Research on Development Status of Multimodal Knowledge Graph Fusion Technology in Medical Field

doi:10.3778/j.issn.1673-9418.2411008

Abstract

Abstract: Multimodal knowledge graph utilizes text, visual and other multimodal data to model entities, relationships and events, demonstrating powerful data processing capabilities and providing richer and deeper understanding for the field of artificial intelligence. Therefore, it has attracted attention in the medical field and has achieved significant results in various research areas such as medical data processing and potential value mining. To better clarify the research status of multimodal knowledge graph in the medical field, firstly, this paper elaborates on the basic knowledge of multimodal knowledge graph and the difficulties and related datasets in constructing multimodal knowledge graph in the medical field. Secondly, this paper analyzes the key technologies involved in multimodal knowledge graph fusion, such as multimodal entity alignment and multimodal entity linking, from the perspectives of traditional methods and deep learning methods. The focus is on the feature extraction and fusion methods of text, image, and audio modalities. This paper summarizes the advantages and disadvantages of each multimodal fusion method, and elaborates on the application of multimodal large language model in multimodal fusion. Finally, this paper reviews the research progress of multimodal knowledge graphs in fields such as medical visual Q&A, drug development, and medical imaging diagnosis. On this basis, this paper analyzes the limitations and challenges faced by multimodal knowledge graphs in the field of medical multimodal fusion and datasets, and provides future research directions.

Key words: multimodal knowledge graph, knowledge graph fusion, multimodal large language model, intelligent healthcare

摘要： 多模态知识图谱利用文本、视觉等多模态数据对实体、关系及事件进行建模，展现出强大的数据处理能力，为人工智能领域提供更丰富、深入的理解，也因此备受医学领域瞩目，其在医学数据处理、潜在价值挖掘等多类研究中均取得显著成效。为更好地厘清多模态知识图谱在医学领域的研究现状，阐述多模态知识图谱基本知识及医学领域多模态知识图谱构建难点与相关数据集；从传统方法及深度学习方法两个角度分析多模态知识图谱融合涉及的多模态实体对齐与多模态实体链接等关键技术，重点分析文本、图像、音频三个模态的特征提取及融合方法，总结各多模态融合方法优缺点并阐述多模态大语言模型在多模态融合中的应用；详细梳理多模态知识图谱在医学视觉问答、药物研发、影像辅助诊断等领域的研究进展。在此基础上，分析归纳医学领域多模态知识图谱在多模态融合与数据集方面的局限性及面临的挑战，并对未来研究方向进行展望。

关键词: 多模态知识图谱, 知识图谱融合, 多模态大语言模型, 智能医疗

SHI Zhenpu, LYU Xiao, DONG Yanru, LIU Jing, WANG Xiaoyan. Research on Development Status of Multimodal Knowledge Graph Fusion Technology in Medical Field[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(7): 1729-1746.

时振普, 吕潇, 董彦如, 刘静, 王晓燕. 医学领域多模态知识图谱融合技术发展现状研究[J]. 计算机科学与探索, 2025, 19(7): 1729-1746.

References

[1] SINGHAL A. Introducing the knowledge graph: things, not strings[J]. Official Google Blog, 2012, 5(16): 3.
[2] YANG F, NING B, LI H Q. An overview of multimodal fusion learning[C]//Proceedings of the 2022 International Conference on Mobile Computing, Applications, and Services. Cham: Springer, 2022: 259-268.
[3] 陈囿任, 李勇, 温明, 等. 多模态知识图谱融合技术研究综述[J]. 计算机工程与应用, 2024, 60(13): 36-50.
CHEN Y R, LI Y, WEN M, et al. Research and comprehensive review on multi-modal knowledge graph fusion techniques[J]. Computer Engineering and Applications, 2024, 60(13): 36-50.
[4] KUMAR S, RANI S, SHARMA S, et al. Multimodality fusion aspects of medical diagnosis: a comprehensive review[J]. Bioengineering, 2024, 11(12): 1233.
[5] SHAIK T, TAO X H, LI L, et al. A survey of multimodal information fusion for smart healthcare: mapping the journey from data to wisdom[J]. Information Fusion, 2024, 102: 102040.
[6] PENG C Y, XIA F, NASERIPARSA M, et al. Knowledge graphs: opportunities and challenges[J]. Artificial Intelligence Review, 2023, 56(11): 13071-13102.
[7] ZHU X R, LI Z X, WANG X D, et al. Multi-modal knowledge graph construction and application: a survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(2): 715-735.
[8] CHEN Y, GE X K, YANG S L, et al. A survey on multimodal knowledge graphs: construction, completion and applications[J]. Mathematics, 2023, 11(8): 1815.
[9] LIU Y, LI H, GARCIA-DURAN A, et al. MMKG: multi-modal knowledge graphs[C]//Proceedings of the 16th International Conference on the Semantic Web. Cham: Springer, 2019: 459-474.
[10] LEHMANN J, ISELE R, JAKOB M, et al. DBpedia - a large-scale, multilingual knowledge base extracted from Wikipedia[J]. Semantic Web, 2015, 6(2): 167-195.
[11] FERRADA S, BUSTOS B, HOGAN A. IMGpedia: a linked dataset with content-based analysis of Wikimedia images[C]//Proceedings of the 2017 International Semantic Web Conference. Cham: Springer, 2017: 84-93.
[12] O?ORO-RUBIO D, NIEPERT M, GARCíA-DURáN A, et al. Answering visual-relational queries in web-extracted knowledge graphs[EB/OL]. [2024-09-16]. https://arxiv.org/abs/1709. 02314.
[13] WANG M, QI G L, WANG H F, et al. Richpedia: a comprehensive multi-modal knowledge graph[C]//Proceedings of the 9th Joint International Conference on Semantic Technology. Cham: Springer, 2020: 130-145.
[14] LI M L, ZAREIAN A, LIN Y, et al. GAIA: a fine-grained multimedia knowledge extraction system[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Stroudsburg: ACL, 2020: 77-86.
[15] KRISHNA R, ZHU Y K, GROTH O, et al. Visual genome: connecting language and vision using crowdsourced dense image annotations[J]. International Journal of Computer Vision, 2017, 123(1): 32-73.
[16] ZHANG N, LI L, CHEN X, et al. Multimodal analogical reasoning over knowledge graphs[C]//Proceedings of the 11th International Conference on Learning Representations, 2023.
[17] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the 13th European Conference on Computer Vision. Cham: Springer, 2014: 740-755.
[18] GOYAL Y, KHOT T, SUMMERS-STAY D, et al. Making the V in VQA matter: elevating the role of image understanding in visual question answering[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6325-6334.
[19] PLUMMER B A, WANG L W, CERVANTES C M, et al. Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 2641-2649.
[20] AGRAWAL H, DESAI K R, WANG Y F, et al. Nocaps: novel object captioning at scale[C]//Proceedings of the 2019 IEEE/ CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 8947-8956.
[21] WANG X W, TIAN J F, GUI M, et al. WikiDiverse: a multimodal entity linking dataset with diversified contextual topics and entity types[EB/OL]. [2024-09-16]. https://arxiv.org/abs/2204.06347.
[22] HU X Y, GU L, KOBAYASHI K, et al. Interpretable medical image visual question answering via multi-modal relationship graph learning[J]. Medical Image Analysis, 2024, 97: 103279.
[23] SUBRAMANIAN S, WANG L L, MEHTA S, et al. MedICaT: a dataset of medical images, captions, and textual references[EB/OL]. [2024-09-16]. https://arxiv.org/abs/2010.06000.
[24] IRVIN J, RAJPURKAR P, KO M, et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 590-597.
[25] PAVLOPOULOS J, KOUGIA V, ANDROUTSOPOULOS I. A survey on biomedical image captioning[C]//Proceedings of the 2nd Workshop on Shortcomings in Vision and Language. Stroudsburg: ACL, 2019: 26-36.
[26] JOHNSON A E W, POLLARD T J, BERKOWITZ S J, et al. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports[J]. Scientific Data, 2019, 6: 317.
[27] LAU J J, GAYEN S, BEN ABACHA A, et al. A dataset of clinically generated visual questions and answers about radiology images[J]. Scientific Data, 2018, 5: 180251.
[28] 陈烨, 周刚, 卢记仓. 多模态知识图谱构建与应用研究综述[J]. 计算机应用研究, 2021, 38(12): 3535-3543.
CHEN Y, ZHOU G, LU J C. Survey on construction and application research for multi-modal knowledge graphs[J]. Application Research of Computers, 2021, 38(12): 3535-3543.
[29] GONG Y C, LV X Q, YUAN Z, et al. GNN-based multimodal named entity recognition[J]. The Computer Journal, 2024, 67(8): 2622-2632.
[30] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9992-10002.
[31] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2261-2269.
[32] WANG F, ZHOU Y, WANG S, et al. Multi-granularity cross-modal alignment for generalized medical visual representation learning[C]//Advances in Neural Information Processing Systems 35, 2022: 33536-33549.
[33] RADFORD A, KIN J W, HALLACY C, et al. Learning transferable visual models from natural language supervision[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 8748-8763.
[34] LI J, LI D, XIONG C, et al. Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation[C]//Proceedings of the 39th International Conference on Machine Learning, 2022: 12888-12900.
[35] YAO L W, HUANG R H, HOU L, et al. FILIP: fine grained interactive language-image pre-training[C]//Proceedings of the 10th International Conference on Learning Representations, 2022.
[36] WANG Z F, WU Z B, AGARWAL D, et al. MedCLIP: contrastive learning from unpaired medical images and text[EB/OL]. [2024-09-19]. https://arxiv.org/abs/2210.10163.
[37] ZHANG Y, JIANG H, MIURA Y, et al. Contrastive learning of medical visual representations from paired images and text[C]//Proceedings of the Machine Learning for Healthcare Conference, 2022: 2-25.
[38] MOON J H, LEE H, SHIN W, et al. Multi-modal understanding and generation for medical images and text via vision-language pre-training[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(12): 6070-6080.
[39] XIANG J X, WANG X Y, ZHANG X M, et al. A vision-language foundation model for precision oncology[J]. Nature, 2025, 638(8051): 769-778.
[40] MA C, JIANG H, CHEN W, et al. Eye-gaze guided multi-modal alignment for medical representation learning[C]//Advances in Neural Information Processing Systems 37, 2024: 6126-6153.
[41] LI Z P, ZOU C H, MA S X, et al. ZALM3: zero-shot enhancement of vision-language alignment via in-context information in multi-turn multimodal medical dialogue[EB/OL]. [2024-10-14]. https://arxiv.org/abs/2409.17610.
[42] XIA P, ZHU K Y, LI H R, et al. MMed-RAG: versatile multimodal RAG system for medical vision language models[EB/OL]. [2024-10-30]. https://arxiv.org/abs/2410.13085.
[43] ZHU K Y, XIA P, LI Y, et al. MMedPO: aligning medical vision-language models with clinical-aware multimodal preference optimization[EB/OL]. [2024-12-15]. https://arxiv.org/abs/ 2412.06141.
[44] DOSOVITSKIY A. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL]. [2024-09-16]. https://arxiv.org/abs/2010.11929.
[45] SHI S B, XU Z R, HU B T, et al. Generative multimodal entity linking[EB/OL]. [2024-09-16]. https://arxiv.org/abs/2306.12725.
[46] LIU Q, HE Y Y, XU T, et al. UniMEL: a unified framework for multimodal entity linking with large language models[C]//Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. New York: ACM, 2024: 1909-1919.
[47] SHERSTINSKY A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 132306.
[48] HAN K, WANG Y H, CHEN H T, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 87-110.
[49] KOROTEEV M V. BERT: a review of applications in natural language processing and understanding[EB/OL]. [2024-09-16]. https://arxiv.org/abs/2103.11943.
[50] ACHIAM J, ADLER S, AGARWAL S, et al. GPT-4 technical report[EB/OL]. [2024-09-16]. https://arxiv.org/abs/2303.08774.
[51] LEE J, YOON W, KIM S, et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining[J]. Bioinformatics, 2020, 36(4): 1234-1240.
[52] HUANG K X, ALTOSAAR J, RANGANATH R. ClinicalBERT: modeling clinical notes and predicting hospital readmission[EB/OL]. [2024-09-19]. https://arxiv.org/abs/1904.05342.
[53] LIU N, HU Q, XU H Y, et al. Med-BERT: a pretraining framework for medical records named entity recognition[J]. IEEE Transactions on Industrial Informatics, 2022, 18(8): 5600-5608.
[54] 胡嘉元, 邱瑞瑾, 孙杨, 等. 自然语言处理及其在医学领域的应用[J]. 中国循证医学杂志, 2024, 24(10): 1205-1211.
HU J Y, QIU R J, SUN Y, et al. Natural language processing and its application in the medical field[J]. Chinese Journal of Evidence-Based Medicine, 2024, 24(10): 1205-1211.
[55] 张云秋, 殷策. 基于大模型的中文电子病历实体自动识别研究[J/OL]. 数据分析与知识发现 [2024-11-19]. https://kns. cnki.net/KCMS/detail/detail.aspx?filename=41115001&dbname=CJFD&dbcode=CJFQ.
ZHANG Y Q, YIN C. Research on entity automatic recognition of Chinese electronic medical records based on large model[J/OL]. Data Analysis and Knowledge Discovery [2024- 11-19]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename= XDTQ20241115001&dbname=CJFD&dbcode=CJFQ.
[56] GOEL A, GUETA A, GILON O, et al. LLMs accelerate annotation for medical information extraction[C]//Machine Learning for Health, ML4H@NeurIPS 2023, 2023: 82-100.
[57] LI D Y, KADAV A, GAO A J, et al. Automated clinical data extraction with knowledge conditioned LLMs[EB/OL]. [2024- 09-19]. https://arxiv.org/abs/2406.18027.
[58] WU Z F, SHEN C H, VAN DEN HENGEL A. Wider or deeper: revisiting the ResNet model for visual recognition[J]. Pattern Recognition, 2019, 90: 119-133.
[59] YUAN Z W, ZHANG J. Feature extraction and image retrieval based on AlexNet[C]//Proceedings of the 8th International Conference on Digital Image Processing, 2016: 65-69.
[60] YU W, YANG K, BAI Y, et al. Visualizing and comparing AlexNet and VGG using deconvolutional layers[C]//Proceedings of the 33rd International Conference on Machine Learning, 2016.
[61] TAMMINA S. Transfer learning using VGG-16 with deep convolutional neural network for classifying images[J]. International Journal of Scientific and Research Publications, 2019, 9(10): 143-150.
[62] LIANG J Z. Image classification based on RESNET[J]. Journal of Physics: Conference Series, 2020, 1634(1): 012110.
[63] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[64] LEI M Q, WU H C, LV X H, et al. ConDSeg: a general medical image segmentation framework via contrast-driven feature enhancement[EB/OL]. [2024-12-15]. https://arxiv.org/ abs/2412.08345.
[65] VAESSEN N, VAN LEEUWEN D A. Fine-tuning Wav2Vec2 for speaker recognition[C]//Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2022: 7967-7971.
[66] CHEN S Y, LIU S J, ZHOU L, et al. VALL-E 2: neural codec language models are human parity zero-shot text to speech synthesizers[EB/OL]. [2024-09-19]. https://arxiv.org/abs/2406. 05370.
[67] RAJASEKAR S J S, BALARAMAN A R, BALARAMAN D V, et al. Detection of tuberculosis using cough audio analysis: a deep learning approach with capsule networks[J]. Discover Artificial Intelligence, 2024, 4(1): 77.
[68] 王慧, 张玭, 金丰护, 等. 基于卷积神经网络和长短时记忆网络的心理疲劳状态识别方法[J]. 生物医学工程学杂志, 2024, 41(1): 34-40.
WANG H, ZHANG P, JIN F H, et al. Mental fatigue state recognition method based on convolution neural network and long short-term memory[J]. Journal of Biomedical Engineering, 2024, 41(1): 34-40.
[69] FUKUI A, PARK D H, YANG D, et al. Multimodal compact bilinear pooling for visual question answering and visual grounding[EB/OL]. [2024-09-19]. https://arxiv.org/abs/1606.01847.
[70] KIM J H, ON K W, LIM W, et al. Hadamard product for low-rank bilinear pooling[EB/OL]. [2024-09-19]. https://arxiv. org/abs/1610.04325.
[71] YU Z, YU J, FAN J P, et al. Multi-modal factorized bilinear pooling with co-attention learning for visual question answering[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 1839-1848.
[72] YU Z, YU J, XIANG C C, et al. Beyond bilinear: generalized multimodal factorized high-order pooling for visual question answering[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(12): 5947-5959.
[73] SU W J, ZHU X Z, CAO Y, et al. VL-BERT: pre-training of generic visual-linguistic representations[EB/OL]. [2024-09-19]. https://arxiv.org/abs/1908.08530.
[74] LI L H, YATSKAR M, YIN D, et al. VisualBERT: a simple and performant baseline for vision and language[EB/OL]. [2024-09-19]. https://arxiv.org/abs/1908.03557.
[75] QI D, SU L, SONG J, et al. ImageBERT: cross-modal pre-training with large-scale weak-supervised image-text data[EB/OL]. [2024-09-19]. https://arxiv.org/abs/2001.07966.
[76] CHEN Y C, LI L J, YU L C, et al. UNITER: universal image-text representation learning[C]//Proceedings of the 16th European Conference on Computer Vision. Cham: Springer, 2020: 104-120.
[77] KIM W, SON B, KIM I. ViLT: vision-and-language transformer without convolution or region supervision[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 5583-5594.
[78] SUN C, MYERS A, VONDRICK C, et al. VideoBERT: a joint model for video and language representation learning[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 7463-7472.
[79] LI L J, CHEN Y C, CHENG Y, et al. HERO: hierarchical encoder for video+language omni-representation pre-training [EB/OL]. [2024-09-19]. https://arxiv.org/abs/2005.00200.
[80] LU J S, BATRA D, PARIKH D, et al. ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks[EB/OL]. [2024-09-19]. https://arxiv.org/abs/1908.02265.
[81] TAN H, BANSAL M. LXMERT: learning cross-modality encoder representations from transformers[EB/OL]. [2024-09-19]. https://arxiv.org/abs/1908.07490.
[82] LUO H S, JI L, SHI B T, et al. UniVL: a unified video and language pre-training model for multimodal understanding and generation[EB/OL]. [2024-09-19]. https://arxiv.org/abs/2002.06353.
[83] ZHU L C, YANG Y. ActBERT: learning global-local video-text representations[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 8743-8752.
[84] KIM D, KIM T. Missing modality prediction for unpaired multimodal learning via joint embedding of unimodal models [C]//Proceedings of the 18th European Conference on Computer Vision. Cham: Springer, 2024: 171-187.
[85] LI W B, ZHOU H, YU J Q, et al. Coupled mamba: enhanced multi-modal fusion with coupled state space model[EB/OL]. [2024-10-14]. https://arxiv.org/abs/2405.18014.
[86] GU A, DAO T. Mamba: linear-time sequence modeling with selective state spaces[EB/OL]. [2024-10-14]. https://arxiv.org/ abs/2312.00752.
[87] WANG J Z, WANG K, YU Y F, et al. Self-improving generative foundation model for synthetic medical image generation and clinical applications[J]. Nature Medicine, 2024, 31(2): 609-617.
[88] SHAO J, MA J C, YU Y Z, et al. A multimodal integration pipeline for accurate diagnosis, pathogen identification, and prognosis prediction of pulmonary infections[J]. The Innovation, 2024, 5(4): 100648.
[89] NIU C, LYU Q, CAROTHERS C D, et al. Medical multimodal multitask foundation model for lung cancer screening[J]. Nature Communications, 2025, 16: 1523.
[90] SAAB K, TU T, WENG W H, et al. Capabilities of gemini models in medicine[EB/OL]. [2024-10-14]. https://arxiv.org/ abs/2404.18416.
[91] LI C, WONG C, ZHANG S, et al. LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day[C]//Advances in Neural Information Processing Systems 36, 2023.
[92] WU C Y, LIN W X, ZHANG X M, et al. PMC-LLaMA: toward building open-source language models for medicine[J]. Journal of the American Medical Informatics Association, 2024, 31(9): 1833-1843.
[93] ZHANG K, ZHOU R, ADHIKARLA E, et al. A generalist vision-language foundation model for diverse biomedical tasks[J]. Nature Medicine, 2024, 30(11): 3129-3141.
[94] CUI H C, ZHAO Y C, XIONG S, et al. Diagnosing solid lesions in the pancreas with multimodal artificial intelligence: a randomized crossover trial[J]. JAMA Network Open, 2024, 7(7): e2422454.
[95] GAO F, DING J X, GAI B W, et al. Interpretable multimodal fusion model for bridged histology and genomics survival prediction in pan-cancer[J]. Advanced Science, 2025: 2407060.
[96] ZHANG X M, WU C Y, ZHAO Z H, et al. PMC-VQA: visual instruction tuning for medical visual question answering[EB/OL]. [2024-10-14]. https://arxiv.org/abs/2305.10415.
[97] 张殿元, 余传明. 基于知识增强与多模态融合的医疗视觉问答模型[J]. 数据分析与知识发现, 2024, 8(S1): 226-239.
ZHANG D Y, YU C M. Medical visual question answering model based on knowledge enhancement and multimodal fusion[J]. Data Analysis and Knowledge Discovery, 2024, 8(S1): 226-239.
[98] 刘亚. 基于深度学习的医疗领域多模态视觉问答研究[D].临沂: 临沂大学, 2024.
LIU Y. Research on multimodal visual question answering in medical field based on deep learning[D]. Linyi: Linyi University, 2024.
[99] LIANG Y W, ZHANG R Y, ZHANG L, et al. DrugChat: towards enabling ChatGPT-like capabilities on drug molecule graphs[EB/OL]. [2024-10-14]. https://arxiv.org/abs/2309.03907.
[100] DEEPSEEK-AI, GUO D Y, YANG D J, et al. DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning[EB/OL]. [2025-01-25]. https://arxiv.org/ abs/2501.12948.
[101] LI J, GUAN Z, WANG J, et al. Integrated image-based deep learning and language models for primary diabetes care[J]. Nature Medicine, 2024, 30(10): 2886-2896.