{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:58Z","timestamp":1786120858430,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U22A6001"],"award-info":[{"award-number":["U22A6001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818885","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"12715-12726","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>Caduceus:<\/scp>\n                    MoE Foundation Models for Unifying Biological and Natural Language"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6595-9849","authenticated-orcid":false,"given":"Mingze","family":"Yin","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8020-9979","authenticated-orcid":false,"given":"Yiheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhongguancun Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2494-6402","authenticated-orcid":false,"given":"Jialu","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7037-4800","authenticated-orcid":false,"given":"Jian","family":"Ma","sequence":"additional","affiliation":[{"name":"Zhongguancun Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9152-2572","authenticated-orcid":false,"given":"Hanjing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Cainiao Group, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1840-8416","authenticated-orcid":false,"given":"Mingyang","family":"Li","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1557-963X","authenticated-orcid":false,"given":"Yuhua","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3199-2597","authenticated-orcid":false,"given":"Jintai","family":"Chen","sequence":"additional","affiliation":[{"name":"AI Thrust, Information Hub, HKUST (GZ), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7227-2580","authenticated-orcid":false,"given":"Tingjun","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9823-1436","authenticated-orcid":false,"given":"Aimin","family":"Pan","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, China and VNET Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_2_1","first-page":"3387","article-title":"Deeploc: prediction of protein subcellular localization using deep learning","volume":"33","author":"Almagro Armenteros Jos\u00e9 Juan","year":"2017","unstructured":"Jos\u00e9 Juan Almagro Armenteros, Casper Kaae S\u00f8nderby, S\u00f8ren Kaae S\u00f8nderby, Henrik Nielsen, and Ole Winther. 2017. Deeploc: prediction of protein subcellular localization using deep learning. Nature Communications, V33, 21 (2017), 3387-3395.","journal-title":"Nature Communications"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/75556"},{"key":"e_1_3_2_2_4_1","volume-title":"The ENZYME database","author":"Bairoch Amos","year":"2000","unstructured":"Amos Bairoch. 2000. The ENZYME database in 2000. Nucleic Acids Research, V28, 1 (2000), 304-305."},{"key":"e_1_3_2_2_5_1","volume-title":"The SWISS-PROT protein sequence database and its supplement TrEMBL","author":"Bairoch Amos","year":"2000","unstructured":"Amos Bairoch and Rolf Apweiler. 2000. The SWISS-PROT protein sequence database and its supplement TrEMBL in 2000. Nucleic Acids Research, V28, 1 (2000), 45-48."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/28.1.235"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Bo Chen Xingyi Cheng Pan Li Yangli-ao Geng Jing Gong Shen Li Zhilei Bei Xu Tan Boyan Wang Xin Zeng et al. 2025. xTrimoPGLM: unified 100-billion-parameter pretrained transformer for deciphering the language of proteins. Nature Methods (2025) 1-12.","DOI":"10.1038\/s41592-025-02636-z"},{"key":"e_1_3_2_2_8_1","volume-title":"Guangyu Zhou, Xuelu Chen, Tianran Zhang, Kai-Wei Chang, Carlo Zaniolo, and Wei Wang.","author":"Chen Muhao","year":"2019","unstructured":"Muhao Chen, Chelsea J-T Ju, Guangyu Zhou, Xuelu Chen, Tianran Zhang, Kai-Wei Chang, Carlo Zaniolo, and Wei Wang. 2019. Multifaceted protein-protein interaction prediction based on Siamese residual RCNN. Bioinformatics, V35, 14 (2019), i305-i314."},{"key":"e_1_3_2_2_9_1","volume-title":"LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs. arXiv preprint arXiv:2401.16160","author":"Chen Shaoxiang","year":"2024","unstructured":"Shaoxiang Chen, Zequn Jie, and Lin Ma. 2024a. LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs. arXiv preprint arXiv:2401.16160 (2024)."},{"key":"e_1_3_2_2_10_1","volume-title":"International Conference on Learning Representations.","author":"Chen Zeren","year":"2024","unstructured":"Zeren Chen, Ziqin Wang, Zhen Wang, Huayang Liu, Zhenfei Yin, Si Liu, Lu Sheng, Wanli Ouyang, and Jing Shao. 2024b. Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_11_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"e_1_3_2_2_12_1","volume-title":"V47, D1","author":"U Consortium","year":"2019","unstructured":"U Consortium. 2019. Uniprot: a worldwide hub of protein knowledge. Nucleic Acids Research, V47, D1 (2019), D506\u2013D515."},{"key":"e_1_3_2_2_13_1","unstructured":"Fengyuan Dai Shiyang You Chentong Wang Yuliang Fan Jin Su Chenchen Han Xibin Zhou Jianming Liu Hui Qian Shunzhi Wang et al. 2024. Toward de novo protein design from natural language. bioRxiv (2024) 2024-08."},{"key":"e_1_3_2_2_14_1","volume-title":"FLIP: Benchmark tasks in fitness landscape inference for proteins. bioRxiv","author":"Dallago Christian","year":"2021","unstructured":"Christian Dallago, Jody Mou, Kadina E Johnston, Bruce J Wittmann, Nicholas Bhattacharya, Samuel Goldman, Ali Madani, and Kevin K Yang. 2021. FLIP: Benchmark tasks in fitness landscape inference for proteins. bioRxiv (2021)."},{"key":"e_1_3_2_2_15_1","volume-title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts. In International Conference on Machine Learning. 5547-5569","author":"Du Nan","year":"2022","unstructured":"Nan Du, Yanping Huang, Andrew M Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, et al., 2022. GLaM: Efficient Scaling of Language Models with Mixture-of-Experts. In International Conference on Machine Learning. 5547-5569."},{"key":"e_1_3_2_2_16_1","volume-title":"Nikita Dhawan, Al\u00e1n Aspuru-Guzik, and Chris J. Maddison.","author":"Duan Haonan","year":"2025","unstructured":"Haonan Duan, Marta Skreta, Leonardo Cotta, Ella Miray Rajaonson, Nikita Dhawan, Al\u00e1n Aspuru-Guzik, and Chris J. Maddison. 2025. Boosting the predictive power of protein representations with a corpus of text annotations. Nature Machine Intelligence (2025), 1-11."},{"key":"e_1_3_2_2_17_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv e-prints (2024) arXiv-2407."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095381"},{"key":"e_1_3_2_2_19_1","first-page":"1","article-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. Journal of Machine Learning Research, V23, 120 (2022), 1-39.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts565"},{"key":"e_1_3_2_2_21_1","unstructured":"Xinyang Geng and Hao Liu. 2023. OpenLLaMA: An Open Reproduction of LLaMA. https:\/\/github.com\/openlm-research\/open_llama."},{"key":"e_1_3_2_2_22_1","first-page":"1","article-title":"Structure-based protein function prediction using graph convolutional networks","volume":"12","author":"Vladimir","year":"2021","unstructured":"Vladimir Gligorijevi?, P Douglas Renfrew, Tomasz Kosciolek, Julia Koehler Leman, Daniel Berenberg, Tommi Vatanen, Chris Chandler, Bryn C Taylor, Ian M Fisk, Hera Vlamakis, et al., 2021. Structure-based protein function prediction using graph convolutional networks. Nature Communications, V12, 1 (2021), 1-14.","journal-title":"Nature Communications"},{"key":"e_1_3_2_2_23_1","unstructured":"Team GLM Aohan Zeng Bin Xu Bowen Wang Chenhui Zhang Da Yin Dan Zhang Diego Rojas Guanyu Feng Hanlin Zhao et al. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_3_2_2_24_1","volume-title":"Mixture of Cluster-Conditional LoRA Experts for Vision-Language Instruction Tuning. arXiv preprint arXiv:2312.12379","author":"Gou Yunhao","year":"2023","unstructured":"Yunhao Gou, Zhili Liu, Kai Chen, Lanqing Hong, Hang Xu, Aoxue Li, Dit-Yan Yeung, James T Kwok, and Yu Zhang. 2023. Mixture of Cluster-Conditional LoRA Experts for Vision-Language Instruction Tuning. arXiv preprint arXiv:2312.12379 (2023)."},{"key":"e_1_3_2_2_25_1","volume-title":"V3, 1","author":"Gu Yu","year":"2021","unstructured":"Yu Gu, Robert Tinn, Hao Cheng, Michael Lucas, Naoto Usuyama, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, and Hoifung Poon. 2021. Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing. ACM Transactions on Computing for Healthcare, V3, 1 (2021), 1-23."},{"key":"e_1_3_2_2_26_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_2_27_1","volume-title":"Embracing Change: Continual Learning in Deep Neural Networks. Trends in cognitive sciences, V24, 12","author":"Hadsell Raia","year":"2020","unstructured":"Raia Hadsell, Dushyant Rao, Andrei A Rusu, and Razvan Pascanu. 2020. Embracing Change: Continual Learning in Deep Neural Networks. Trends in cognitive sciences, V24, 12 (2020), 1028-1040."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Thomas Hayes Roshan Rao Halil Akin Nicholas J Sofroniew Deniz Oktay Zeming Lin Robert Verkuil Vincent Q Tran Jonathan Deaton Marius Wiggert et al. 2025. Simulating 500 million years of evolution with a language model. Science V387 6736 (2025) 850-858.","DOI":"10.1126\/science.ads0018"},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Machine Learning. 2790-2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. 2790-2799."},{"key":"e_1_3_2_2_30_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_31_1","volume-title":"V3, 1","author":"Jacobs Robert A","year":"1991","unstructured":"Robert A Jacobs, Michael I Jordan, Steven J Nowlan, and Geoffrey E Hinton. 1991. Adaptive Mixtures of Local Experts. Neural computation, V3, 1 (1991), 79-87."},{"key":"e_1_3_2_2_32_1","volume-title":"V6, 2","author":"Jordan Michael I","year":"1994","unstructured":"Michael I Jordan and Robert A Jacobs. 1994. Hierarchical Mixtures of Experts and the EM Algorithm. Neural computation, V6, 2 (1994), 181-214."},{"key":"e_1_3_2_2_33_1","volume-title":"International Conference on Machine Learning.","author":"Junnan Li","year":"2023","unstructured":"Li Junnan, Li Dongxu, Savarese Silvio, and Hoi Steven. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_34_1","volume-title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers. Advances in Neural Information Processing Systems, V34","author":"Mahabadi Rabeeh Karimi","year":"2021","unstructured":"Rabeeh Karimi Mahabadi, James Henderson, and Sebastian Ruder. 2021. Compacter: Efficient Low-Rank Hypercomplex Adapter Layers. Advances in Neural Information Processing Systems, V34 (2021), 1022-1035."},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Machine Learning. 5583-5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In International Conference on Machine Learning. 5583-5594."},{"key":"e_1_3_2_2_36_1","volume-title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In International Conference on Learning Representations.","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_37_1","volume-title":"The Power of Scale for Parameter-Efficient Prompt Tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The Power of Scale for Parameter-Efficient Prompt Tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_2_38_1","volume-title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-Tuning: Optimizing Continuous Prompts for Generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Zeming Lin Halil Akin Roshan Rao Brian Hie Zhongkai Zhu Wenting Lu Nikita Smetanin Robert Verkuil Ori Kabeli Yaniv Shmueli et al. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science V379 6637 (2023) 1123-1130.","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_2_2_40_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024a. DeepSeek-V3 Technical Report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_2_42_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_43_1","unstructured":"Shengchao Liu Yanjing Li Zhuoxinran Li Anthony Gitter Yutao Zhu Jiarui Lu Zhao Xu Weili Nie Arvind Ramanathan Chaowei Xiao et al. 2025. A text-guided protein design framework. Nature Machine Intelligence (2025) 1-12."},{"key":"e_1_3_2_2_44_1","volume-title":"ProtT3: Protein-to-Text Generation for Text-based Protein Understanding","author":"Liu Zhiyuan","unstructured":"Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, and Tat-Seng Chua. 2024c. ProtT3: Protein-to-Text Generation for Text-based Protein Understanding. In Association for Computational Linguistics."},{"key":"e_1_3_2_2_45_1","volume-title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for Biomedicine. arXiv preprint arXiv:2308.09442","author":"Luo Yizhen","year":"2023","unstructured":"Yizhen Luo, Jiahuan Zhang, Siqi Fan, Kai Yang, Yushuai Wu, Mu Qiao, and Zaiqing Nie. 2023. BioMedGPT: Open Multimodal Generative Pre-trained Transformer for Biomedicine. arXiv preprint arXiv:2308.09442 (2023)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/506"},{"key":"e_1_3_2_2_47_1","volume-title":"Li Yuan, and Yonghong Tian.","author":"Lv Liuzhenghao","year":"2025","unstructured":"Liuzhenghao Lv, Zongying Lin, Hao Li, Yuyang Liu, Jiaxi Cui, Calvin Yu-Chian Chen, Li Yuan, and Yonghong Tian. 2025. ProLLaMA: A Protein Language Model for Multi-Task Protein Language Processing. IEEE Transactions on Artificial Intelligence (2025)."},{"key":"e_1_3_2_2_48_1","volume-title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications. arXiv preprint arXiv:2503.07137","author":"Mu Siyuan","year":"2025","unstructured":"Siyuan Mu and Sen Lin. 2025. A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications. arXiv preprint arXiv:2503.07137 (2025)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_2_50_1","first-page":"1216","article-title":"BioT5","author":"Pei Qizhi","year":"2024","unstructured":"Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, and Rui Yan. 2024. BioT5: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning. In Findings of the Association for Computational Linguistics. 1216-1240.","journal-title":"In Findings of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_51_1","volume-title":"International Conference on Machine Learning. 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748-8763."},{"key":"e_1_3_2_2_52_1","unstructured":"Roshan Rao Nicholas Bhattacharya Neil Thomas Yan Duan Peter Chen John Canny Pieter Abbeel and Yun Song. 2019. Evaluating protein transfer learning with tape. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"e_1_3_2_2_54_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations.","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_55_1","volume-title":"ProTrek: Navigating the protein universe through tri-modal contrastive learning. bioRxiv","author":"Su Jin","year":"2024","unstructured":"Jin Su, Xibin Zhou, Xuting Zhang, and Fajie Yuan. 2024. ProTrek: Navigating the protein universe through tri-modal contrastive learning. bioRxiv (2024), 2024-05."},{"key":"e_1_3_2_2_56_1","volume-title":"Galactica: A Large Language Model for Science. arXiv preprint arXiv:2211.09085","author":"Taylor Ross","year":"2022","unstructured":"Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. 2022. Galactica: A Large Language Model for Science. arXiv preprint arXiv:2211.09085 (2022)."},{"key":"e_1_3_2_2_57_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730064"},{"key":"e_1_3_2_2_59_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_2_60_1","volume-title":"LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations? arXiv preprint arXiv:2605.26781","author":"Wang Xiaohan","year":"2026","unstructured":"Xiaohan Wang, Mingze Yin, Yilin Zhao, Gang Liu, and Dian Li. 2026. LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations? arXiv preprint arXiv:2605.26781 (2026)."},{"key":"e_1_3_2_2_61_1","first-page":"1114","article-title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","author":"Wang Zeyuan","year":"2024","unstructured":"Zeyuan Wang, Qiang Zhang, Keyan Ding, Ming Qin, Xiang Zhuang, Xiaotong Li, and Huajun Chen. 2024b. InstructProtein: Aligning Human and Protein Language via Knowledge Instruction. In Association for Computational Linguistics. 1114-1136.","journal-title":"Association for Computational Linguistics."},{"key":"e_1_3_2_2_62_1","volume-title":"Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 3216\u20133227","author":"Wu Wei","year":"2025","unstructured":"Wei Wu, Chao Wang, Liyi Chen, Mingze Yin, Yiheng Zhu, Kun Fu, Jieping Ye, Hui Xiong, and Zheng Wang. 2025. Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 3216\u20133227."},{"key":"e_1_3_2_2_63_1","volume-title":"Mixture of LoRA Experts. In International Conference on Learning Representations.","author":"Wu Xun","year":"2024","unstructured":"Xun Wu, Shaohan Huang, and Furu Wei. 2024. Mixture of LoRA Experts. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_64_1","volume-title":"ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts. In International Conference on Machine Learning.","author":"Xu Minghao","year":"2023","unstructured":"Minghao Xu, Xinyu Yuan, Santiago Miret, and Jian Tang. 2023. ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_65_1","volume-title":"PEER: A comprehensive and multi-task benchmark for protein sequence understanding. In Advances in Neural Information Processing Systems.","author":"Xu Minghao","year":"2022","unstructured":"Minghao Xu, Zuobai Zhang, Jiarui Lu, Zhaocheng Zhu, Yangtian Zhang, Ma Chang, Runcheng Liu, and Jian Tang. 2022. PEER: A comprehensive and multi-task benchmark for protein sequence understanding. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_66_1","volume-title":"V8","author":"Yin Mingze","year":"2025","unstructured":"Mingze Yin, Hanjing Zhou, Jialu Wu, Yiheng Zhu, Yuxuan Zhan, Zitai Kong, Hongxia Xu, Chang-Yu Hsieh, Jintai Chen, Tingjun Hou, and Jian Wu. 2025a. S$^2$ALM: Sequence-Structure Pre-trained Large Language Model for Comprehensive Antibody Representation Learning. Research, V8 (2025), 0721."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"crossref","unstructured":"Mingze Yin Hanjing Zhou Yiheng Zhu Miao Lin Yixuan Wu Jialu Wu Hongxia Xu Chang-Yu Hsieh Tingjun Hou Jintai Chen et al. 2024. Multi-Modal CLIP-Informed Protein Editing. Health Data Science V4 (2024) 0211.","DOI":"10.34133\/hds.0211"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34370"},{"key":"e_1_3_2_2_69_1","volume-title":"Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding. In International Conference on Machine Learning.","author":"Zhang Jiasheng","year":"2025","unstructured":"Jiasheng Zhang, Delvin Ce Zhang, Shuang Liang, Zhengpin Li, Rex Ying, and Jie Shao. 2025. Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_70_1","volume-title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding. In International Conference on Learning Representations.","author":"Zhang Ningyu","year":"2022","unstructured":"Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Qiang Zhang, Jiazhang Lian, and Huajun Chen. 2022. OntoProtein: Protein Pretraining With Gene Ontology Embedding. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34456"},{"key":"e_1_3_2_2_72_1","volume-title":"International Conference on Learning Representations.","author":"Zhou Hong-Yu","year":"2023","unstructured":"Hong-Yu Zhou, Yunxiang Fu, Zhicheng Zhang, Bian Cheng, and Yizhou Yu. 2023. Protein representation learning via knowledge enhanced primary structure reasoning. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_73_1","volume-title":"Decoding the Molecular Language of Proteins with Evolla. bioRxiv","author":"Zhou Xibin","year":"2025","unstructured":"Xibin Zhou, Chenchen Han, Yingqi Zhang, Jin Su, Kai Zhuang, Shiyu Jiang, Zichen Yuan, Wei Zheng, Fengyuan Dai, Yuyang Zhou, Yuyang Tao, Dan Wu, and Fajie Yuan. 2025a. Decoding the Molecular Language of Proteins with Evolla. bioRxiv (2025)."},{"key":"e_1_3_2_2_74_1","volume-title":"International Conference on Machine Learning.","author":"Zhou Yuhua","year":"2025","unstructured":"Yuhua Zhou, Ruifeng Li, Changhai Zhou, Fei Yang, and Aimin Pan. 2025b. BSLoRA: Enhancing the parameter efficiency of loRA with intra-layer and inter-layer sharing. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_75_1","unstructured":"Yiheng Zhu Jian Ma Mingze Yin Jialu Wu Lin Tang Zhiyun Zhang Qiuyi Li Shikun Feng Haiguang Liu Tao Qin et al. 2026. Ophiuchus-Ab: A Versatile Generative Foundation Model for Advanced Antibody-Based Immunotherapy. bioRxiv (2026) 2026-02."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:28:33Z","timestamp":1786066113000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":75,"alternative-id":["10.1145\/3770855.3818885","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818885","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}