313882 (2024)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"16_CR15","unstructured":"Li, B., et al.: Llava-onevision: easy visual task transfer. Trans. Mach. Learn. Res. (2025)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Galley, M., Brockett, C., Gao, J., Dolan, W.B.: A diversity-promoting objective function for neural conversation models. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 110\u2013119 (2016)","DOI":"10.18653\/v1\/N16-1014"},{"key":"16_CR17","unstructured":"Li, T., He, K.: Back to basics: let denoising generative models denoise. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 36115\u201336125 (2026)"},{"key":"16_CR18","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: 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":"16_CR19","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: Colorbench: can VLMs see and understand the colorful world? A comprehensive benchmark for color perception, reasoning, and robustness. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2025)","DOI":"10.52202\/085713-4803"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Liao, D., et al.: Assessing neural network representations during training using noise-resilient diffusion spectral entropy. In: 2024 58th Annual Conference on Information Sciences and Systems (CISS), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/CISS59072.2024.10480166"},{"key":"16_CR21","unstructured":"Liao, D., et al.: Rnagenscape: property-guided optimization and interpolation of MRNA sequences with manifold langevin dynamics. arXiv preprint arXiv:2510.24736 (2025)"},{"key":"16_CR22","unstructured":"Lin, Z., Liu, Y., Yang, Y., Tao, L., Ye, D.: Adaptvision: efficient vision-language models via adaptive visual acquisition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11923\u201311932 (2026)"},{"key":"16_CR23","unstructured":"Liu, C., et al.: Dispersion loss counteracts embedding condensation and improves generalization in small language models. In: International Conference on Machine Learning. PMLR (2026)"},{"key":"16_CR24","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, Cham (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"16_CR25","unstructured":"Long, L., Oh, C., Park, S., Li, S.: Understanding language prior of LVLMs by contrasting chain-of-embedding. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"16_CR26","unstructured":"Lu, P., et al.: Mathvista: evaluating mathematical reasoning of foundation models in visual contexts. In: The Twelfth International Conference on Learning Representations (2024)"},{"issue":"1","key":"16_CR27","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1146\/annurev-statistics-040522-115238","volume":"11","author":"M Meil\u0103","year":"2024","unstructured":"Meil\u0103, M., Zhang, H.: Manifold learning: what, how, and why. Ann. Rev. Stat. Appl. 11(1), 393\u2013417 (2024)","journal-title":"Ann. Rev. Stat. Appl."},{"key":"16_CR28","doi-asserted-by":"publisher","first-page":"124198","DOI":"10.52202\/079017-3946","volume":"37","author":"Y Meng","year":"2024","unstructured":"Meng, Y., Xia, M., Chen, D.: Simpo: simple preference optimization with a reference-free reward. Adv. Neural. Inf. Process. Syst. 37, 124198\u2013124235 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Panagopoulou, A., et al.: Viunit: visual unit tests for more robust visual programming. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24646\u201324656 (2025)","DOI":"10.1109\/CVPR52734.2025.02295"},{"key":"16_CR31","unstructured":"Qiu, L., Ning, S., Zhang, C., Sun, J., He, X.: DA-DPO: cost-efficient difficulty-aware preference optimization for reducing MLLM hallucinations. Trans. Machi. Learn. Res. (2025)"},{"key":"16_CR32","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","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. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201316. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"16_CR34","unstructured":"Sun, X., et al.: Geometry-aware generative autoencoders for warped Riemannian metric learning and generative modeling on data manifolds. In: The 28th International Conference on Artificial Intelligence and Statistics (2025)"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Sun, Z., et\u00a0al.: Aligning large multimodal models with factually augmented RLHF. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 13088\u201313110 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"16_CR36","unstructured":"Wang, J., et\u00a0al.: Amber: an LLM-free multi-dimensional benchmark for MLLMs hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)"},{"key":"16_CR37","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":"16_CR38","unstructured":"Wang, Z., et\u00a0al.: Perception-aware policy optimization for multimodal reasoning. arXiv preprint arXiv:2507.06448 (2025)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, D., et\u00a0al.: From system 1 to system 2: a survey of reasoning large language models. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3637037"},{"key":"16_CR40","unstructured":"Zhang, J., Khayatkhoei, M., Chhikara, P., Ilievski, F.: MLLMs know where to look: training-free perception of small visual details with multimodal LLMs. In: The Thirteenth International Conference on Learning Representations (2025)"},{"issue":"12","key":"16_CR41","doi-asserted-by":"publisher","first-page":"3848","DOI":"10.14778\/3611540.3611569","volume":"16","author":"Y Zhao","year":"2023","unstructured":"Zhao, Y., et al.: Pytorch FSDP: experiences on scaling fully sharded data parallel. Proc. VLDB Endow. 16(12), 3848\u20133860 (2023)","journal-title":"Proc. VLDB Endow."},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Wang, B., Ouyang, L., Dong, X., Wang, J., He, C.: Beyond multimodal hallucinations: enhancing LVLMs through hallucination-aware direct preference optimization. In: 2025 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2025)","DOI":"10.1109\/ICME59968.2025.11209377"},{"key":"16_CR43","unstructured":"Zhou, Y., et al.: Analyzing and mitigating object hallucination in large vision-language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"16_CR44","unstructured":"Zhu, D., et al.: Leveraging latent visual reasoning in silence. arXiv preprint arXiv:2605.18641 (2026)"}],"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\/978-3-032-37232-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:56:50Z","timestamp":1788933410000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37232-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372314","9783032372321"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37232-1_16","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"}}]}}