{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:09:08Z","timestamp":1788995348181,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375766","type":"print"},{"value":"9783032375773","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37577-3_1","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:01:25Z","timestamp":1788994885000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TSEmbed: Unlocking Task Scaling in\u00a0Universal Multimodal Embeddings"],"prefix":"10.1007","author":[{"given":"Yebo","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changwang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Cao, M., Li, S., Li, J., Nie, L., Zhang, M.: Image-text retrieval: a survey on recent research and development. arXiv preprint arXiv:2203.14713 (2022)","DOI":"10.24963\/ijcai.2022\/759"},{"issue":"12","key":"1_CR2","first-page":"1","volume":"56","author":"S Chen","year":"2024","unstructured":"Chen, S., Zhang, Y., Yang, Q.: Multi-task learning in natural language processing: an overview. ACM Comput. Surv. 56(12), 1\u201332 (2024)","journal-title":"ACM Comput. Surv."},{"key":"1_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PmLR (2020)"},{"key":"1_CR4","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.Y., Rabinovich, A.: Gradnorm: gradient normalization for adaptive loss balancing in deep multitask networks. In: International Conference on Machine Learning, pp. 794\u2013803. PMLR (2018)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"1_CR6","unstructured":"Cui, X., et al.: Think then embed: generative context improves multimodal embedding. arXiv preprint arXiv:2510.05014 (2025)"},{"key":"1_CR7","unstructured":"Faysse, M., et al.: Colpali: efficient document retrieval with vision language models. In: International Conference on Learning Representations, vol. 2025, pp. 61424\u201361449 (2025)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Gao, L., Zhang, Y., Han, J., Callan, J.: Scaling deep contrastive learning batch size under memory limited setup. In: Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pp. 316\u2013321 (2021)","DOI":"10.18653\/v1\/2021.repl4nlp-1.31"},{"issue":"1","key":"1_CR9","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1038\/s43586-022-00184-w","volume":"2","author":"M Greenacre","year":"2022","unstructured":"Greenacre, M., Groenen, P.J., Hastie, T., d\u2019Enza, A.I., Markos, A., Tuzhilina, E.: Principal component analysis. Nat. Rev. Methods Primers 2(1), 100 (2022)","journal-title":"Nat. Rev. Methods Primers"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Gu, T., et al.: Unime-v2: Mllm-as-a-judge for universal multimodal embedding learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a040, pp. 21378\u201321386 (2026)","DOI":"10.1609\/aaai.v40i26.39284"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1_CR12","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: ICLR, vol. 1, no. 2, p. 3 (2022)"},{"key":"1_CR13","unstructured":"Jian, W., et al.: Rzenembed: towards comprehensive multimodal retrieval. arXiv preprint arXiv:2510.27350 (2025)"},{"key":"1_CR14","unstructured":"Jiang, H., et al.: Embed-rl: reinforcement learning for reasoning-driven multimodal embeddings. arXiv preprint arXiv:2602.13823 (2026)"},{"key":"1_CR15","unstructured":"Jiang, T., et al.: E5-v: universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580 (2024)"},{"key":"1_CR16","unstructured":"Jiang, Z., Meng, R., Yang, X., Yavuz, S., Zhou, Y., Chen, W.: Vlm2vec: training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160 (2024)"},{"key":"1_CR17","first-page":"21798","volume":"33","author":"Y Kalantidis","year":"2020","unstructured":"Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 21798\u201321809 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR18","unstructured":"Kong, F., et\u00a0al.: Modality curation: building universal embeddings for advanced multimodal information retrieval. arXiv preprint arXiv:2505.19650 (2025)"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Lan, Z., Niu, L., Meng, F., Zhou, J., Su, J.: Llave: large language and vision embedding models with hardness-weighted contrastive learning. arXiv preprint arXiv:2503.04812 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.740"},{"key":"1_CR20","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"1_CR21","unstructured":"Li, M., et\u00a0al.: Qwen3-vl-embedding and qwen3-vl-reranker: a unified framework for state-of-the-art multimodal retrieval and ranking. arXiv preprint arXiv:2601.04720 (2026)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Q., et al.: Multimodal pretraining, adaptation, and generation for recommendation: a survey. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 6566\u20136576 (2024)","DOI":"10.1145\/3637528.3671473"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Lamra: large multimodal model as your advanced retrieval assistant. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4015\u20134025 (2025)","DOI":"10.1109\/CVPR52734.2025.00380"},{"key":"1_CR24","unstructured":"Meng, R., et al.: Vlm2vec-v2: advancing multimodal embedding for videos, images, and visual documents. arXiv preprint arXiv:2507.04590 (2025)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3994\u20134003 (2016)","DOI":"10.1109\/CVPR.2016.433"},{"key":"1_CR26","unstructured":"Navon, A., et al.: Multi-task learning as a bargaining game. arXiv preprint arXiv:2202.01017 (2022)"},{"key":"1_CR27","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"1_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"1_CR29","unstructured":"Robinson, J., Chuang, C.Y., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. arXiv preprint arXiv:2010.04592 (2020)"},{"issue":"1","key":"1_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3767328","volume":"44","author":"X Song","year":"2025","unstructured":"Song, X., Lin, H., Wen, H., Hou, B., Xu, M., Nie, L.: A comprehensive survey on composed image retrieval. ACM Trans. Inf. Syst. 44(1), 1\u201354 (2025)","journal-title":"ACM Trans. Inf. Syst."},{"key":"1_CR31","first-page":"8728","volume":"33","author":"X Sun","year":"2020","unstructured":"Sun, X., Panda, R., Feris, R., Saenko, K.: Adashare: learning what to share for efficient deep multi-task learning. Adv. Neural. Inf. Process. Syst. 33, 8728\u20138740 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR32","first-page":"23218","volume":"38","author":"R Thirukovalluru","year":"2026","unstructured":"Thirukovalluru, R., et al.: Breaking the batch barrier (b3) of contrastive learning via smart batch mining. Adv. Neural. Inf. Process. Syst. 38, 23218\u201323241 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR33","unstructured":"Tschannen, M., et al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"1_CR34","unstructured":"Wang, P., et\u00a0al.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"1_CR35","doi-asserted-by":"publisher","unstructured":"Wei, C., et al.: Uniir: training and benchmarking universal multimodal information retrievers. In: European Conference on Computer Vision, pp. 387\u2013404. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73021-4_23","DOI":"10.1007\/978-3-031-73021-4_23"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Wu, Y., Jin, H., Guo, Z., Li, L.: Spotlight and shadow: attention-guided dual-anchor introspective decoding for mllm hallucination mitigation. arXiv preprint arXiv:2604.10071 (2026)","DOI":"10.18653\/v1\/2026.findings-acl.646"},{"key":"1_CR37","unstructured":"Wu, Y., Li, J., Guo, Z., Li, L.: Elastic mixture of rank-wise experts for knowledge reuse in federated fine-tuning. arXiv preprint arXiv:2512.00902 (2025)"},{"key":"1_CR38","unstructured":"Wu, Y., Li, J., Guo, Z., Li, L.: Developmental federated tuning: a cognitive-inspired paradigm for efficient llm adaptation. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"1_CR39","unstructured":"Wu, Y., Li, J., Tian, C., Guo, Z., Li, L.: Memory-efficient federated fine-tuning of large language models via layer pruning. arXiv preprint arXiv:2508.17209 (2025)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Y., Li, J., Tian, C., Tam, K., Guo, Z., Li, L.: Beyond end-to-end: dynamic chain optimization for private llm adaptation on the edge. arXiv preprint arXiv:2604.06819 (2026)","DOI":"10.18653\/v1\/2026.acl-long.839"},{"key":"1_CR41","unstructured":"Xu, N., et\u00a0al.: Copyrightmeter: revisiting copyright protection in text-to-image models. arXiv preprint arXiv:2411.13144 (2024)"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Xu, N., et al.: Bridging the copyright gap: do large vision-language models recognize and respect copyrighted content? In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a040, pp. 35949\u201335957 (2026)","DOI":"10.1609\/aaai.v40i42.40910"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Xu, N., et al.: Videoeraser: concept erasure in text-to-video diffusion models. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 5965\u20135994 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.304"},{"key":"1_CR44","unstructured":"Xue, Y., Li, D., Liu, G.: Improve multi-modal embedding learning via explicit hard negative gradient amplifying. arXiv preprint arXiv:2506.02020 (2025)"},{"key":"1_CR45","unstructured":"Yang, Z., Li, L., Lin, K., Wang, J., Lin, C.C., Liu, Z., Wang, L.: The dawn of lmms: preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421 (2023)"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Ye, Y., et al.: Harnessing multimodal large language models for multimodal sequential recommendation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 13069\u201313077 (2025)","DOI":"10.1609\/aaai.v39i12.33426"},{"key":"1_CR47","doi-asserted-by":"publisher","unstructured":"Yu, H., Gan, A., Zhang, K., Tong, S., Liu, Q., Liu, Z.: Evaluation of retrieval-augmented generation: a survey. In: CCF Conference on Big Data, pp. 102\u2013120. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-981-96-1024-2_8","DOI":"10.1007\/978-981-96-1024-2_8"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Yu, H., et al.: Cafe: unifying representation and generation with contrastive-autoregressive finetuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6286\u20136297 (2025)","DOI":"10.1109\/ICCVW69036.2025.00659"},{"key":"1_CR49","first-page":"5824","volume":"33","author":"T Yu","year":"2020","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. Adv. Neural. Inf. Process. Syst. 33, 5824\u20135836 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Notellm-2: multimodal large representation models for recommendation. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, vol. 1, pp. 2815\u20132826 (2025)","DOI":"10.1145\/3690624.3709440"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Dual temperature helps contrastive learning without many negative samples: towards understanding and simplifying moco. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14441\u201314450 (2022)","DOI":"10.1109\/CVPR52688.2022.01404"},{"key":"1_CR52","unstructured":"Zhang, K., et al.: Magiclens: self-supervised image retrieval with open-ended instructions. arXiv preprint arXiv:2403.19651 (2024)"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Bridging modalities: improving universal multimodal retrieval by multimodal large language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9274\u20139285 (2025)","DOI":"10.1109\/CVPR52734.2025.00866"},{"issue":"12","key":"1_CR54","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","volume":"34","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. IEEE Trans. Knowl. Data Eng. 34(12), 5586\u20135609 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, P., et al.: Retrieval-augmented generation for ai-generated content: a survey. Data Sci. Eng. 1\u201329 (2026)","DOI":"10.1007\/s41019-025-00335-5"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37577-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:01:36Z","timestamp":1788994896000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37577-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375766","9783032375773"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37577-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}