{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:18:41Z","timestamp":1788985121136,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376268","type":"print"},{"value":"9783032376275","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\/978-3-032-37627-5_18","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:04:41Z","timestamp":1788984281000},"page":"321-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VIVAS: Vitalizing Visual Perception in\u00a0VLM Pre-training via\u00a0Vision-Language Unified Autoregressive Supervision"],"prefix":"10.1007","author":[{"given":"Zhehan","family":"Kan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubo","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghua","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixiang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shifeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingmin","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenming","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinsong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deqiang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"18_CR1","unstructured":"Bai, S., et al.: Qwen3-VL technical report (2025). https:\/\/arxiv.org\/abs\/2511.21631"},{"key":"18_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"18_CR3","unstructured":"Chen, L., et al.: Are we on the right way for evaluating large vision-language models? (2024). https:\/\/arxiv.org\/abs\/2403.20330"},{"key":"18_CR4","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Danish, M.S., et al.: GEOBench-VLM: benchmarking vision-language models for geospatial tasks (2025). https:\/\/arxiv.org\/abs\/2411.19325","DOI":"10.1109\/ICCV51701.2025.00670"},{"key":"18_CR6","unstructured":"DeepSeek-AI, et al.: DeepSeek-V3 technical report (2025). https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"18_CR7","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models (2025). https:\/\/arxiv.org\/abs\/2306.13394"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Fu, L., et al.: OCRBench v2: an improved benchmark for evaluating large multimodal models on visual text localization and reasoning (2025). https:\/\/arxiv.org\/abs\/2501.00321","DOI":"10.52202\/085713-3253"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: BLINK: multimodal large language models can see but not perceive (2024). https:\/\/arxiv.org\/abs\/2404.12390","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: HallusionBench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models (2024). https:\/\/arxiv.org\/abs\/2310.14566","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"18_CR11","unstructured":"Guo, D., et al.: Seed1.5-VL technical report (2025). https:\/\/arxiv.org\/abs\/2505.07062"},{"key":"18_CR12","unstructured":"Kan, Z., et al.: RAR: reversing visual attention re-sinking for unlocking potential in multimodal large language models. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=xTbFeDhdRG"},{"key":"18_CR13","unstructured":"Kan, Z., et al.: TACO: think-answer consistency for optimized long-chain reasoning and efficient data learning via reinforcement learning in LVLMs (2025). https:\/\/arxiv.org\/abs\/2505.20777"},{"key":"18_CR14","unstructured":"Kan, Z., et al.: Catch: complementary adaptive token-level contrastive decoding to mitigate hallucinations in LVLMs (2024). https:\/\/arxiv.org\/abs\/2411.12713"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images (2016). https:\/\/arxiv.org\/abs\/1603.07396","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"18_CR16","unstructured":"Li, B., et al.: Seed-bench-2: benchmarking multimodal large language models (2023). https:\/\/arxiv.org\/abs\/2311.17092"},{"key":"18_CR17","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: benchmarking multimodal LLMs with generative comprehension (2023). https:\/\/arxiv.org\/abs\/2307.16125"},{"key":"18_CR18","unstructured":"Li, F., et al.: Spatial forcing: implicit spatial representation alignment for vision-language-action model. arXiv preprint arXiv:2510.12276 (2025)"},{"key":"18_CR19","unstructured":"Li, H., et al.: Unleashing the intrinsic visual representation capability of multimodal large language models. arXiv preprint arXiv:2512.06281 (2025)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: ScreenSpot-Pro: GUI grounding for professional high-resolution computer use (2025). https:\/\/arxiv.org\/abs\/2504.07981","DOI":"10.1145\/3746027.3755688"},{"key":"18_CR21","unstructured":"Li, M., et al.: VISTA: enhancing vision-text alignment in MLLMs via cross-modal mutual information maximization. arXiv preprint arXiv:2505.10917 (2025)"},{"key":"18_CR22","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR23","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023). https:\/\/arxiv.org\/abs\/2304.08485"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: MMBench: Is your multi-modal model an all-around player? (2024). https:\/\/arxiv.org\/abs\/2307.06281","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"18_CR25","unstructured":"Lu, J., et al.: Youtu-LLM: unlocking the native agentic potential for lightweight large language models (2026). https:\/\/arxiv.org\/abs\/2512.24618"},{"key":"18_CR26","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts (2024). https:\/\/arxiv.org\/abs\/2310.02255"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering (2022). https:\/\/arxiv.org\/abs\/2209.09513","DOI":"10.52202\/068431-0182"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning (2022). https:\/\/arxiv.org\/abs\/2203.10244","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"18_CR29","unstructured":"Mathew, M., Bagal, V., Tito, R.P., Karatzas, D., Valveny, E., Jawahar, C.V.: Infographicvqa (2021). https:\/\/arxiv.org\/abs\/2104.12756"},{"key":"18_CR30","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":"18_CR31","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers (2023). https:\/\/arxiv.org\/abs\/2212.09748","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"18_CR32","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"18_CR33","unstructured":"Rahmanzadehgervi, P., Bolton, L., Taesiri, M.R., Nguyen, A.T.: Vision language models are blind: failing to translate detailed visual features into words (2025). https:\/\/arxiv.org\/abs\/2407.06581"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Shi, F., Luo, Z., Ge, Y., Yang, Y., Shan, Y., Wang, L.: Scalable image tokenization with index backpropagation quantization (2025). https:\/\/arxiv.org\/abs\/2412.02692","DOI":"10.1109\/ICCV51701.2025.01488"},{"key":"18_CR35","unstructured":"Sim\u00e9oni, O., et al.: DINOv3 (2025). https:\/\/arxiv.org\/abs\/2508.10104"},{"key":"18_CR36","unstructured":"Singh, A., et al.: Towards VQA models that can read (2019). https:\/\/arxiv.org\/abs\/1904.08920"},{"key":"18_CR37","unstructured":"Team, et al.: GLM-4.5: agentic, reasoning, and coding (ARC) foundation models (2025). https:\/\/arxiv.org\/abs\/2508.06471"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Tong, S., Bet al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs (2024). https:\/\/arxiv.org\/abs\/2406.16860","DOI":"10.52202\/079017-2771"},{"key":"18_CR39","unstructured":"Tschannen, M., et al.: SigLIP 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features (2025). https:\/\/arxiv.org\/abs\/2502.14786"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Wang, D., et al.: Autoregressive semantic visual reconstruction helps VLMs understand better. arXiv preprint arXiv:2506.09040 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.1900"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Wang, D., et al.: Autoregressive semantic visual reconstruction helps VLMs understand better (2026). https:\/\/arxiv.org\/abs\/2506.09040","DOI":"10.18653\/v1\/2026.findings-acl.1900"},{"key":"18_CR42","unstructured":"Wang, H., et al.: Reconstructive visual instruction tuning. arXiv preprint arXiv:2410.09575 (2024)"},{"key":"18_CR43","unstructured":"Wang, S., et al.: VLBiasBench: a comprehensive benchmark for evaluating bias in large vision-language model (2026). https:\/\/arxiv.org\/abs\/2406.14194"},{"key":"18_CR44","unstructured":"Wang, W., et al.: InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency (2025). https:\/\/arxiv.org\/abs\/2508.18265"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: The all-seeing project V2: towards general relation comprehension of the open world. arXiv preprint arXiv:2402.19474 (2024)","DOI":"10.1007\/978-3-031-73414-4_27"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CharXiv: charting gaps in realistic chart understanding in multimodal LLMs (2024). https:\/\/arxiv.org\/abs\/2406.18521","DOI":"10.52202\/079017-3609"},{"key":"18_CR47","unstructured":"Wu, P., Xie, S.: V*: guided visual search as a core mechanism in multimodal LLMs (2023). https:\/\/arxiv.org\/abs\/2312.14135"},{"key":"18_CR48","unstructured":"Xiao, Y., Sun, E., Liu, T., Wang, W.: LogicVista: multimodal LLM logical reasoning benchmark in visual contexts (2024). https:\/\/arxiv.org\/abs\/2407.04973"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Xie, T., et al.: OSWorld: benchmarking multimodal agents for open-ended tasks in real computer environments (2024). https:\/\/arxiv.org\/abs\/2404.07972","DOI":"10.52202\/079017-1650"},{"key":"18_CR50","unstructured":"Xu, W., et al.: VisuLogic: a benchmark for evaluating visual reasoning in multi-modal large language models (2025). https:\/\/arxiv.org\/abs\/2504.15279"},{"key":"18_CR51","unstructured":"Yoon, H., et\u00a0al.: Visual representation alignment for multimodal large language models. arXiv preprint arXiv:2509.07979 (2025)"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions (2016). https:\/\/arxiv.org\/abs\/1608.00272","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training (2023). https:\/\/arxiv.org\/abs\/2303.15343","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: MathVerse: does your multi-modal LLM truly see the diagrams in visual math problems? (2024). https:\/\/arxiv.org\/abs\/2403.14624","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"18_CR55","unstructured":"Zhang, Y.F., et al.: MME-RealWorld: could your multimodal LLM challenge high-resolution real-world scenarios that are difficult for humans? (2025). https:\/\/arxiv.org\/abs\/2408.13257"}],"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\/978-3-032-37627-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:04:52Z","timestamp":1788984292000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37627-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376268","9783032376275"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37627-5_18","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"}}]}}