{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T03:54:15Z","timestamp":1772942055652,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620609","type":"print"},{"value":"9789819620616","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2061-6_2","type":"book-chapter","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T05:45:40Z","timestamp":1735537540000},"page":"17-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Grounding Deliberate Reasoning in\u00a0Multimodal Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5538-3803","authenticated-orcid":false,"given":"Jiaxing","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9684-6416","authenticated-orcid":false,"given":"Yuxuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Dehu","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4652-8296","authenticated-orcid":false,"given":"Xiang","family":"An","sequence":"additional","affiliation":[]},{"given":"Weimo","family":"Deng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8689-8366","authenticated-orcid":false,"given":"Ziyong","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Yongle","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yin","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"2_CR1","unstructured":"PaddleOCR (2022). https:\/\/github.com\/PaddlePaddle\/PaddleOCR"},{"key":"2_CR2","unstructured":"Alayrac, J., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"2_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"2_CR4","unstructured":"Cheng, Q., et al.: Can AI assistants know what they don\u2019t know? CoRR abs\/2401.13275 (2024)"},{"key":"2_CR5","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality (2023)"},{"key":"2_CR6","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)"},{"key":"2_CR7","unstructured":"Dong, Q., et al.: A survey for in-context learning. CoRR abs\/2301.00234 (2023)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: EVA-02: a visual representation for neon genesis. CoRR abs\/2303.11331 (2023)","DOI":"10.2139\/ssrn.4813567"},{"key":"2_CR9","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. CoRR abs\/2312.10997 (2023)"},{"key":"2_CR10","unstructured":"Huang, S., et al.: Language is not all you need: aligning perception with language models. In: NeurIPS (2023)"},{"key":"2_CR11","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2_CR13","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: benchmarking multimodal llms with generative comprehension. CoRR abs\/2307.16125 (2023)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: Taskmatrix.ai: completing tasks by connecting foundation models with millions of apis. CoRR abs\/2303.16434 (2023)","DOI":"10.34133\/icomputing.0063"},{"key":"2_CR15","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. CoRR abs\/2310.03744 (2023)"},{"key":"2_CR16","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. CoRR abs\/2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2_CR18","unstructured":"Liu, X., et al.: What large language models bring to text-rich vqa? CoRR abs\/2311.07306 (2023)"},{"key":"2_CR19","unstructured":"Longpre, S., et al.: The flan collection: designing data and methods for effective instruction tuning. In: ICML (2023)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S.R., Hoque, E.: Chartqa: a benchmark for question answering about charts with visual and logical reasoning. In: Findings of ACL (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: Docvqa: a dataset for VQA on document images. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"2_CR22","unstructured":"Meta: Llama 2: Open foundation and fine-tuned chat models. CoRR abs\/2307.09288 (2023)"},{"key":"2_CR23","unstructured":"OpenAI: GPT-4 technical report. CoRR abs\/2303.08774 (2023)"},{"key":"2_CR24","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: NeurIPS (2022)"},{"key":"2_CR25","unstructured":"Peng, Z., et al.: Grounding multimodal large language models to the world. In: ICLR (2024)"},{"key":"2_CR26","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Hugginggpt: solving AI tasks with chatgpt and its friends in hugging face. In: NeurIPS (2023)"},{"key":"2_CR27","unstructured":"Sun, J., et al.: A survey of reasoning with foundation models. CoRR abs\/2312.11562 (2023)"},{"key":"2_CR28","unstructured":"Touvron, H., et al.: Llama: ppen and efficient foundation language models. CoRR abs\/2302.13971 (2023)"},{"key":"2_CR29","unstructured":"Wang, W., et al.: Cogvlm: visual expert for pretrained language models. CoRR abs\/2311.03079 (2023)"},{"key":"2_CR30","unstructured":"Wang, Y., Zhou, W., Feng, H., Zhou, K., Li, H.: Towards improving document understanding: An exploration on text-grounding via mllms. CoRR abs\/2311.13194 (2023)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Democratizing reasoning ability: tailored learning from large language model. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.120"},{"key":"2_CR32","unstructured":"Wu, P., Xie, S.: V*: guided visual search as a core mechanism in multimodal llms. CoRR abs\/2312.14135 (2023)"},{"key":"2_CR33","unstructured":"Wu, S., Fei, H., Qu, L., Ji, W., Chua, T.: Next-gpt: any-to-any multimodal LLM. CoRR abs\/2309.05519 (2023)"},{"key":"2_CR34","unstructured":"Ye, Q., et al.: mplug-owl: modularization empowers large language models with multimodality. CoRR abs\/2304.14178 (2023)"},{"key":"2_CR35","unstructured":"Yu, W., et al.: Mm-vet: evaluating large multimodal models for integrated capabilities. CoRR abs\/2308.02490 (2023)"},{"key":"2_CR36","unstructured":"Zhang, Y., et al.: Llavar: enhanced visual instruction tuning for text-rich image understanding. CoRR abs\/2306.17107 (2023)"},{"key":"2_CR37","unstructured":"Zheng, L., et\u00a0al.: Judging llm-as-a-judge with mt-bench and chatbot arena. In: NeurIPS (2024)"},{"key":"2_CR38","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. CoRR abs\/2304.10592 (2023)"},{"key":"2_CR39","unstructured":"Zhuang, Y., Yu, Y., Wang, K., Sun, H., Zhang, C.: Toolqa: a dataset for LLM question answering with external tools. In: NeurIPS (2023)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2061-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T06:03:31Z","timestamp":1735538611000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2061-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"ISBN":["9789819620609","9789819620616"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2061-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,31]]},"assertion":[{"value":"31 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}