{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:47:49Z","timestamp":1787017669191,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023ZD0120801"],"award-info":[{"award-number":["2023ZD0120801"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472381"],"award-info":[{"award-number":["62472381"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730064","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:21:38Z","timestamp":1752456098000},"page":"1076-1086","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["ProtChatGPT: Towards Understanding Proteins with Hybrid Representation and Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1297-768X","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"first","affiliation":[{"name":"CSIRO's Data 61, Sydney, NSW, Australia and The University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9572-2345","authenticated-orcid":false,"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4077-1398","authenticated-orcid":false,"given":"Ruijie","family":"Quan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4149-839X","authenticated-orcid":false,"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"CSIRO's Data 61, Sydney, NSW, Australia and The University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems 35 (2022), 23716-23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","volume-title":"The protein data bank. Nucleic acids research 28, 1","author":"Berman Helen M","year":"2000","unstructured":"Helen M Berman, John Westbrook, Zukang Feng, Gary Gilliland, Talapady N Bhat, Helge Weissig, Ilya N Shindyalov, and Philip E Bourne. 2000. The protein data bank. Nucleic acids research 28, 1 (2000), 235-242."},{"key":"e_1_3_2_1_3_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_1_4_1","volume-title":"Charles Sutton, Sebastian Gehrmann, et al.","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv:2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_6_1","volume-title":"Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36","author":"Dettmers Tim","year":"2024","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2024. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"Ankh: Optimized protein language model unlocks general-purpose modelling. arXiv preprint arXiv:2301.06568","author":"Elnaggar Ahmed","year":"2023","unstructured":"Ahmed Elnaggar, Hazem Essam, Wafaa Salah-Eldin, Walid Moustafa, Mohamed Elkerdawy, Charlotte Rochereau, and Burkhard Rost. 2023. Ankh: Optimized protein language model unlocks general-purpose modelling. arXiv preprint arXiv:2301.06568 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Fan Hehe","year":"2022","unstructured":"Hehe Fan, ZhangyangWang, Yi Yang, and Mohan Kankanhalli. 2022. Continuousdiscrete convolution for geometry-sequence modeling in proteins. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01697"},{"key":"e_1_3_2_1_11_1","volume-title":"Daniel Berenberg, Tommi Vatanen, Chris Chandler, Bryn C Taylor, Ian M Fisk, Hera Vlamakis, et al.","author":"Gligorijevic Vladimir","year":"2021","unstructured":"Vladimir Gligorijevic, 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 12, 1 (2021), 3168."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"e_1_3_2_1_13_1","volume-title":"Proteinchat: Towards achieving chatgpt-like functionalities on protein 3d structures. Authorea Preprints","author":"Guo Han","year":"2023","unstructured":"Han Guo, Mingjia Huo, Ruiyi Zhang, and Pengtao Xie. 2023. Proteinchat: Towards achieving chatgpt-like functionalities on protein 3d structures. Authorea Preprints (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.04.10.487779"},{"key":"e_1_3_2_1_15_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Iterative refinement graph neural network for antibody sequence-structure codesign. arXiv preprint arXiv:2110.04624","author":"Jin Wengong","year":"2021","unstructured":"Wengong Jin, Jeremy Wohlwend, Regina Barzilay, and Tommi Jaakkola. 2021. Iterative refinement graph neural network for antibody sequence-structure codesign. arXiv preprint arXiv:2110.04624 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Raphael JL Townshend, and Ron Dror","author":"Jing Bowen","year":"2020","unstructured":"Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael JL Townshend, and Ron Dror. 2020. Learning from protein structure with geometric vector perceptrons. arXiv preprint arXiv:2009.01411 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin Z\u00eddek Anna Potapenko et al. 2021. Highly accurate protein structure prediction with AlphaFold. Nature 596 7873 (2021) 583-589.","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_1_19_1","volume-title":"Scaling laws for forgetting when fine-tuning large language models. arXiv preprint arXiv:2401.05605","author":"Kalajdzievski Damjan","year":"2024","unstructured":"Damjan Kalajdzievski. 2024. Scaling laws for forgetting when fine-tuning large language models. arXiv preprint arXiv:2401.05605 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.25674"},{"key":"e_1_3_2_1_21_1","volume-title":"Grounding language models to images for multimodal generation. arXiv preprint arXiv:2301.13823","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Ruslan Salakhutdinov, and Daniel Fried. 2023. Grounding language models to images for multimodal generation. arXiv preprint arXiv:2301.13823 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Conditional antibody design as 3d equivariant graph translation. arXiv preprint arXiv:2208.06073","author":"Kong Xiangzhe","year":"2022","unstructured":"Xiangzhe Kong, Wenbing Huang, and Yang Liu. 2022. Conditional antibody design as 3d equivariant graph translation. arXiv preprint arXiv:2208.06073 (2022)."},{"key":"e_1_3_2_1_23_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_24_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. Evolutionaryscale prediction of atomic-level protein structure with a language model. Science 379 6637 (2023) 1123-1130.","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_2_1_25_1","unstructured":"Shengchao Liu Yanjing Li Zhuoxinran Li Anthony Gitter Yutao Zhu Jiarui Lu Zhao Xu Weili Nie Arvind Ramanathan Chaowei Xiao et al. 2023. A text-guided protein design framework. arXiv preprint arXiv:2302.04611 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"ProtT3: Protein-to-Text Generation for Text-based Protein Understanding. arXiv preprint arXiv:2405.12564","author":"Liu Zhiyuan","year":"2024","unstructured":"Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, and Tat-Seng Chua. 2024. ProtT3: Protein-to-Text Generation for Text-based Protein Understanding. arXiv preprint arXiv:2405.12564 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_28_1","volume-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747","author":"Luo Yun","year":"2023","unstructured":"Yun Luo, Zhen Yang, Fandong Meng, Yafu Li, Jie Zhou, and Yue Zhang. 2023. An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Caiming Xiong, Zachary Z Sun, Richard Socher, et al.","author":"Madani Ali","year":"2023","unstructured":"Ali Madani, Ben Krause, Eric R Greene, Subu Subramanian, Benjamin P Mohr, James M Holton, Jose Luis Olmos Jr, Caiming Xiong, Zachary Z Sun, Richard Socher, et al. 2023. Large language models generate functional protein sequences across diverse families. Nature Biotechnology (2023), 1-8."},{"key":"e_1_3_2_1_30_1","volume-title":"EGRET: edge aggregated graph attention networks and transfer learning improve protein-protein interaction site prediction. Briefings in Bioinformatics 23, 2","author":"Mahbub Sazan","year":"2022","unstructured":"Sazan Mahbub and Md Shamsuzzoha Bayzid. 2022. EGRET: edge aggregated graph attention networks and transfer learning improve protein-protein interaction site prediction. Briefings in Bioinformatics 23, 2 (2022), bbab578."},{"key":"e_1_3_2_1_31_1","first-page":"29287","article-title":"Language models enable zero-shot prediction of the effects of mutations on protein function","volume":"34","author":"Meier Joshua","year":"2021","unstructured":"Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu, and Alex Rives. 2021. Language models enable zero-shot prediction of the effects of mutations on protein function. Advances in Neural Information Processing Systems 34 (2021), 29287-29303.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","volume-title":"Silvio CE Tosatto, Lisanna Paladin, Shriya Raj, Lorna J Richardson, et al.","author":"Mistry Jaina","year":"2021","unstructured":"Jaina Mistry, Sara Chuguransky, Lowri Williams, Matloob Qureshi, Gustavo A Salazar, Erik LL Sonnhammer, Silvio CE Tosatto, Lisanna Paladin, Shriya Raj, Lorna J Richardson, et al. 2021. Pfam: The protein families database in 2021. Nucleic acids research 49, D1 (2021), D412-D419."},{"key":"e_1_3_2_1_33_1","volume-title":"Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation. arXiv preprint arXiv:2402.18334","author":"Nayak Nihal V","year":"2024","unstructured":"Nihal V Nayak, Yiyang Nan, Avi Trost, and Stephen H Bach. 2024. Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation. arXiv preprint arXiv:2402.18334 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. 16990-17017","author":"Notin Pascal","year":"2022","unstructured":"Pascal Notin, Mafalda Dias, Jonathan Frazer, Javier Marchena Hurtado, Aidan N Gomez, Debora Marks, and Yarin Gal. 2022. Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval. In International Conference on Machine Learning. 16990-17017."},{"key":"e_1_3_2_1_35_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00038"},{"key":"e_1_3_2_1_37_1","unstructured":"Alec Radford JeffreyWu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1101\/2020.12.15.422761"},{"key":"e_1_3_2_1_40_1","volume-title":"DeepRank-GNN: a graph neural network framework to learn patterns in protein- protein interfaces. Bioinformatics 39, 1","author":"R\u00e9au Manon","year":"2023","unstructured":"Manon R\u00e9au, Nicolas Renaud, Li C Xue, and Alexandre MJJ Bonvin. 2023. DeepRank-GNN: a graph neural network framework to learn patterns in protein- protein interfaces. Bioinformatics 39, 1 (2023), btac759."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"e_1_3_2_1_42_1","volume-title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding. arXiv preprint arXiv:2406.05540","author":"Shen Yiqing","year":"2024","unstructured":"Yiqing Shen, Zan Chen, Michail Mamalakis, Luhan He, Haiyang Xia, Tianbin Li, Yanzhou Su, Junjun He, and Yu Guang Wang. 2024. A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding. arXiv preprint arXiv:2406.05540 (2024)."},{"key":"e_1_3_2_1_43_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_1_44_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Ivona Najdenkoska, Cees GM Snoek, and Marcel Worring.","author":"van Sonsbeek Tom","year":"2023","unstructured":"Tom van Sonsbeek, Mohammad Mahdi Derakhshani, Ivona Najdenkoska, Cees GM Snoek, and Marcel Worring. 2023. Open-ended medical visual question answering through prefix tuning of language models. arXiv preprint arXiv:2303.05977 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Mihaly Varadi Stephen Anyango Mandar Deshpande Sreenath Nair Cindy Natassia Galabina Yordanova David Yuan Oana Stroe Gemma Wood Agata Laydon et al. 2022. AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic acids research 50 D1 (2022) D439-D444.","DOI":"10.1093\/nar\/gkab1061"},{"key":"e_1_3_2_1_47_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_48_1","volume-title":"Bertology meets biology: Interpreting attention in protein language models. arXiv preprint arXiv:2006.15222","author":"Vig Jesse","year":"2020","unstructured":"Jesse Vig, Ali Madani, Lav R Varshney, Caiming Xiong, Richard Socher, and Nazneen Fatema Rajani. 2020. Bertology meets biology: Interpreting attention in protein language models. arXiv preprint arXiv:2006.15222 (2020)."},{"key":"e_1_3_2_1_49_1","volume-title":"Chatcad: Interactive computer-aided diagnosis on medical image using large language models. arXiv preprint arXiv:2302.07257","author":"Wang Sheng","year":"2023","unstructured":"Sheng Wang, Zihao Zhao, Xi Ouyang, Qian Wang, and Dinggang Shen. 2023. Chatcad: Interactive computer-aided diagnosis on medical image using large language models. arXiv preprint arXiv:2302.07257 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"Protst: Multimodality learning of protein sequences and biomedical texts. arXiv preprint arXiv:2301.12040","author":"Xu Minghao","year":"2023","unstructured":"Minghao Xu, Xinyu Yuan, Santiago Miret, and Jian Tang. 2023. Protst: Multimodality learning of protein sequences and biomedical texts. arXiv preprint arXiv:2301.12040 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705322"},{"key":"e_1_3_2_1_52_1","volume-title":"Ontoprotein: Protein pretraining with gene ontology embedding. arXiv preprint arXiv:2201.11147","author":"Zhang Ningyu","year":"2022","unstructured":"Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Jiazhang Lian, Qiang Zhang, and Huajun Chen. 2022. Ontoprotein: Protein pretraining with gene ontology embedding. arXiv preprint arXiv:2201.11147 (2022)."},{"key":"e_1_3_2_1_53_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Zhang Ningyu","year":"2022","unstructured":"Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Jiazhang Lian, Qiang Zhang, and Huajun Chen. 2022. Ontoprotein: Protein pretraining with gene ontology embedding. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_54_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Zuobai","year":"2023","unstructured":"Zuobai Zhang, Minghao Xu, Arian Jamasb, Vijil Chenthamarakshan, Aurelie Lozano, Payel Das, and Jian Tang. 2023. Protein representation learning by geometric structure pretraining. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_55_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T09:59:15Z","timestamp":1755856755000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730064"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":55,"alternative-id":["10.1145\/3726302.3730064","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730064","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}