{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T21:14:16Z","timestamp":1788556456507,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":54,"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\/4.0\/legalcode"}],"funder":[{"name":"NUS Artificial Intelligence Institute (NAII)","award":["A-8003158-00-00"],"award-info":[{"award-number":["A-8003158-00-00"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818997","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"12231-12242","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DeepTaxon: An Interpretable Retrieval-Augmented Multimodal Framework for Unified Species Identification and Discovery"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6601-2958","authenticated-orcid":false,"given":"Jiawei","family":"Wang","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9097-9084","authenticated-orcid":false,"given":"Ming","family":"Lei","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5819-7005","authenticated-orcid":false,"given":"Yaning","family":"Yang","sequence":"additional","affiliation":[{"name":"Xiangtan University, Xiangtan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3495-3231","authenticated-orcid":false,"given":"Xinyan","family":"Lin","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6283-9037","authenticated-orcid":false,"given":"Yuquan","family":"Le","sequence":"additional","affiliation":[{"name":"Hunan Normal University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2382-1416","authenticated-orcid":false,"given":"Qiwei","family":"Ma","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1829-2468","authenticated-orcid":false,"given":"Zhiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Meituan, Hangzhou, China and Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6529-8088","authenticated-orcid":false,"given":"Zheqi","family":"Lv","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5889-018X","authenticated-orcid":false,"given":"Yuchen","family":"Ang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2669-9190","authenticated-orcid":false,"given":"Zhe","family":"Quan","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_2_2_1","unstructured":"Shuai Bai et al. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_2_4_1","volume-title":"doubao-seed-1.6-vision. https:\/\/www.volcengine.com\/products\/doubao. Accessed","year":"2025","unstructured":"ByteDance. 2025. doubao-seed-1.6-vision. https:\/\/www.volcengine.com\/products\/doubao. Accessed 2025."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 3163-3171","author":"Chang Wei-Cheng","unstructured":"Wei-Cheng Chang, Hsiang-Fu Yu, Kai Zhong, Yiming Yang, and Inderjit S. Dhillon. 2020. Taming Pretrained Transformers for eXtreme Multi-label Text Classification. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 3163-3171."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240523"},{"key":"e_1_3_2_2_7_1","volume-title":"ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models. arXiv preprint arXiv:2510.01582","author":"Chitty-Venkata Krishna Teja","year":"2025","unstructured":"Krishna Teja Chitty-Venkata and Murali Emani. 2025. ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models. arXiv preprint arXiv:2510.01582 (2025)."},{"key":"e_1_3_2_2_8_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"e_1_3_2_2_10_1","volume-title":"Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805","author":"Team Gemini","year":"2023","unstructured":"Gemini Team. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"kNN-CLIP: Retrieval enables training-free segmentation on continually expanding large vocabularies. arXiv preprint arXiv:2404.09447","author":"Gui Zhongrui","year":"2024","unstructured":"Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, and Philip Torr. 2024. kNN-CLIP: Retrieval enables training-free segmentation on continually expanding large vocabularies. arXiv preprint arXiv:2404.09447 (2024)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Learning Representations.","author":"Hendrycks Dan","year":"2017","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_14_1","volume-title":"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_15_1","volume-title":"V91","author":"Hu Xiaobin","year":"2023","unstructured":"Xiaobin Hu, Shining Zhu, and Taile Peng. 2023. Hierarchical attention vision transformer for fine-grained visual classification. Journal of Visual Communication and Image Representation, V91 (2023), 103755."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","unstructured":"Gabriel Ilharco Mitchell Wortsman Ross Wightman Cade Gordon Nicholas Carlini Rohan Taori Achal Dave Vaishaal Shankar Hongseok Namkoong John Miller Hannaneh Hajishirzi Ali Farhadi and Ludwig Schmidt. 2021. OpenCLIP. https:\/\/doi.org\/10.5281\/zenodo.5143773.","DOI":"10.5281\/zenodo.5143773"},{"key":"e_1_3_2_2_17_1","first-page":"1","article-title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","volume":"24","author":"Izacard Gautier","year":"2023","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2023. Atlas: Few-shot Learning with Retrieval Augmented Language Models. Journal of Machine Learning Research, V24, 251 (2023), 1-43.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson Jeff","year":"2019","unstructured":"Jeff Johnson, Matthijs Douze, and Herv\u00e9 J\u00e9gou. 2019. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, V7, 3 (2019), 535-547.","journal-title":"IEEE Transactions on Big Data"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672063"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization.","author":"Khosla Aditya","year":"2011","unstructured":"Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Li Fei-Fei. 2011. Novel dataset for fine-grained image categorization: Stanford Dogs. In Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization."},{"key":"e_1_3_2_2_21_1","volume-title":"International Conference on Learning Representations.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01686"},{"key":"e_1_3_2_2_24_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in neural information processing systems V33 (2020) 9459-9474."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00721"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_4"},{"key":"e_1_3_2_2_28_1","volume-title":"Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151","author":"Maji Subhransu","year":"2013","unstructured":"Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew Blaschko, and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28217"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1719367115"},{"key":"e_1_3_2_2_32_1","unstructured":"OpenAI. 2023. GPT-4V(ision) system card. OpenAI Technical Report (2023)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeff 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. Advances in Neural Information Processing Systems V35 (2022) 27730-27744.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_2_34_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Peng Zhiliang","year":"2024","unstructured":"Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, Qixiang Ye, and Furu Wei. 2024. Kosmos-2: Grounding Multimodal Large Language Models to the World. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_2_36_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Ridnik Tal","year":"2021","unstructured":"Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, and Lihi Zelnik-Manor. 2021. ImageNet-21K pretraining for the masses. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"e_1_3_2_2_38_1","volume-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, and Daya Guo. 2024. DeepSeekMath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_2_39_1","volume-title":"Scaling LLM test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314","author":"Snell Charlie","year":"2024","unstructured":"Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. Scaling LLM test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314 (2024)."},{"key":"e_1_3_2_2_40_1","volume-title":"V169","author":"Sullivan Brian L.","year":"2014","unstructured":"Brian L. Sullivan, Jocelyn L. Aycrigg, Jessie H. Barry, Rick E. Bonney, Nicholas Bruns, Caren B. Cooper, Theo Damoulas, Andr\u00e9 A. Dhondt, Tom Dietterich, Andrew Farnsworth, Daniel Fink, John W. Fitzpatrick, Thomas Fredericks, Jeff Gerbracht, Carla Gomes, Wesley M. Hochachka, Marshall J. Iliff, Carl Lagoze, Frank A. La Sorte, Matthew Merrifield, Will Morris, Tina B. Phillips, Mark Reynolds, Amanda D. Rodewald, Kenneth V. Rosenberg, Nancy M. Trautmann, Andrea Wiggins, David W. Winkler, Weng-Keen Wong, Christopher L. Wood, Jun Yu, and Steve Kelling. 2014. The eBird enterprise: An integrated approach to development and application of citizen science. Biological Conservation, V169 (2014), 31-40."},{"key":"e_1_3_2_2_41_1","volume-title":"V34","author":"Sun Yiyou","year":"2021","unstructured":"Yiyou Sun, Chuan Guo, and Yixuan Li. 2021. ReAct: Out-of-distribution detection with rectified activations. Advances in neural information processing systems, V34 (2021), 144-157."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"e_1_3_2_2_43_1","volume-title":"V9, 11","author":"W\u00e4ldchen Jana","year":"2018","unstructured":"Jana W\u00e4ldchen and Patrick M\u00e4der. 2018. Machine learning for image based species identification. Methods in Ecology and Evolution, V9, 11 (2018), 2216-2225."},{"key":"e_1_3_2_2_44_1","volume-title":"XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained Recognition. arXiv preprint arXiv:2503.07075","author":"Wang Chuanming","year":"2025","unstructured":"Chuanming Wang, Henming Mao, Huanhuan Zhang, Huiyuan Fu, and Huadong Ma. 2025. XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained Recognition. arXiv preprint arXiv:2503.07075 (2025)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681263"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613822"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","first-page":"10393","DOI":"10.1109\/TCYB.2021.3069836","article-title":"Progressive self-supervised clustering with novel category discovery","volume":"52","author":"Wang Jingyu","year":"2021","unstructured":"Jingyu Wang, Zhenyu Ma, Feiping Nie, and Xuelong Li. 2021. Progressive self-supervised clustering with novel category discovery. IEEE Transactions on Cybernetics, V52, 10 (2021), 10393-10406.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (PhD Consortium). ACM.","author":"Wang Ziqing","year":"2025","unstructured":"Ziqing Wang. 2025. ReMol: LLM-guided Molecular Optimization with Reinforcement Learning. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (PhD Consortium). ACM."},{"key":"e_1_3_2_2_50_1","volume-title":"Chi, Quoc V Le, and Denny Zhou","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, V35 (2022), 24824-24837."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357503"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Jingkang Yang Pengyun Wang Dejian Zou Zitang Zhou Kunyuan Ding Wenxuan Peng Haoqi Wang Guangyao Chen Bo Li Yiyou Sun et al. 2022. OpenOOD: Benchmarking generalized out-of-distribution detection. Advances in Neural Information Processing Systems V35 (2022) 32598-32611.","DOI":"10.52202\/068431-2362"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02587"},{"key":"e_1_3_2_2_54_1","volume-title":"Multimodal Chain-of-Thought Reasoning in Language Models. Transactions on Machine Learning Research (TMLR)","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023. Multimodal Chain-of-Thought Reasoning in Language Models. Transactions on Machine Learning Research (TMLR) (2023)."}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770855.3818997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T20:34:23Z","timestamp":1788554063000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818997"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":54,"alternative-id":["10.1145\/3770855.3818997","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818997","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"}}]}}