{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T01:04:01Z","timestamp":1774400641214,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730135","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:25:28Z","timestamp":1752456328000},"page":"4061-4065","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3430-4910","authenticated-orcid":false,"given":"Xueguang","family":"Ma","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5806-3022","authenticated-orcid":false,"given":"Luyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-0955","authenticated-orcid":false,"given":"Shengyao","family":"Zhuang","sequence":"additional","affiliation":[{"name":"CSIRO, Queensland, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0952-7284","authenticated-orcid":false,"given":"Jiaqi Samantha","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1211-7754","authenticated-orcid":false,"given":"Jamie","family":"Callan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7189","authenticated-orcid":false,"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"2318","volume-title":"Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. In Findings of the Association for Computational Linguistics: ACL","author":"Chen Jianlyu","year":"2024","unstructured":"Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. In Findings of the Association for Computational Linguistics: ACL 2024, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, Bangkok, Thailand, 2318-2335."},{"key":"e_1_3_2_1_2_1","unstructured":"Tri Dao Daniel Y Fu Stefano Ermon Atri Rudra and Christopher Re. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. In Advances in Neural Information Processing Systems Alice H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Matt Deitke Christopher Clark Sangho Lee Rohun Tripathi Yue Yang Jae Sung Park Mohammadreza Salehi Niklas Muennighoff Kyle Lo Luca Soldaini Jiasen Lu Taira Anderson Erin Bransom Kiana Ehsani Huong Ngo YenSung Chen Ajay Patel Mark Yatskar Chris Callison-Burch Andrew Head Rose Hendrix Favyen Bastani Eli VanderBilt Nathan Lambert Yvonne Chou Arnavi Chheda Jenna Sparks Sam Skjonsberg Michael Schmitz Aaron Sarnat Byron Bischoff Pete Walsh Chris Newell Piper Wolters Tanmay Gupta Kuo-Hao Zeng Jon Borchardt Dirk Groeneveld Crystal Nam Sophie Lebrecht Caitlin Wittlif Carissa Schoenick Oscar Michel Ranjay Krishna Luca Weihs Noah A. Smith Hannaneh Hajishirzi Ross Girshick Ali Farhadi and Aniruddha Kembhavi. 2024. Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models. arXiv:2409.17146 (2024).","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"e_1_3_2_1_4_1","volume-title":"ColPali: Efficient Document Retrieval with Vision Language Models. arXiv:2407.01449","author":"Faysse Manuel","year":"2024","unstructured":"Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, C\u00e9line Hudelot, and Pierre Colombo. 2024. ColPali: Efficient Document Retrieval with Vision Language Models. arXiv:2407.01449 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591805"},{"key":"e_1_3_2_1_6_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Karpukhin Vladimir","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Bonnie Webber, Trevor Cohn, Yulan He, and Yang Liu (Eds.). Association for Computational Linguistics, Online, 6769-6781."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"e_1_3_2_1_10_1","unstructured":"Aditya Kusupati Gantavya Bhatt Aniket Rege Matthew Wallingford Aditya Sinha Vivek Ramanujan William Howard-Snyder Kaifeng Chen Sham Kakade Prateek Jain et al. 2022. Matryoshka Representation Learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_13_1","volume-title":"Universal Multimodal Retrieval with Multimodal LLMs. In The Thirteenth International Conference on Learning Representations.","author":"Lin Sheng-Chieh","year":"2025","unstructured":"Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi, Jimmy Lin, Bryan Catanzaro, and Wei Ping. 2025. Universal Multimodal Retrieval with Multimodal LLMs. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.373"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730331"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_1_22_1","unstructured":"Qwen Team. 2025. Qwen2.5-VL."},{"key":"e_1_3_2_1_23_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_24_1","volume-title":"Improving Text Embeddings with Large Language Models. arXiv:2401.00368","author":"Wang Liang","year":"2024","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024. Improving Text Embeddings with Large Language Models. arXiv:2401.00368 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"arXiv:2503.20215","author":"Xu Jin","year":"2025","unstructured":"Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, Bin Zhang, Xiong Wang, Yunfei Chu, and Junyang Lin. 2025. Qwen2.5-Omni Technical Report. arXiv:2503.20215 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5288-5296","author":"Xu Jun","year":"2016","unstructured":"Jun Xu, Tao Mei, Ting Yao, and Yong Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5288-5296."},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Information Retrieval","author":"Zhang Crystina","unstructured":"Crystina Zhang, Sebastian Hofst\u00e4tter, Patrick Lewis, Raphael Tang, and Jimmy Lin. 2025 a. Rank-Without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models. In Advances in Information Retrieval, Claudia Hauff, Craig Macdonald, Dietmar Jannach, Gabriella Kazai, Franco Maria Nardini, Fabio Pinelli, Fabrizio Silvestri, and Nicola Tonellotto (Eds.). Springer Nature Switzerland, Cham, 233-247."},{"key":"e_1_3_2_1_28_1","volume-title":"2025 b. Jasper and Stella: distillation of SOTA embedding models. arXiv:2412.19048","author":"Zhang Dun","year":"2025","unstructured":"Dun Zhang, Jiacheng Li, Ziyang Zeng, and Fulong Wang. 2025 b. Jasper and Stella: distillation of SOTA embedding models. arXiv:2412.19048 (2025)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00595"},{"key":"e_1_3_2_1_30_1","volume-title":"2025 c. GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv:2412.16855","author":"Zhang Xin","year":"2025","unstructured":"Xin Zhang, Yanzhao Zhang, Wen Xie, Mingxin Li, Ziqi Dai, Dingkun Long, Pengjun Xie, Meishan Zhang, Wenjie Li, and Min Zhang. 2025 c. GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv:2412.16855 (2025)."}],"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\/3726302.3730135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:17:13Z","timestamp":1755865033000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":30,"alternative-id":["10.1145\/3726302.3730135","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730135","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"}}]}}