{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:20:13Z","timestamp":1783153213331,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"name":"Beijing Natural Science Foundation","award":["No. 4254079"],"award-info":[{"award-number":["No. 4254079"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792528","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"4127-4136","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6801-4471","authenticated-orcid":false,"given":"Jinjin","family":"Guo","sequence":"first","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5907-8978","authenticated-orcid":false,"given":"Yexin","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7662-5184","authenticated-orcid":false,"given":"Zhichao","family":"Huang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9389-6618","authenticated-orcid":false,"given":"Jun","family":"Fang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8508-444X","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9104-1587","authenticated-orcid":false,"given":"Chao","family":"Liu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6031-5245","authenticated-orcid":false,"given":"Pengzhang","family":"Liu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1465-041X","authenticated-orcid":false,"given":"Qixia","family":"Jiang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al.","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al., 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"VICReg: Variance-Invariance-Covariance Regularization For Self-Supervised Learning. In ICLR 2022-ICLR.","author":"Bardes Adrien","year":"2022","unstructured":"Adrien Bardes, Jean Ponce, and Yann Lecun. 2022. VICReg: Variance-Invariance-Covariance Regularization For Self-Supervised Learning. In ICLR 2022-ICLR."},{"key":"e_1_3_2_1_3_1","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron Mathilde","year":"2020","unstructured":"Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2020. Unsupervised learning of visual features by contrasting cluster assignments. NeurIPS, Vol. 33 (2020), 9912-9924.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_4_1","volume-title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data. arXiv preprint arXiv:2502.08468","author":"Chen Haonan","year":"2025","unstructured":"Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, and Zhicheng Dou. 2025. mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data. arXiv preprint arXiv:2502.08468 (2025)."},{"key":"e_1_3_2_1_5_1","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML. PmLR, 1597-1607.","journal-title":"ICML. PmLR"},{"key":"e_1_3_2_1_6_1","first-page":"15750","article-title":"Exploring simple siamese representation learning","author":"Chen Xinlei","year":"2021","unstructured":"Xinlei Chen and Kaiming He. 2021. Exploring simple siamese representation learning. In CVPR. 15750-15758.","journal-title":"CVPR."},{"key":"e_1_3_2_1_7_1","first-page":"8765","article-title":"Debiased contrastive learning","volume":"33","author":"Chuang Ching-Yao","year":"2020","unstructured":"Ching-Yao Chuang, Joshua Robinson, Yen-Chen Lin, Antonio Torralba, and Stefanie Jegelka. 2020. Debiased contrastive learning. NeurIPS, Vol. 33 (2020), 8765-8775.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.31"},{"key":"e_1_3_2_1_9_1","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021a. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In EMNLP."},{"key":"e_1_3_2_1_10_1","volume-title":"Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9mi Munos, and Michal Valko.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R\u00e9mi Munos, and Michal Valko. 2020. Bootstrap your own latent a new approach to self-supervised learning. In NeurIPS."},{"key":"e_1_3_2_1_11_1","volume-title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs. arXiv preprint arXiv:2504.17432","author":"Gu Tiancheng","year":"2025","unstructured":"Tiancheng Gu, Kaicheng Yang, Ziyong Feng, Xingjun Wang, Yanzhao Zhang, Dingkun Long, Yingda Chen, Weidong Cai, and Jiankang Deng. 2025. Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs. arXiv preprint arXiv:2504.17432 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"AAAI. JMLR Workshop and Conference Proceedings, 297-304","author":"Gutmann Michael","year":"2010","unstructured":"Michael Gutmann and Aapo Hyv\u00e4rinen. 2010. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In AAAI. JMLR Workshop and Conference Proceedings, 297-304."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_2_1_14_1","volume-title":"Fernando Fernandes Neto, and David Golchinfar","author":"Hartford Eric","year":"2024","unstructured":"Eric Hartford, Lucas Atkins, Fernando Fernandes Neto, and David Golchinfar. 2024. Spectrum: Targeted Training on Signal to Noise Ratio. arXiv preprint arXiv:2406.06623 (2024)."},{"key":"e_1_3_2_1_15_1","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In CVPR. 9729-9738.","journal-title":"CVPR."},{"key":"e_1_3_2_1_16_1","first-page":"17081","article-title":"Contrastive learning with adversarial examples","volume":"33","author":"Ho Chih-Hui","year":"2020","unstructured":"Chih-Hui Ho and Nuno Nvasconcelos. 2020. Contrastive learning with adversarial examples. NeurIPS, Vol. 33 (2020), 17081-17093.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_17_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_18_1","volume-title":"Neftune: Noisy Embeddings Improve Instruction Finetuning. arXiv, abs\/2310.05914.","author":"Jain N","year":"2023","unstructured":"N Jain, P-y Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, BR Bartoldson, B Kailkhura, A Schwarzschild, and A Saha. 2023. Neftune: Noisy Embeddings Improve Instruction Finetuning. arXiv, abs\/2310.05914."},{"key":"e_1_3_2_1_19_1","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021a. Scaling up visual and vision-language representation learning with noisy text supervision. In ICML. PMLR, 4904-4916.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_20_1","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021b. Scaling up visual and vision-language representation learning with noisy text supervision. In ICML. PMLR, 4904-4916.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_21_1","volume-title":"E5-v: Universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580","author":"Jiang Ting","year":"2024","unstructured":"Ting Jiang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, and Fuzhen Zhuang. 2024b. E5-v: Universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160","author":"Jiang Ziyan","year":"2024","unstructured":"Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, and Wenhu Chen. 2024a. Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"No'e Pion, Philippe Weinzaepfel, and Diane Larlus.","author":"Kalantidis Yannis","year":"2020","unstructured":"Yannis Kalantidis, Mert Bulent Sariyildiz, No'e Pion, Philippe Weinzaepfel, and Diane Larlus. 2020. Hard Negative Mixing for Contrastive Learning. ArXiv (2020)."},{"key":"e_1_3_2_1_24_1","volume-title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning. arXiv preprint arXiv:2503.04812","author":"Lan Zhibin","year":"2025","unstructured":"Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou, and Jinsong Su. 2025. LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning. arXiv preprint arXiv:2503.04812 (2025)."},{"key":"e_1_3_2_1_25_1","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023a. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In ICML. PMLR, 19730-19742.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_26_1","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML. PMLR, 12888-12900.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_27_1","volume-title":"Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023b. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)."},{"key":"e_1_3_2_1_28_1","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang Victor Weixin","year":"2022","unstructured":"Victor Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, and James Y Zou. 2022. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. NeurIPS, Vol. 35 (2022), 17612-17625.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_29_1","volume-title":"Llavanext: Improved reasoning, ocr, and world knowledge.","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024. Llavanext: Improved reasoning, ocr, and world knowledge."},{"key":"e_1_3_2_1_30_1","volume-title":"Universal vision-language dense retrieval: Learning a unified representation space for multi-modal retrieval. arXiv preprint arXiv:2209.00179","author":"Liu Zhenghao","year":"2022","unstructured":"Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, and Ge Yu. 2022. Universal vision-language dense retrieval: Learning a unified representation space for multi-modal retrieval. arXiv preprint arXiv:2209.00179 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1070\/SM1967v001n04ABEH001994"},{"key":"e_1_3_2_1_32_1","volume-title":"Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning. arXiv preprint arXiv:2504.07097","author":"Nayak Nikhil Shivakumar","year":"2025","unstructured":"Nikhil Shivakumar Nayak, Krishnateja Killamsetty, Ligong Han, Abhishek Bhandwaldar, Prateek Chanda, Kai Xu, Hao Wang, Aldo Pareja, Oleg Silkin, Mustafa Eyceoz, et al., 2025. Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning. arXiv preprint arXiv:2504.07097 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018a. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018b. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_35_1","first-page":"1150","article-title":"Gcc: Graph contrastive coding for graph neural network pre-training","author":"Qiu Jiezhong","year":"2020","unstructured":"Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, and Jie Tang. 2020. Gcc: Graph contrastive coding for graph neural network pre-training. In SIGKDD. 1150-1160.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_36_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","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 ICML. PMLR, 8748-8763.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_37_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_38_1","volume-title":"VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation. arXiv preprint arXiv:2412.00927","author":"Ren Weiming","year":"2024","unstructured":"Weiming Ren, Huan Yang, Jie Min, Cong Wei, and Wenhu Chen. 2024. VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation. arXiv preprint arXiv:2412.00927 (2024)."},{"key":"e_1_3_2_1_39_1","unstructured":"Joshua Robinson Ching-Yao Chuang Suvrit Sra and Stefanie Jegelka. 2021. CONTRASTIVE LEARNING WITH HARD NEGATIVE SAMPLES. In ICLR."},{"key":"e_1_3_2_1_40_1","volume-title":"The truth is in there: Improving reasoning in language models with layer-selective rank reduction. arXiv preprint arXiv:2312.13558","author":"Sharma Pratyusha","year":"2023","unstructured":"Pratyusha Sharma, Jordan T Ash, and Dipendra Misra. 2023. The truth is in there: Improving reasoning in language models with layer-selective rank reduction. arXiv preprint arXiv:2312.13558 (2023)."},{"key":"e_1_3_2_1_41_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024. 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_1_42_1","volume-title":"European Conference on Computer Vision. Springer, 387-404","author":"Wei Cong","year":"2024","unstructured":"Cong Wei, Yang Chen, Haonan Chen, Hexiang Hu, Ge Zhang, Jie Fu, Alan Ritter, and Wenhu Chen. 2024. Uniir: Training and benchmarking universal multimodal information retrievers. In European Conference on Computer Vision. Springer, 387-404."},{"key":"e_1_3_2_1_43_1","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You Yuning","year":"2020","unstructured":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. NeurIPS, Vol. 33 (2020), 5812-5823.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_44_1","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar Jure","year":"2021","unstructured":"Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, and St\u00e9phane Deny. 2021. Barlow twins: Self-supervised learning via redundancy reduction. In ICML. PMLR, 12310-12320.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_45_1","first-page":"11975","article-title":"Sigmoid loss for language image pre-training","author":"Zhai Xiaohua","year":"2023","unstructured":"Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. 2023. Sigmoid loss for language image pre-training. In ICCV. 11975-11986.","journal-title":"ICCV."},{"key":"e_1_3_2_1_46_1","volume-title":"Magiclens: Self-supervised image retrieval with open-ended instructions. arXiv preprint arXiv:2403.19651","author":"Zhang Kai","year":"2024","unstructured":"Kai Zhang, Yi Luan, Hexiang Hu, Kenton Lee, Siyuan Qiao, Wenhu Chen, Yu Su, and Ming-Wei Chang. 2024a. Magiclens: Self-supervised image retrieval with open-ended instructions. arXiv preprint arXiv:2403.19651 (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv preprint arXiv:2412.16855","author":"Zhang Xin","year":"2024","unstructured":"Xin Zhang, Yanzhao Zhang, Wen Xie, Mingxin Li, Ziqi Dai, Dingkun Long, Pengjun Xie, Meishan Zhang, Wenjie Li, and Min Zhang. 2024b. GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv preprint arXiv:2412.16855 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 7th Machine Learning for Healthcare Conference. PMLR.","author":"Zhang Yuhao","unstructured":"Yuhao Zhang, Hang Jiang, Yasuhide Miura, Christopher D. Manning, and Curtis P. Langlotz. 2022. Contrastive Learning of Medical Visual Representations from Paired Images and Text. In Proceedings of the 7th Machine Learning for Healthcare Conference. PMLR."},{"key":"e_1_3_2_1_49_1","volume-title":"Defu Lian, and Yongping Xiong.","author":"Zhou Junjie","year":"2024","unstructured":"Junjie Zhou, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian, and Yongping Xiong. 2024. MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval. arXiv preprint arXiv:2412.14475 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"Deep graph contrastive representation learning. arXiv preprint arXiv:2006.04131","author":"Zhu Yanqiao","year":"2020","unstructured":"Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, and Liang Wang. 2020. Deep graph contrastive representation learning. arXiv preprint arXiv:2006.04131 (2020)."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:01:35Z","timestamp":1783152095000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":50,"alternative-id":["10.1145\/3774904.3792528","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792528","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}