{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:19:25Z","timestamp":1777655965580,"version":"3.51.4"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732348","type":"print"},{"value":"9783031732355","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73235-5_24","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"425-443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Merlin: Empowering Multimodal LLMs with\u00a0Foresight Minds"],"prefix":"10.1007","author":[{"given":"En","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yana","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinrong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongming","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingyu","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiancai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbing","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"24_CR1","unstructured":"Alayrac, J., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"24_CR2","unstructured":"Anil, R., et\u00a0al.: PaLM 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"24_CR3","unstructured":"Awadalla, A., et\u00a0al.: OpenFlamingo: an open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"24_CR4","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"24_CR5","unstructured":"Bates, C., Battaglia, P.W., Yildirim, I., Tenenbaum, J.B.: Humans predict liquid dynamics using probabilistic simulation. In: CogSci (2015)"},{"key":"24_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"24_CR7","unstructured":"Bolya, D., Fu, C., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: ICLR. OpenReview.net (2023)"},{"key":"24_CR8","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: SpatialVLM: endowing vision-language models with spatial reasoning capabilities. arXiv preprint arXiv:2401.12168 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"24_CR10","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"24_CR11","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"24_CR12","unstructured":"Cholakov, R., Kolev, T.: Transformers predicting the future. applying attention in next-frame and time series forecasting. arXiv preprint arXiv:2108.08224 (2021)"},{"key":"24_CR13","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. arXiv preprint arXiv:2305.06500 (2023)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ATOM: accurate tracking by overlap maximization. In: CVPR, pp. 4660\u20134669 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"24_CR15","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"24_CR16","unstructured":"Dong, R., et\u00a0al.: DreamLLM: synergistic multimodal comprehension and creation. arXiv preprint arXiv:2309.11499 (2023)"},{"key":"24_CR17","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR. OpenReview.net (2021)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"2","key":"24_CR19","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/nrn2787","volume":"11","author":"K Friston","year":"2010","unstructured":"Friston, K.: The free-energy principle: a unified brain theory? Nat. Rev. Neurosci. 11(2), 127\u2013138 (2010)","journal-title":"Nat. Rev. Neurosci."},{"key":"24_CR20","unstructured":"Ge, Y., Ge, Y., Zeng, Z., Wang, X., Shan, Y.: Planting a seed of vision in large language model. arXiv preprint arXiv:2307.08041 (2023)"},{"key":"24_CR21","unstructured":"Gong, T., et al.: Multimodal-GPT: a vision and language model for dialogue with humans. arXiv preprint arXiv:2305.04790 (2023)"},{"key":"24_CR22","unstructured":"Goyal, A., Bengio, Y.: Inductive biases for deep learning of higher-level cognition. CoRR abs\/2011.15091 (2020)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: VizWiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"5","key":"24_CR25","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR26","unstructured":"Huang, S., et\u00a0al.: Language is not all you need: aligning perception with language models. arXiv preprint arXiv:2302.14045 (2023)"},{"key":"24_CR27","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":"24_CR28","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML. JMLR Workshop and Conference Proceedings, vol.\u00a037, pp. 448\u2013456. JMLR.org (2015)"},{"issue":"7185","key":"24_CR29","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1038\/nature06713","volume":"452","author":"KN Kay","year":"2008","unstructured":"Kay, K.N., Naselaris, T., Prenger, R.J., Gallant, J.L.: Identifying natural images from human brain activity. Nature 452(7185), 352\u2013355 (2008)","journal-title":"Nature"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"24_CR31","unstructured":"Koh, J.Y., Fried, D., Salakhutdinov, R.: Generating images with multimodal language models. arXiv preprint arXiv:2305.17216 (2023)"},{"issue":"7","key":"24_CR32","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-zD","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01316-zD","journal-title":"Int. J. Comput. Vis."},{"key":"24_CR33","unstructured":"Lauren\u00e7on, H., et\u00a0al.: OBELICS: an open web-scale filtered dataset of interleaved image-text documents. In: Thirty-Seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2023)"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of siamese visual tracking with very deep networks. In: CVPR, pp. 4282\u20134291 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"24_CR35","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":"24_CR36","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 preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, L., He, R., Wang, Z., Wu, G., Wang, L.: MultiSports: a multi-person video dataset of spatio-temporally localized sports actions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13536\u201313545 (2021)","DOI":"10.1109\/ICCV48922.2021.01328"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"24_CR39","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"24_CR41","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"24_CR42","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Malla, S., Dariush, B., Choi, C.: TITAN: future forecast using action priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11186\u201311196 (2020)","DOI":"10.1109\/CVPR42600.2020.01120"},{"key":"24_CR44","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)"},{"key":"24_CR45","unstructured":"OpenAI: ChatGPT (2023). https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"24_CR46","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"24_CR47","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: NeurIPS (2022)"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: DetGPT: detect what you need via reasoning. arXiv preprint arXiv:2305.14167 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"24_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"24_CR50","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)"},{"issue":"1","key":"24_CR51","first-page":"5485","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(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"24_CR52","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1038\/nn1168","volume":"7","author":"N Ramnani","year":"2004","unstructured":"Ramnani, N., Miall, R.C.: A system in the human brain for predicting the actions of others. Nat. Neurosci. 7(1), 85\u201390 (2004)","journal-title":"Nat. Neurosci."},{"key":"24_CR53","unstructured":"Ryoo, M.S., Piergiovanni, A.J., Arnab, A., Dehghani, M., Angelova, A.: TokenLearner: what can 8 learned tokens do for images and videos? CoRR abs\/2106.11297 (2021)"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Sap, M., Bras, R.L., Fried, D., Choi, Y.: Neural theory-of-mind? On the limits of social intelligence in large LMs. In: EMNLP, pp. 3762\u20133780. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.248"},{"key":"24_CR55","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"24_CR56","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"24_CR57","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"24_CR58","doi-asserted-by":"publisher","unstructured":"Simsek, F.E., Cigla, C., Kayabol, K.: SOMPT22: a surveillance oriented multi-pedestrian tracking dataset. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision, ECCV 2022 Workshops, ECCV 2022. LNCS, vol. 13805, pp. 659\u2013675. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25072-9_44","DOI":"10.1007\/978-3-031-25072-9_44"},{"key":"24_CR59","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":"24_CR60","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: DanceTrack: multi-object tracking in uniform appearance and diverse motion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20993\u201321002 (2022),","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"24_CR61","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following LLaMA model (2023). https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"24_CR62","unstructured":"Touvron, H., et al.: LLaMA : open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"24_CR63","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"24_CR64","unstructured":"Ullman, T.D.: Large language models fail on trivial alterations to theory-of-mind tasks. CoRR abs\/2302.08399 (2023)"},{"key":"24_CR65","unstructured":"Wei, H., et al.: Small language model meets with reinforced vision vocabulary. arXiv preprint arXiv:2401.12503 (2024)"},{"key":"24_CR66","unstructured":"Wei, J., et al.: Emergent abilities of large language models. Trans. Mach. Learn. Res. 2022 (2022)"},{"key":"24_CR67","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"24_CR68","unstructured":"Wu, B., Yu, S., Chen, Z., Tenenbaum, J.B., Gan, C.: STAR: a benchmark for situated reasoning in real-world videos. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"24_CR69","doi-asserted-by":"crossref","unstructured":"Wu, D., Han, W., Wang, T., Dong, X., Zhang, X., Shen, J.: Referring multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14633\u201314642 (2023)","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"24_CR70","unstructured":"Xu, Y., et\u00a0al.: SiamFC++: towards robust and accurate visual tracking with target estimation guidelines. In: AAAI, pp. 140\u2013148 (2020)"},{"key":"24_CR71","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: VideoGPT: video generation using VQ-VAE and transformers. arXiv preprint arXiv:2104.10157 (2021)"},{"key":"24_CR72","unstructured":"Ye, Q., et\u00a0al.: mplug-owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"24_CR73","doi-asserted-by":"crossref","unstructured":"Yu, E., Li, Z., Han, S.: Towards discriminative representation: multi-view trajectory contrastive learning for online multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8834\u20138843 (2022)","DOI":"10.1109\/CVPR52688.2022.00863"},{"key":"24_CR74","doi-asserted-by":"crossref","unstructured":"Yu, E., et al.: Generalizing multiple object tracking to unseen domains by introducing natural language representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3304\u20133312 (2023)","DOI":"10.1609\/aaai.v37i3.25437"},{"key":"24_CR75","unstructured":"Yu, E., Wang, T., Li, Z., Zhang, Y., Zhang, X., Tao, W.: MOTRv3: release-fetch supervision for end-to-end multi-object tracking. arXiv preprint arXiv:2305.14298 (2023)"},{"key":"24_CR76","unstructured":"Yu, W., et al.: MM-Vet: evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"24_CR77","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6720\u20136731 (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"24_CR78","unstructured":"Zeng, A., et\u00a0al.: GLM-130B: an open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)"},{"key":"24_CR79","unstructured":"Zhang, S., et al.: GPT4RoI: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"24_CR80","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"24_CR81","doi-asserted-by":"crossref","unstructured":"Zhao, L., et\u00a0al.: ChatSpot: bootstrapping multimodal LLMs via precise referring instruction tuning. arXiv preprint arXiv:2307.09474 (2023)","DOI":"10.24963\/ijcai.2024\/193"},{"key":"24_CR82","unstructured":"Zhou, P., et al.: How far are large language models from agents with theory-of-mind? CoRR abs\/2310.03051 (2023)"},{"key":"24_CR83","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73235-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:17:37Z","timestamp":1732828657000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73235-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732348","9783031732355"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73235-5_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}