{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:28:53Z","timestamp":1768375733672,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556786","type":"print"},{"value":"9789819556793","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\/978-981-95-5679-3_6","type":"book-chapter","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:45Z","timestamp":1768329405000},"page":"76-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Compositional Reasoning in\u00a0Multimodal Large Language Models"],"prefix":"10.1007","author":[{"given":"Shun","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingquan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjie","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoxun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"6_CR1","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it?. In: International Conference on Learning Representations (2023)"},{"key":"6_CR2","unstructured":"Doveh, S., Arbelle, A., Harary, S., Panda, R., Giryes, R., Feris, R., et\u00a0al.: Dense and aligned captions (DAC) promote compositional reasoning in VL models. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 76:137\u201376:150 (2023)"},{"key":"6_CR3","unstructured":"Patel, M., et al.: TripletCLIP: improving compositional reasoning of clip via synthetic vision-language negatives. In: Advances in Neural Information Processing Systems (2024)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Sahin, U., Li, H., Khan, Q., Cremers, D., Tresp, V.: Enhancing multimodal compositional reasoning of visual language models with generative negative mining. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5563\u20135573 (2024)","DOI":"10.1109\/WACV57701.2024.00547"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Peng, W., Xie, S., You, Z., Lan, S., Wu, Z.: Synthesize diagnose and optimize: towards fine-grained vision-language understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13:279\u201313:288 (2024)","DOI":"10.1109\/CVPR52733.2024.01261"},{"key":"6_CR6","unstructured":"Hsieh, C.-Y., Zhang, J., Ma, Z., Kembhavi, A., Krishna, R.: SugarCrepe: fixing hackable benchmarks for vision-language compositionality. In: 37th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2023)"},{"key":"6_CR7","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"6_CR8","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems, ser. NIPS \u201923 (2023)"},{"key":"6_CR9","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"6_CR10","unstructured":"Gao, P., et\u00a0al.: SPHINX-X: scaling data and parameters for a family of multi-modal large language models. CoRR (2024)"},{"key":"6_CR11","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":"6_CR12","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"6_CR13","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision, pp. 8748\u20138763. PmLR (2021)"},{"key":"6_CR14","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. 26:296\u201326:306 (2024)"},{"key":"6_CR15","unstructured":"Cao, Y., et al.: MMFuser: multimodal multi-layer feature fuser for fine-grained vision-language understanding. arXiv preprint arXiv:2410.11829 (2024)"},{"key":"6_CR16","unstructured":"Yao, H., et al.: Dense connector for MLLMs. In: Advances in Neural Information Processing Systems, vol.\u00a037, pp. 33:108\u201333:140 (2025)"},{"key":"6_CR17","unstructured":"Yang, A., et\u00a0al.: Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"key":"6_CR18","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"6_CR19","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11:975\u201311:986 (2023)"},{"key":"6_CR20","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: EVA-CLIP: improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"6_CR21","unstructured":"Ray, A., Radenovic, F., Dubey, A., Plummer, B., Krishna, R., Saenko, K.: COLA: a benchmark for compositional text-to-image retrieval. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 46:433\u201346:445 (2023)"},{"key":"6_CR22","unstructured":"Zhao, T., et al.: VL-Checklist: evaluating pre-trained vision-language models with objects, attributes and relations. arXiv preprint arXiv:2207.00221 (2022)"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: MMBench: is your multi-modal model an all-around player? In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) European Conference on Computer Vision, pp. 216\u2013233. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Wen, J.-R.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"6_CR25","unstructured":"Zhang, P., et al.: InternLM-XComposer: a vision-language large model for advanced text-image comprehension and composition. arXiv preprint arXiv:2309.15112 (2023)"},{"key":"6_CR26","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":"6_CR27","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 34:892\u201334:916 (2023)"},{"key":"6_CR28","unstructured":"Lee, C., et al.: NV-Embed: improved techniques for training LLMs as generalist embedding models. arXiv preprint arXiv:2405.17428 (2024)"},{"key":"6_CR29","unstructured":"Zhang, X., et al.: GME: improving universal multimodal retrieval by multimodal LLMs. arXiv preprint arXiv:2412.16855 (2024)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"6_CR31","unstructured":"Yu, W., et al.: MM-Vet: evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"6_CR32","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"6_CR33","unstructured":"Qian, S., Liu, B., Sun, C., Xu, Z., Wang, B.: Spatial-aware efficient projector for MLLMs via multi-layer feature aggregation. arXiv preprint arXiv:2410.10319 (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5679-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:49Z","timestamp":1768329409000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5679-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556786","9789819556793"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5679-3_6","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":"14 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}