{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:19:37Z","timestamp":1784179177389,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":85,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657725","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"687-697","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-2042","authenticated-orcid":false,"given":"Junchen","family":"Fu","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3925-4951","authenticated-orcid":false,"given":"Xuri","family":"Ge","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-9115","authenticated-orcid":false,"given":"Xin","family":"Xin","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6063-9023","authenticated-orcid":false,"given":"Alexandros","family":"Karatzoglou","sequence":"additional","affiliation":[{"name":"Amazon, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2528-6597","authenticated-orcid":false,"given":"Ioannis","family":"Arapakis","sequence":"additional","affiliation":[{"name":"Telefonica Research, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7117-8580","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9228-1759","authenticated-orcid":false,"given":"Joemon M.","family":"Jose","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","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_1_2_1","volume-title":"Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447","author":"Bao Keqin","year":"2023","unstructured":"Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447 (2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_4_1","first-page":"11285","article-title":"Tinytl: Reduce memory, not parameters for efficient on-device learning","volume":"33","author":"Cai Han","year":"2020","unstructured":"Han Cai, Chuang Gan, Ligeng Zhu, and Song Han. 2020. Tinytl: Reduce memory, not parameters for efficient on-device learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 11285--11297.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10311-022-01435-8"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964711"},{"key":"e_1_3_2_1_7_1","volume-title":"Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534","author":"Chen Zhe","year":"2022","unstructured":"Zhe Chen, Yuchen Duan, Wenhai Wang, Junjun He, Tong Lu, Jifeng Dai, and Yu Qiao. 2022a. Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"An Image Dataset for Benchmarking Recommender Systems with Raw Pixels. arXiv preprint arXiv:2309.06789","author":"Cheng Yu","year":"2023","unstructured":"Yu Cheng, Yunzhu Pan, Jiaqi Zhang, Yongxin Ni, Aixin Sun, and Fajie Yuan. 2023. An Image Dataset for Benchmarking Recommender Systems with Raw Pixels. arXiv preprint arXiv:2309.06789 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084","author":"Cui Zeyu","year":"2022","unstructured":"Zeyu Cui, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Qlora: Efficient finetuning of quantized llms. arXiv preprint arXiv:2305.14314","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. arXiv preprint arXiv:2305.14314 (2023)."},{"key":"e_1_3_2_1_11_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_12_1","unstructured":"Alexey Dosovitskiy Lucas Beyer et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"End-to-End Image-Based Fashion Recommendation. arXiv preprint arXiv:2205.02923","author":"Elsayed Shereen","year":"2022","unstructured":"Shereen Elsayed, Lukas Brinkmeyer, and Lars Schmidt-Thieme. 2022. End-to-End Image-Based Fashion Recommendation. arXiv preprint arXiv:2205.02923 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Reducing transformer depth on demand with structured dropout. arXiv preprint arXiv:1909.11556","author":"Fan Angela","year":"2019","unstructured":"Angela Fan, Edouard Grave, and Armand Joulin. 2019. Reducing transformer depth on demand with structured dropout. arXiv preprint arXiv:1909.11556 (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635805"},{"key":"e_1_3_2_1_16_1","volume-title":"Scaling deep contrastive learning batch size under memory limited setup. arXiv preprint arXiv:2101.06983","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao, Yunyi Zhang, Jiawei Han, and Jamie Callan. 2021. Scaling deep contrastive learning batch size under memory limited setup. arXiv preprint arXiv:2101.06983 (2021)."},{"key":"e_1_3_2_1_17_1","unstructured":"Peng Gao Jiaming Han Renrui Zhang Ziyi Lin Shijie Geng Aojun Zhou Wei Zhang Pan Lu Conghui He Xiangyu Yue et al. 2023. Llama-adapter v2: Parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00069"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00108"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103716"},{"key":"e_1_3_2_1_22_1","volume-title":"VIP5: Towards Multimodal Foundation Models for Recommendation. arXiv preprint arXiv:2305.14302","author":"Geng Shijie","year":"2023","unstructured":"Shijie Geng, Juntao Tan, Shuchang Liu, Zuohui Fu, and Yongfeng Zhang. 2023. VIP5: Towards Multimodal Foundation Models for Recommendation. arXiv preprint arXiv:2305.14302 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"The reversible residual network: Backpropagation without storing activations. Advances in neural information processing systems","author":"Gomez Aidan N","year":"2017","unstructured":"Aidan N Gomez, Mengye Ren, Raquel Urtasun, and Roger B Grosse. 2017. The reversible residual network: Backpropagation without storing activations. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_25_1","volume-title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543","author":"He Pengcheng","year":"2021","unstructured":"Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654","author":"He Pengcheng","year":"2020","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Xuehai He Chunyuan Li Pengchuan Zhang Jianwei Yang and Xin Eric Wang. 2022. Parameter-efficient Fine-tuning for Vision Transformers. https:\/\/doi.org\/10.48550\/ARXIV.2203.16329","DOI":"10.48550\/ARXIV.2203.16329"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_29_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_30_1","volume-title":"Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders. arXiv preprint arXiv:2210.12316","author":"Hou Yupeng","year":"2022","unstructured":"Yupeng Hou, Zhankui He, Julian McAuley, and Wayne Xin Zhao. 2022a. Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders. arXiv preprint arXiv:2210.12316 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR, 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. PMLR, 2790--2799."},{"key":"e_1_3_2_1_33_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_34_1","volume-title":"Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision. arXiv preprint arXiv:2401.07257","author":"Hu Hengchang","year":"2024","unstructured":"Hengchang Hu, Qijiong Liu, Chuang Li, and Min-Yen Kan. 2024. Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision. arXiv preprint arXiv:2401.07257 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Introduction to transformers for NLP: With the hugging face library and models to solve problems","author":"Jain Shashank Mohan","unstructured":"Shashank Mohan Jain. 2022. Hugging face. In Introduction to transformers for NLP: With the hugging face library and models to solve problems. Springer, 51--67."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612091"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.268884"},{"key":"e_1_3_2_1_39_1","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume":"34","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, Vol. 34 (2021), 1022--1035.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_40_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Walid Krichene and Steffen Rendle. 2020. On Sampled Metrics for Item Recommendation. In KDD.","DOI":"10.1145\/3394486.3403226"},{"key":"e_1_3_2_1_42_1","article-title":"Exploring strategies for training deep neural networks","volume":"10","author":"Larochelle Hugo","year":"2009","unstructured":"Hugo Larochelle, Yoshua Bengio, J\u00e9r\u00f4me Louradour, and Pascal Lamblin. 2009. Exploring strategies for training deep neural networks. Journal of machine learning research, Vol. 10, 1 (2009).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_43_1","volume-title":"2023 a. Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights. arXiv preprint arXiv:2305.11700","author":"Li Ruyu","year":"2023","unstructured":"Ruyu Li, Wenhao Deng, Yu Cheng, Zheng Yuan, Jiaqi Zhang, and Fajie Yuan. 2023 a. Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights. arXiv preprint arXiv:2305.11700 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders. arXiv preprint arXiv:2403.17372","author":"Li Youhua","year":"2024","unstructured":"Youhua Li, Hanwen Du, Yongxin Ni, Yuanqi He, Junchen Fu, Xiangyan Liu, and Qi Guo. 2024. An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders. arXiv preprint arXiv:2403.17372 (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"2023 b. Multi-Modality is All You Need for Transferable Recommender Systems. arXiv preprint arXiv:2312.09602","author":"Li Youhua","year":"2023","unstructured":"Youhua Li, Hanwen Du, Yongxin Ni, Pengpeng Zhao, Qi Guo, Fajie Yuan, and Xiaofang Zhou. 2023 b. Multi-Modality is All You Need for Transferable Recommender Systems. arXiv preprint arXiv:2312.09602 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635845"},{"key":"e_1_3_2_1_48_1","volume-title":"ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation. arXiv preprint arXiv:2311.05956","author":"Liu Yuting","year":"2023","unstructured":"Yuting Liu, Enneng Yang, Yizhou Dang, Guibing Guo, Qiang Liu, Yuliang Liang, Linying Jiang, and Xingwei Wang. 2023. ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation. arXiv preprint arXiv:2311.05956 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413598"},{"key":"e_1_3_2_1_51_1","volume-title":"ID-Agnostic User Behavior Pre-training for Sequential Recommendation. In China Conference on Information Retrieval. Springer, 16--27","author":"Mu Shanlei","year":"2022","unstructured":"Shanlei Mu, Yupeng Hou, Wayne Xin Zhao, Yaliang Li, and Bolin Ding. 2022. ID-Agnostic User Behavior Pre-training for Sequential Recommendation. In China Conference on Information Retrieval. Springer, 16--27."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_53_1","volume-title":"A Content-Driven Micro-Video Recommendation Dataset at Scale. arXiv preprint arXiv:2309.15379","author":"Ni Yongxin","year":"2023","unstructured":"Yongxin Ni, Yu Cheng, Xiangyan Liu, Junchen Fu, Youhua Li, Xiangnan He, Yongfeng Zhang, and Fajie Yuan. 2023. A Content-Driven Micro-Video Recommendation Dataset at Scale. arXiv preprint arXiv:2309.15379 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation. arXiv preprint arXiv:2310.01612","author":"Peng Bo","year":"2023","unstructured":"Bo Peng, Ben Burns, Ziqi Chen, Srinivasan Parthasarathy, and Xia Ning. 2023. Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation. arXiv preprint arXiv:2310.01612 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"Adapterhub: A framework for adapting transformers. arXiv preprint arXiv:2007.07779","author":"Pfeiffer Jonas","year":"2020","unstructured":"Jonas Pfeiffer, Andreas R\u00fcckl\u00e9, Clifton Poth, Aishwarya Kamath, Ivan Vulic, Sebastian Ruder, Kyunghyun Cho, and Iryna Gurevych. 2020. Adapterhub: A framework for adapting transformers. arXiv preprint arXiv:2007.07779 (2020)."},{"key":"e_1_3_2_1_56_1","volume-title":"Thoroughly Modeling Multi-domain Pre-trained Recommendation as Language. arXiv preprint arXiv:2310.13540","author":"Qu Zekai","year":"2023","unstructured":"Zekai Qu, Ruobing Xie, Chaojun Xiao, Yuan Yao, Zhiyuan Liu, Fengzong Lian, Zhanhui Kang, and Jie Zhou. 2023. Thoroughly Modeling Multi-domain Pre-trained Recommendation as Language. arXiv preprint arXiv:2310.13540 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_59_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3127907"},{"key":"e_1_3_2_1_61_1","volume-title":"The human development index: a critical review. Ecological economics","author":"Sagar Ambuj D","year":"1998","unstructured":"Ambuj D Sagar and Adil Najam. 1998. The human development index: a critical review. Ecological economics, Vol. 25, 3 (1998), 249--264."},{"key":"e_1_3_2_1_62_1","volume-title":"The algorithm design manual","author":"Skiena Steven S","unstructured":"Steven S Skiena. 1998. The algorithm design manual. Vol. 2. Springer."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411947"},{"key":"e_1_3_2_1_65_1","first-page":"12991","article-title":"Lst: Ladder side-tuning for parameter and memory efficient transfer learning","volume":"35","author":"Sung Yi-Lin","year":"2022","unstructured":"Yi-Lin Sung, Jaemin Cho, and Mohit Bansal. 2022. Lst: Ladder side-tuning for parameter and memory efficient transfer learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 12991--13005.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_66_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_67_1","volume-title":"TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback. arXiv preprint arXiv:2206.06190","author":"Wang Jie","year":"2022","unstructured":"Jie Wang, Fajie Yuan, Mingyue Cheng, Joemon M Jose, Chenyun Yu, Beibei Kong, Zhijin Wang, Bo Hu, and Zang Li. 2022. TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback. arXiv preprint arXiv:2206.06190 (2022)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611967"},{"key":"e_1_3_2_1_69_1","volume-title":"K-adapter: Infusing knowledge into pre-trained models with adapters. arXiv preprint arXiv:2002.01808","author":"Wang Ruize","year":"2020","unstructured":"Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Guihong Cao, Daxin Jiang, Ming Zhou, et al. 2020. K-adapter: Infusing knowledge into pre-trained models with adapters. arXiv preprint arXiv:2002.01808 (2020)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583206"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_72_1","volume-title":"Carbon-neutral pathways for the United States. AGU advances","author":"Williams James H","year":"2021","unstructured":"James H Williams, Ryan A Jones, Ben Haley, Gabe Kwok, Jeremy Hargreaves, Jamil Farbes, and Margaret S Torn. 2021. Carbon-neutral pathways for the United States. AGU advances, Vol. 2, 1 (2021), e2020AV000284."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463069"},{"key":"e_1_3_2_1_74_1","volume-title":"Mm-rec: multimodal news recommendation. arXiv preprint arXiv:2104.07407","author":"Wu Chuhan","year":"2021","unstructured":"Chuhan Wu, Fangzhao Wu, Tao Qi, and Yongfeng Huang. 2021b. Mm-rec: multimodal news recommendation. arXiv preprint arXiv:2104.07407 (2021)."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401145"},{"key":"e_1_3_2_1_76_1","volume-title":"2023 a. SAN: Side Adapter Network for Open-vocabulary Semantic Segmentation","author":"Xu Mengde","year":"2023","unstructured":"Mengde Xu, Zheng Zhang, Fangyun Wei, Han Hu, and Xiang Bai. 2023 a. SAN: Side Adapter Network for Open-vocabulary Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"e_1_3_2_1_78_1","volume-title":"Tackling Vision Language Tasks Through Learning Inner Monologues. arXiv preprint arXiv:2308.09970","author":"Yang Diji","year":"2023","unstructured":"Diji Yang, Kezhen Chen, Jinmeng Rao, Xiaoyuan Guo, Yawen Zhang, Jie Yang, and Yi Zhang. 2023. Tackling Vision Language Tasks Through Learning Inner Monologues. arXiv preprint arXiv:2308.09970 (2023)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346996"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01926"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_82_1","volume-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199","author":"Zaken Elad Ben","year":"2021","unstructured":"Elad Ben Zaken, Shauli Ravfogel, and Yoav Goldberg. 2021. Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)."},{"key":"e_1_3_2_1_83_1","volume-title":"NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation. arXiv preprint arXiv:2309.07705","author":"Zhang Jiaqi","year":"2023","unstructured":"Jiaqi Zhang, Yu Cheng, Yongxin Ni, Yunzhu Pan, Zheng Yuan, Junchen Fu, Youhua Li, Jie Wang, and Fajie Yuan. 2023. NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation. arXiv preprint arXiv:2309.07705 (2023)."},{"key":"e_1_3_2_1_84_1","volume-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930","author":"Zhang Renrui","year":"2021","unstructured":"Renrui Zhang, Rongyao Fang, Wei Zhang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, and Hongsheng Li. 2021. Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930 (2021)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657725","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:43:49Z","timestamp":1755841429000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":85,"alternative-id":["10.1145\/3626772.3657725","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657725","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}