{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:18:55Z","timestamp":1788985135098,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":66,"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_30","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:05:46Z","timestamp":1788984346000},"page":"551-569","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6965-1459","authenticated-orcid":false,"given":"Lin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7160-5523","authenticated-orcid":false,"given":"Bolin","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8373-6096","authenticated-orcid":false,"given":"Qi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0455-7631","authenticated-orcid":false,"given":"Zili","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2256-8815","authenticated-orcid":false,"given":"Kun","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-3224","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8544-8952","authenticated-orcid":false,"given":"Houwen","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2089-9733","authenticated-orcid":false,"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"30_CR1","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv:2303.08774 arXiv preprint (2023)"},{"key":"30_CR2","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR3","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"30_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":"30_CR5","unstructured":"Bai, S., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"30_CR6","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: Llava-kd: a framework of distilling multimodal large language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 239\u2013249 (2025)","DOI":"10.1109\/ICCV51701.2025.00030"},{"key":"30_CR8","doi-asserted-by":"publisher","first-page":"27056","DOI":"10.52202\/079017-0850","volume":"37","author":"L Chen","year":"2024","unstructured":"Chen, L., et al.: Are we on the right way for evaluating large vision-language models? Adv. Neural. Inf. Process. Syst. 37, 27056\u201327087 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR9","unstructured":"Chen, L., et\u00a0al.: Beyond next-token alignment: distilling multimodal large language models via token interactions. arXiv preprint arXiv:2602.09483 (2026)"},{"key":"30_CR10","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"},{"key":"30_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929 arXiv preprint (2020)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Blink: multimodal large language models can see but not perceive. In: European Conference on Computer Vision, pp. 148\u2013166. Springer (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Gao, Y., Xiong, Y., Wu, W., Huang, Z., Li, B., Wang, H.: U-niah: unified rag and LLM evaluation for long context needle-in-a-haystack. arXiv:2503.00353 arXiv preprint (2025)","DOI":"10.1145\/3786609"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Gao, Z., et al.: Mini-internvl: a flexible-transfer pocket multi-modal model with 5% parameters and 90% performance. Visual Intell. 2(1), 1\u201317 (2024)","DOI":"10.1007\/s44267-024-00067-6"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Ge, J., et al.: V2pe: improving multimodal long-context capability of vision-language models with variable visual position encoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21070\u201321084 (2025)","DOI":"10.1109\/ICCV51701.2025.01958"},{"key":"30_CR16","unstructured":"Guessous, D., Liang, Y., Dong, J., He, H.: Flexattention: the flexibility of pytorch with the performance of flashattention. PyTorch Blog (2024). https:\/\/pytorch.org\/blog\/flexattention\/. Accessed 24 June 2026"},{"key":"30_CR17","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced Bert with disentangled attention. arXiv:2006.03654 arXiv preprint (2020)"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Heo, B., Park, S., Han, D., Yun, S.: Rotary position embedding for vision transformer. In: European Conference on Computer Vision, pp. 289\u2013305. Springer (2024)","DOI":"10.1007\/978-3-031-72684-2_17"},{"key":"30_CR19","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.15351","volume":"11","author":"H Huang","year":"2023","unstructured":"Huang, H., Li, R., Zhang, J.: A review of visual sustained attention: neural mechanisms and computational models. PeerJ 11, e15351 (2023)","journal-title":"PeerJ"},{"key":"30_CR20","unstructured":"Huang, J., et al.: Revisiting multimodal positional encoding in vision-language models. arXiv:2510.23095 arXiv preprint (2025)"},{"key":"30_CR21","unstructured":"Hurst, A., et al.: Gpt-4o system card. arXiv:2410.21276 arXiv preprint (2024)"},{"key":"30_CR22","unstructured":"Kamradt, G.: Needle in a haystack - pressure testing LLMs (2023). https:\/\/github.com\/gkamradt\/LLMTest_NeedleInAHaystack. Accessed 10 Feb 2026"},{"key":"30_CR23","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":"30_CR24","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite Bert for self-supervised learning of language representations. arXiv:1909.11942 arXiv preprint (2019)"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Li, H., Qin, Y., Ou, B., Xu, L., Xu, R.: Hope: hybrid of position embedding for long context vision-language models. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-5430"},{"key":"30_CR26","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"30_CR27","unstructured":"Li, M., Zhang, S., Zhang, T., Duan, H., Liu, Y., Chen, K.: Needlebench: evaluating LLM retrieval and reasoning across varying information densities. arXiv preprint arXiv:2407.11963 (2024)"},{"key":"30_CR28","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. arXiv:2305.10355 arXiv preprint (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"30_CR29","unstructured":"Liu, A., et al.: Deepseek-v3 technical report. arXiv:2412.19437 arXiv preprint (2024)"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"30_CR31","unstructured":"Liu, H., et al.: Llava-next: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"30_CR32","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":"30_CR33","unstructured":"Liu, J., Feng, M., Chen, L.: Better, stronger, faster: tackling the trilemma in MLLM-based segmentation with simultaneous textual mask prediction. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2026)"},{"key":"30_CR34","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":"30_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Ocrbench: on the hidden mystery of OCR in large multimodal models. SCIENCE CHINA Inf. Sci. 67(12), 220102 (2024)","DOI":"10.1007\/s11432-024-4235-6"},{"key":"30_CR36","unstructured":"Liu, Y., et al.: Seg-zero: reasoning-chain guided segmentation via cognitive reinforcement. arXiv:2503.06520 arXiv preprint (2025)"},{"key":"30_CR37","unstructured":"Lu, P., et al.: Mathvista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv:2310.02255 arXiv preprint (2023)"},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Masry, A., Do, X.L., 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":"30_CR39","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":"30_CR40","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"30_CR41","doi-asserted-by":"crossref","unstructured":"Paiss, R., et al.: Teaching clip to count to ten. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3170\u20133180 (2023)","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"30_CR42","unstructured":"Park, S., Kim, J., Lee, J., Lee, S.: Dnotitia niah: enhanced multi-needle retrieval testing framework for evaluating LLM long-context understanding capabilities (2025). https:\/\/github.com\/dnotitia\/dnotitia-NIAH"},{"key":"30_CR43","unstructured":"Press, O., Smith, N.A., Lewis, M.: Train short, test long: attention with linear biases enables input length extrapolation. arXiv:2108.12409 arXiv preprint (2021)"},{"issue":"140","key":"30_CR44","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv:1803.02155 arXiv preprint (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"30_CR46","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"30_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"30_CR48","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv:2312.11805 arXiv preprint (2023)"},{"key":"30_CR49","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 arXiv preprint (2024)"},{"key":"30_CR50","unstructured":"Team, Q.: Qwen2.5: a party of foundation models (2024). https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"30_CR51","doi-asserted-by":"crossref","unstructured":"Tong, S., Liu, Z., Zhai, Y., Ma, Y., LeCun, Y., Xie, S.: Eyes wide shut? exploring the visual shortcomings of multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9568\u20139578 (2024)","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"30_CR52","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv:2302.13971 arXiv preprint (2023)"},{"key":"30_CR53","unstructured":"Tschannen, M., et al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv:2502.14786 arXiv preprint (2025)"},{"key":"30_CR54","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"30_CR55","unstructured":"Wang, C., et al.: Circle-rope: cone-like decoupled rotary positional embedding for large vision-language models. arXiv:2505.16416 arXiv preprint (2025)"},{"key":"30_CR56","doi-asserted-by":"publisher","first-page":"95095","DOI":"10.52202\/079017-3014","volume":"37","author":"K Wang","year":"2024","unstructured":"Wang, K., et al.: Measuring multimodal mathematical reasoning with math-vision dataset. Adv. Neural. Inf. Process. Syst. 37, 95095\u201395169 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR57","unstructured":"Wang, P., et al.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"30_CR58","unstructured":"Wang, W., et al.: Internvl3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv:2508.18265 arXiv preprint (2025)"},{"key":"30_CR59","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Divide, conquer and combine: a training-free framework for high-resolution image perception in multimodal large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 7907\u20137915 (2025)","DOI":"10.1609\/aaai.v39i8.32852"},{"key":"30_CR60","unstructured":"Wei, X., et al.: Videorope: what makes for good video rotary position embedding? arXiv preprint. arXiv:2502.05173 (2025)"},{"key":"30_CR61","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V?: Guided visual search as a core mechanism in multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13084\u201313094 (2024)","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"30_CR62","unstructured":"xAI: Grok-1.5 vision preview. https:\/\/x.ai\/blog\/grok-1.5v. Accessed 10 Feb 2026"},{"key":"30_CR63","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"30_CR64","unstructured":"Yao, Y., et al.: MINICPM-v: a GPT-4v level MLLM on your phone. arXiv:2408.01800 arXiv preprint (2024)"},{"key":"30_CR65","unstructured":"Yu, T., et\u00a0al.: Minicpm-v 4.5: Cooking efficient MLLMs via architecture, data, and training recipe. arXiv preprint arXiv:2509.18154 (2025)"},{"key":"30_CR66","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv:2504.10479 arXiv preprint (2025)"}],"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_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:05:56Z","timestamp":1788984356000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37627-5_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376268","9783032376275"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37627-5_30","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"}}]}}