In this report, we introduce the Qwen3-VL-Embedding and Qwen3-VL-Reranker model series, the latest extensions of the Qwen family built on the Qwen3-VL foundation model. Together, they provide an end-to-end pipeline for high-precision multimodal search by mapping diverse modalities, including text, images, document images, and video, into a unified representation space. The Qwen3-VL-Embedding model employs a multi-stage training paradigm, progressing from large-scale contrastive pre-training to reranking model distillation, to generate semantically rich high-dimensional vectors. It supports Matryoshka Representation Learning, enabling flexible embedding dimensions, and handles inputs up to 32k tokens. Complementing this, Qwen3-VL-Reranker performs fine-grained relevance estimation for query-document pairs using a cross-encoder architecture with cross-attention mechanisms. Both model series inherit the multilingual capabilities of Qwen3-VL, supporting more than 30 languages, and are released in $\textbf{2B}$ and $\textbf{8B}$ parameter sizes to accommodate diverse deployment requirements. Empirical evaluations demonstrate that the Qwen3-VL-Embedding series achieves state-of-the-art results across diverse multimodal embedding evaluation benchmarks. Specifically, Qwen3-VL-Embedding-8B attains an overall score of $\textbf{77.8}$ on MMEB-V2, ranking first among all models (as of January 8, 2025). This report presents the architecture, training methodology, and practical capabilities of the series, demonstrating their effectiveness on various multimodal retrieval tasks, including image-text retrieval, visual question answering, and video-text matching.
RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection
Shenzhen University of Advanced Technology(深圳理工大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Xiamen University(厦门大学)
Can LLM Rerankers Predict Their Own Ranking Performance?
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学)
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院 Gallagher 分校);Baidu Inc., Beijing, China(百度公司,北京,中国);Carnegie Mellon University(卡内基梅隆大学)
Query-focused and Memory-aware Reranker for Long Context Processing
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Pattern Recognition Center, WeChat AI, Tencent(腾讯微信人工智能研究院模式识别中心);East China Normal University(华东师范大学)
Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers
Georgetown University(乔治城大学);University of Southern California(南加州大学);University of Maryland, College Park(马里兰大学学院公园分校);Arizona State University(亚利桑那州立大学)
Multimodal Language Models as Text-to-Image Model Evaluators
FAIR at Meta - Montreal, New York(Meta 蒙特利尔 FAIR);University of Texas at Austin(德克萨斯大学奥斯汀分校);Mila;McGill University(麦吉尔大学);Canada CIFAR AI chair(加拿大 CIFAR 人工智能主席)
Distillation versus Contrastive Learning: How to Train Your Rerankers
Kahlert School of Computing, University of Utah(犹他大学计算机学院);Scientific Computing and Imaging Institute, University of Utah(犹他大学科学计算与成像研究所);Capital One, Inc(Capital One公司);The University of Queensland(昆士兰大学)
Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations
V. A. Trapeznikov ICS RAS Russian Biotechnological University (ROSBIOTECH)(Trapeznikov ICS 俄罗斯科学院俄罗斯生物技术大学);Russian Biotechnological University (ROSBIOTECH)(俄罗斯生物技术大学)
LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems
organization= School of Computer Science;Technology, Dalian University of Technology , addressline= No.2 Linggong Road, Ganjingzi District , city= Dalian , postcode= 116024 , country= China;organization= School of Information Engineering, Liaodong University , addressline= No.116 Linjiang Back Street, Zhenan District , city= Dandong , postcode= 118001 , country= China;organization= School of Information Engineering, Dalian Ocean University , addressline= No. 2-52, Heishijiao Street, Shahekou District , city= Dalian , postcode= 116023 , country= China;organization= Information Technology Center, Qinghai University , addressline= 251 Ningda Road, Chengbei District , city= Xining , postcode= 810016 , country= China;organization= School of Electronic;Information Engineering, Liaoning Technical University , addressline= 188 Longwan South Street, Sijiatun District , city= Huludao , postcode= 125105 , country= China;organization= School of Artificial Intelligence, Tianjin Normal University , addressline= 393 Binshui West Road, Xiqing District , city= Tianjin , postcode= 300387 , country= China;organization= Tencent (Dalian Northern Interactive Entertainment Technology Co., Ltd.) , addressline= 21/F, Tencent Building, No. 26 Jingxian St, Ganjingzi District , city= Dalian , postcode= 116085 , country= China
SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training
College of Computer Science and Technology(计算机科学与技术学院);The State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);Zhejiang University(浙江大学);Hangzhou City University(杭州市城市大学);Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(浙江大学和杭州高新区(滨江)区块链与数据安全研究院)
mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset
Univ. of Campinas(坎皮纳斯大学);NeuralMind(NeuralMind公司);Zeta Alpha(Zeta Alpha公司);Univ. of Waterloo(滑铁卢大学)
MS MARCO排名数据集已被广泛用于训练IR任务的深度学习模型,在各种zero-shot场景中取得了相当大的效果。然而,这种类型的资源在英语以外的语言中是稀缺的。在这项工作中,我们提出了mMARCO,MS MARCO通道排名数据集的多语言版本,包括13种语言,使用机器翻译创建。我们通过微调单语和多语言重新排序模型以及该数据集上的多语言稠密检索模型来评估mMARCO。我们还在Mr. TyDi数据集上的zero-shot场景中评估了使用mMARCO数据集进行微调的模型,证明了在我们翻译的数据集上进行微调的多语言模型比仅在原始英文版本上进行微调的模型具有更好的有效性。我们的实验还表明,一个蒸馏的多语言reranker是有竞争力的非蒸馏模型,同时具有5.4倍少的参数。最后,我们显示了翻译质量和检索效果之间的正相关性,提供证据表明,翻译方法的改进可能会导致多语言信息检索的改进。翻译的数据集和微调的模型可在https://github.com/unicamp-dl/mMARCO上获得。
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
University of Science and Technology of China(中国科学技术大学);Yuanbao Team, Tencent(腾讯元宝团队);University of Chinese Academy of Sciences(中国科学院大学);Shandong University(山东大学)
GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases
Department of Electrical Engineering and Computer Science, University of Michigan(密歇根大学电气工程与计算机科学系);Department of Computational Medicine and Bioinformatics, University of Michigan(密歇根大学计算医学与生物信息学系)
LegalMALR:Multi-Agent Query Understanding and LLM-Based Reranking for Chinese Statute Retrieval
Faculty of Data Science(数据科学学院);City University of Macau(澳门城市大学);Shenzhen Key Laboratory for High Performance Data Mining(深圳高性能数据挖掘重点实验室);Shenzhen Institutes of Advanced Technology(深圳先进技术研究所);Chinese Academy of Sciences(中国科学院);Southern University of Science and Technology(南方科技大学);Artificial Intelligence Research Institute(人工智能研究院);Shenzhen University of Advanced Technology(深圳大学先进技术学院)
Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis
Harvard University(哈佛大学);University of California, Santa Cruz(加州大学圣克鲁兹分校);Brown University(布朗大学);Johns Hopkins University(约翰斯·霍普金斯大学);Georgia Institute of Technology(佐治亚理工学院)
Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Alibaba Cloud Computing(阿里云计算);Hong Kong University of Science and Technology(香港科技大学);University of Illinois Chicago(伊利诺伊大学芝加哥分校)
Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansion
Shenzhen International Graduate School Tsinghua University(清华大学深圳国际研究生院);Peng Cheng Laboratory(鹏城实验室);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳));Seoul National University(首尔大学)