Multimodal Foundation Models (MMFMs) have demonstrated strong performance in both computer vision and natural language processing tasks. However, their performance diminishes in tasks that require a high degree of integration between these modalities, such as document understanding. Moreover, finetuning these models and deploying them requires significantly more compute and more engineering effort than unimodal models. In this work, we present Multimodal Structured Generation, a framework that forces (frozen) MMFMs to produce outputs in a strictly structured format by applying hard constraints directly to the output logits. This approach not only ensures that the model generates parseable outputs that downstream APIs can easily ingest but also allows us to force the model to reason before answering, which significantly boosts performance without the need for expensive fine-tuning. We demonstrate the effectiveness of our method through competitive results in the CVPR 2nd MMFM Challenge, highlighting that carefully designed lightweight engineering can outperform expensive and complicated modeling approaches. All of our scripts, deployment steps, and evaluation results can be accessed in https://github.com/leloykun/MMFM-Challenge
Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Ruoyu Technology(若愚科技)
Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challenge
Shanghai Jiao Tong University(上海交通大学);JITRI(江苏集萃智能制造技术研究所有限公司);Dalian University of Technology(大连理工大学);University of Electronic Science and Technology of China(电子科技大学);The University of Tokyo(东京大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Beihang University(北京航空航天大学);University of Chinese Academy of Sciences(中国科学院大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Tongji University(同济大学);iFLYTEK Co., Ltd.(科大讯飞股份有限公司);Anhui Laboratory for Safe Artificial Intelligence in the Yangtze River Delta(长三角安全人工智能安徽实验室);Wenzhou Business College(温州商学院);Jiangnan University(江南大学);Guangzhou City University of Technology(广州理工学院);Inceptio Technology(智元机器);Institute of Dataspace(数据空间研究所);Zhongguancun Laboratory(中关村实验室);Tsinghua University(清华大学);ETH Zürich(苏黎世联邦理工学院);University of Oxford(牛津大学);Shanghai AI Laboratory(上海人工智能实验室);BAAI(北京智源人工智能研究院);Meta;Johns Hopkins University(约翰·霍普金斯大学);University of California, Berkeley(加州大学伯克利分校);Nanyang Technological University(南洋理工大学)
Technical Report for Argoverse Challenges on Unified Sensor-based Detection, Tracking, and Forecasting
Lenovo Research(联想研究院);Liaoning Petrochemical University(辽宁石油化工大学);University of Science and Technology Beijing(北京科技大学);University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学)
SuperAD: A Training-free Anomaly Classification and Segmentation Method for CVPR 2025 VAND 3.0 Workshop Challenge Track 1: Adapt & Detect
School of Computer Science and Engineering, Southeast University, China(东南大学计算机科学与工程学院);School of Computer Science and Engineering, Nanjing University of Science and Technology, China(南京理工大学计算机科学与工程学院)
针对MVTec AD 2真实工业异常检测挑战,提出基于DINOv2特征提取与记忆库最近邻匹配的完全无需训练方法SuperAD,在测试集上取得有竞争力结果。
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023
Southwest University(西南大学);Samsung Research China-Beijing(SRC-B)(三星中国研究院-北京);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview
LOOKOUT;Helmut Schmidt University(海姆·施密特大学);catskill GmbH(catskill公司);University of Ljubljana(卢布尔雅那大学);Virginia Tech(弗吉尼亚理工大学);Shield AI;Queensland University of Technology(昆士兰理工大学);Dartmouth College(达特茅斯学院);LinkedIn;University of Tuebingen(图宾根大学);Konya Technical University(科尼亚技术大学);Schneider Electric Taiwan Co., Ltd.(施耐德电气台湾有限公司);University of Taipei(台北大学);National Yang Ming Chiao Tung University(阳明交通大学);University at Albany, SUNY(阿尔巴尼大学,SUNY);Inventec Corporation(Inventec公司);HD Korea Shipbuilding & Offshore Engineering Co., Ltd.(韩国海事造船与海洋工程公司);Seoul National University(首尔国立大学);Xidian University(西安电子科技大学);Indian Institute of Technology, Tirupati(印度泰浦蒂理工学院);Centre for Artificial Intelligence and Robotics (CAIR), Bangalore, India(人工智能与机器人中心(CAIR),印度班加罗尔);Gwangju Institute of Science and Technology(全州科学技术院);Fraunhofer IOSB(弗劳恩霍夫 IOSB研究所);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Kansas State University(堪萨斯州立大学);Colorado School of Mines(科罗拉多矿业学院);Arquimea Research Center(Arquimea研究中心);Independent Researcher(独立研究员)