Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models.

Hao Yang 0043 Amazon Web Services, AWS AI Labs Hao Yang Hao Yang 0001 Nanjing University of Aeronautics and Astronautics, College of Automation Engineering, China Université de Lille 1, France Nanjing University of Aeronautics and Astronautics, China https://orcid.org/0000-0003-1914-084X https://ieeexplore.ieee.org/author/37694106500 Hao Yang 0002 Yancheng Teachers University, School of Information Engineering, China https://orcid.org/0000-0001-6521-3080 Hao Yang 0003 Nantong University, China Jiangsu University of Science and Technology, Zhenjiang City, China University of Hanover, Geodetic Institute, Faculty of Civil Engineering and Geodetic Science, Hannover, Germany https://orcid.org/0000-0001-7883-9808 https://www.wikidata.org/entity/Q96176880 Hao Yang 0004 Nokia Research Center, White Plains, NY, USA IBM Thomas J. Watson Research Center, Hawthorne, NY, USA University of California, Los Angeles, CA, USA Hao Yang 0005 Soochow University, Robotics and Microsystems Center, College of Mechanical and Electrical Engineering, China City University of Hong Kong, Mechanical and Biomedical Engineering Department, Hong Kong https://orcid.org/0000-0002-4516-1321 https://www.wikidata.org/entity/Q93241910 Hao Yang 0006 Huawei Technologies, 2012 Labs, Beijing, China Huawei Translation Services Center, Beijing, China Beijing University of Posts and Telecommunications, State Key Laboratory of Networking and Switching Technology, Beijing, China https://scholar.google.com/citations?user=lOsjM5sAAAAJ https://orcid.org/0000-0001-8861-7010 https://www.wikidata.org/entity/Q130895194 Hao Yang 0007 Visa Research, Palo Alto, CA, USA https://usa.visa.com/about-visa/visa-research/hao-yang.html https://scholar.google.com/citations?user=BUBXsWgAAAAJ https://orcid.org/0000-0003-3020-9828 https://ieeexplore.ieee.org/author/37086368522 https://www.wikidata.org/entity/Q130891620 Hao Yang 0008 Shanghai University, Shanghai Institute for Advanced Communication and Data Science, China https://orcid.org/0009-0008-9115-4174 https://ieeexplore.ieee.org/author/37086342276 Hao Yang 0009 Beijing Academy of Agriculture and Forestry Sciences, Beijing Research Center for Information Technology in Agriculture, Key Laboratory of Quantitative Remote Sensing in Agriculture, Beijing, China https://orcid.org/0000-0001-8506-7295 https://www.scopus.com/authid/detail.uri?authorId=56957326900 Hao Yang 0010 Nuctech Company Ltd., R&D Center of Artificial Intelligent, Beijing, China Chinese Academy of Sciences, Institute of Automation, Beijing, China https://orcid.org/0000-0003-3590-4491 https://ieeexplore.ieee.org/author/37086342243 Hao Yang 0011 Worcester Polytechnic Institute, Robotics Engineering Department, Worcester, MA, USA https://orcid.org/0000-0002-1270-7850 Hao Yang 0012 Anhui University of Technology, School of Mechanical Engineering, Maanshan, China https://orcid.org/0000-0001-9806-5678 https://ieeexplore.ieee.org/author/37089391353 Hao Yang 0013 State Grid Jiangxi Electric Power Research Institute, Nanchang, Chian https://orcid.org/0000-0002-4095-6811 https://www.wikidata.org/entity/Q130972505 Hao Yang 0014 Shanghai Jiao tong University, School of Electronic Information and Electrical Engineering, Shanghai, China https://orcid.org/0000-0002-4098-5604 https://ieeexplore.ieee.org/author/37089254437 Hao Yang 0015 Southeast University, School of Computer Science and Engineering, China Key Laboratory of Computer Network and Information Integration, Nanjing, China https://orcid.org/0000-0002-3599-9876 https://ieeexplore.ieee.org/author/37089426430 Hao Yang 0016 Beihang University, School of Electronics and Information Engineering, Beijing, China https://orcid.org/0000-0003-2103-451X Hao Yang 0017 Harbin Institute of Technology, State Key Laboratory of Robotics and System, Harbin, China https://orcid.org/0000-0003-3625-1517 https://ieeexplore.ieee.org/author/37089306541 Hao (Frank) Yang Hao Yang 0018 University of Washington, Department of Civil and Environmental Engineering, Seattle, WA, USA Queen Mary University of London, School of Electronic Engineering & Computer Science, London, UK Beijing University of Posts and Telecommunications, International School, Beijing, China https://www.haofrankyang.net/ https://scholar.google.com/citations?user=IA_dRMIAAAAJ https://orcid.org/0000-0001-6431-8956 https://ieeexplore.ieee.org/author/37089329382 Hao Yang 0019 University of Science and Technology of China, School of Information Science and Technology, Hefei, China Southwest University of Science and Technology, Department of Information Engineering, Mianyang, China https://orcid.org/0000-0001-9484-7752 https://www.wikidata.org/entity/Q131129396 Hao Yang 0020 University of Electronic Science and Technology of China (UESTC), Chengdu, China https://orcid.org/0000-0002-9769-3493 Hao Yang 0021 Guangdong Polytechnic Normal University, School of Automation, Guangzhou, China South China University of Technology, School of Automation Science and Engineering, Key Laboratory of Autonomous Systems and Networked Control, Guangzhou, China https://orcid.org/0000-0003-4284-7130 https://ieeexplore.ieee.org/author/37087502156 Hao Yang 0022 Chengdu University of Information Technology, School of Computing Science, Chengdu, China https://orcid.org/0000-0002-6527-2387 https://www.wikidata.org/entity/Q89865967 Hao Yang 0023 University of Leicester, School of Engineering, Aerospace and Computational Engineering Research Group, Leicester, UK https://orcid.org/0000-0002-6895-640X https://ieeexplore.ieee.org/author/37085877971 Hao Yang 0024 Guangdong University of Technology, College of Computer, Guangzhou, China https://orcid.org/0000-0001-6491-8716 https://ieeexplore.ieee.org/author/37088571928 Hao Yang 0025 McMaster University, Department of Civil Engineering, Hamilton, Canada Toyota InfoTechnology Center, Mountain View, CA, USA Lamar University, Department of Civil and Environmental Engineering, Beaumont, TX, USA University of California, Irvine, CA, USA https://www.eng.mcmaster.ca/civil/people/faculty/hao-yang https://scholar.google.com/citations?user=ezMdZ-4AAAAJ https://orcid.org/0000-0003-0814-6058 https://ieeexplore.ieee.org/author/37086021194 Hao Yang 0026 Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen, China https://orcid.org/0000-0002-4378-5755 https://ieeexplore.ieee.org/author/37087131578 Hao Yang 0027 Nanchang University, School of Information Engineering, Nanchang, China https://orcid.org/0000-0003-2943-9650 https://ieeexplore.ieee.org/author/37088656459 Hao Yang 0028 Fuzhou University, College of Electrical Engineering and Automation, Fujian Key Laboratory of Medical Instrumentation and Pharmaceutical Technology, Fuzhou, China https://orcid.org/0000-0003-0642-8000 https://ieeexplore.ieee.org/author/37088573567 Hao Yang 0029 University of Southern California, Ming Hsieh Department of Electrical and Computer Engineering, Los Angeles, CA, USA https://orcid.org/0000-0002-0992-9161 https://www.wikidata.org/entity/Q100761230 Hao Yang 0030 Tsinghua University, Department of Electronic Engineering, Beijing, China https://orcid.org/0000-0001-7004-914X Hao Yang 0031 Army Academy of Armored Forces, Department of Arms and Control Engineering, Beijing, China https://orcid.org/0000-0001-6498-8917 https://www.wikidata.org/entity/Q93105880 Hao Yang 0032 Beihang University, School of Automation Sciences and Electrical Engineering, Beijing, China https://orcid.org/0000-0001-5263-0424 Hao Yang 0033 Amazon, Seattle, WA, USA Nanyang Technological University, School of Computer Engineering, Singapore https://sites.google.com/site/lancelot365/ https://scholar.google.com/citations?user=Y-I1X9QAAAAJ https://orcid.org/0000-0003-1061-7605 https://ieeexplore.ieee.org/author/37085715536 Hao Yang 0034 South China University of Technology, School of Mechanical and Automotive Engineering, Guangzhou, China https://orcid.org/0000-0001-6657-8188 Hao Yang 0035 Sichuan University, West China Hospital, Key Lab of Transplant Engineering and Immunology, Chengdu, China https://orcid.org/0000-0003-2214-9474 https://www.wikidata.org/entity/Q90768331 Hao Yang 0036 Microsoft Research Asia, Visual Computing Group, Beijing, China Tsinghua University, School of Software, Beijing, China https://haya.pro/ https://scholar.google.com/citations?user=bMMEEWcAAAAJ Hao Yang 0037 Alibaba Group, Hangzhou, China Hao Yang 0039 Amazon, Vancouver, Canada University of British Columbia, ECE Department, Vancouver, Canada https://people.ece.ubc.ca/haoy/ https://www.linkedin.com/in/steven-hao-yang-b00a5220 https://ieeexplore.ieee.org/author/37085837080 Hao Yang 0040 Beijing Institute of Technology, School of Computer Science and Technology, Beijing, China Yunnan University, School of Information Science and Engineering, Kunming, China https://orcid.org/0000-0002-8112-0869 Hao Yang 0041 Shaanxi Normal University, School of Mathematics and Statistics, Xi'an, China https://orcid.org/0009-0005-9807-5186 Hao Yang 0042 National University of Defense Technology, College of Systems Engineering, Changsha, China https://orcid.org/0000-0002-8013-9023 https://www.wikidata.org/entity/Q131167962 Hao Yang 0044 杨昊 Peking University, Center for Data Science, Beijing, China Hao Yang 0045 Renmin University of China, Gaoling School of Artificial Intelligence, Beijing, China https://orcid.org/0009-0008-5365-897X https://www.wikidata.org/entity/Q131013393 Hao Yang 0046 Northwestern Polytechnical University, School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Xi'an, China https://orcid.org/0009-0007-1273-0050 Hao Yang 0047 Zhejiang University of Technology, Department of Automation, Hangzhou, China https://orcid.org/0000-0002-4506-5524 Hao Yang 0048 Key Laboratory of Cyberspace Situation Awareness of Henan Province, Zhengzhou, China https://orcid.org/0009-0007-7245-1010 https://www.wikidata.org/entity/Q131018103 Hao Yang 0049 Shopee Discovery Ads, Beijing, China https://orcid.org/0009-0007-0867-7410 Hao Yang 0050 Huazhong University of Science and Technology, School of Cyber Science and Engineering, Wuhan, China https://orcid.org/0009-0007-2030-1248 https://www.wikidata.org/entity/Q130909489 Hao Yang 0051 Guangxi University for Nationalities, Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis, Nanning, China https://orcid.org/0009-0004-2759-1864 Hao Yang 0052 Beihang University, School of Aeronautic Science and Engineering, Beijing, China https://orcid.org/0000-0003-1374-6437 Hao Yang 0053 Shanghai University of Engineering Science, School of Mechanical and Automotive Engineering, China Beijing University of Aeronautics and Astronautics, Beijing, China https://orcid.org/0000-0003-3786-5908 Hao Yang 0054 Chinese Academy of Sciences (CAS), Institute of Microelectronics, Beijing, China University of Chinese Academy of Sciences (UCAS), School of Integrated Circuits, Beijing, China https://orcid.org/0000-0002-9564-4815 https://www.wikidata.org/entity/Q130937206 Hao Yang 0055 Fudan University, School of Information Science and Technology, Shanghai, China https://orcid.org/0009-0001-3231-5475 Hao Yang 0056 University of Macau, Department of Computer and Information Science, PAMI Research Group, Macau, China https://orcid.org/0009-0006-8287-4861 Hao Yang 0057 Communication University of China, State Key Laboratory of Media Convergence and Communication, Beijing, China https://orcid.org/0009-0005-9035-8181 Hao Yang 0058 East China University of Science and Technology (ECUST), Department of control science and engineering, Shanghai, China https://orcid.org/0000-0002-5277-1961 Hao Yang 0059 Beijing Institute of Technology, BSchool of Information and Electronics, Beijing, China https://orcid.org/0009-0007-7437-1815 Hao Yang 0060 ShanghaiTech University, Shanghai Institute for Advanced Immunochemical Studies, School of Life Science and Technology, China https://orcid.org/0009-0008-0040-276X Hao Yang 0061 Guizhou University, College of Electrical Engineering, China https://orcid.org/0000-0001-9011-288X Hao Yang 0062 City University of Hong Kong, Department of Electrical Engineering, Hong Kong Nanjing University of Aeronautics and Astronautics, College of Computer Science and Technology, Nanjing, China https://crypto.d4rk.dev/ https://scholar.google.com/citations?user=3SH16Q0AAAAJ https://ieeexplore.ieee.org/author/37088763057 https://orcid.org/0000-0002-9735-255X https://www.wikidata.org/entity/Q130949163 Hao Yang 0063 Hubei University of Technology, School of Electrical and Electronic Engineering, Wuhan, Hubei, China https://orcid.org/0009-0002-2796-4208 Hao Yang 0064 Lanzhou University, School of Information Science and Engineering, China https://orcid.org/0009-0000-0143-372X Hao Yang 0065 Shandong University, School of Software, Jinan, China https://orcid.org/0009-0000-7947-605X Hao Yang 0066 Harbin Institute of Technology, Harbin, China https://orcid.org/0000-0002-8138-7387 Hao Yang 0067 Tianjin University of Technology, School of Computer Science and Engineering, Tianjin, China https://orcid.org/0009-0008-1931-7143 Yuxiao Chen Jue Wang 0010 Zhikang Zhang Jingru Yi Xu Zhang Yang Zou Zhaowei Cai Jianbo Yuan Xinyu Li 0003 Hao Yang 0043 Davide Modolo Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models. WACV 2026 4242-4252 conf/wacv/2026 https://doi.org/10.1109/WACV61042.2026.00413 db/conf/wacv/wacv2026.html#ChenWZYZZCYLYM26 streams/conf/wacv

Yuxiao Chen Jue Wang 0010 Zhikang Zhang Jingru Yi Xu Zhang Yang Zou Zhaowei Cai Jianbo Yuan Xinyu Li 0003 Hao Yang 0043 Davide Modolo Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models. 2026 February abs/2602.17869 CoRR https://doi.org/10.48550/arXiv.2602.17869 db/journals/corr/corr2602.html#abs-2602-17869 streams/journals/corr

Qihua Dong Gozde Sahin Pei Wang Zhaowei Cai Robik Shrestha Hao Yang 0043 Davide Modolo Visual Reasoning through Tool-supervised Reinforcement Learning. 2026 April abs/2604.19945 CoRR https://doi.org/10.48550/arXiv.2604.19945 db/journals/corr/corr2604.html#abs-2604-19945 streams/journals/corr

Pei Wang Zhaowei Cai Hao Yang 0043 Ashwin Swaminathan R. Manmatha Stefano Soatto Scaling up Image Segmentation across Data and Tasks. 4573-4583 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Wang_Scaling_up_Image_Segmentation_across_Data_and_Tasks_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.00431 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#WangCYSMS25 Pei Wang Zhaowei Cai Hao Yang 0043 Davide Modolo Ashwin Swaminathan Enhancing Numerical Prediction of MLLMS With Soft Labeling. 2025 ICCV 3424-3434 conf/iccv/2025 https://doi.org/10.1109/ICCV51701.2025.00327 db/conf/iccv/iccv2025.html#WangCYMS25 streams/conf/iccv Prannay Kaul Zhizhong Li 0001 Hao Yang 0043 Yonatan Dukler Ashwin Swaminathan C. J. Taylor Stefano Soatto THRONE: An Object-Based Hallucination Benchmark for the Free-Form Generations of Large Vision-Language Models. 27218-27228 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.02571 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#KaulLYDSTS24

Pei Wang Zhaowei Cai Hao Yang 0043 Ashwin Swaminathan R. Manmatha Stefano Soatto Mixed-Query Transformer: A Unified Image Segmentation Architecture. 2024 abs/2404.04469 CoRR https://doi.org/10.48550/arXiv.2404.04469 db/journals/corr/corr2404.html#abs-2404-04469

Prannay Kaul Zhizhong Li 0001 Hao Yang 0043 Yonatan Dukler Ashwin Swaminathan C. J. Taylor Stefano Soatto THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models. 2024 abs/2405.05256 CoRR https://doi.org/10.48550/arXiv.2405.05256 db/journals/corr/corr2405.html#abs-2405-05256

Chaofan Tao Gukyeong Kwon Varad Gunjal Hao Yang 0043 Zhaowei Cai Yonatan Dukler Ashwin Swaminathan R. Manmatha Colin J. Taylor Stefano Soatto NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality. 2024 abs/2408.09511 CoRR https://doi.org/10.48550/arXiv.2408.09511 db/journals/corr/corr2408.html#abs-2408-09511 streams/journals/corr

Achin Jain Gurumurthy Swaminathan Paolo Favaro Hao Yang 0043 Avinash Ravichandran Hrayr Harutyunyan Alessandro Achille Onkar Dabeer Bernt Schiele Ashwin Swaminathan Stefano Soatto A Meta-Learning Approach to Predicting Performance and Data Requirements. 3623-3632 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.00353 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#JainSFYRHADSSS23 Hao Li Charless C. Fowlkes Hao Yang 0043 Onkar Dabeer Zhuowen Tu Stefano Soatto Guided Recommendation for Model Fine-Tuning. 3633-3642 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.00354 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#LiFYDTS23 Yonatan Dukler Alessandro Achille Hao Yang 0043 Varsha Vivek Luca Zancato Benjamin Bowman Avinash Ravichandran Charless C. Fowlkes Ashwin Swaminathan Stefano Soatto Your representations are in the network: composable and parallel adaptation for large scale models. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/5be3783ea9d43d7add5409c101d87d83-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#DuklerAYVZBRFSS23

Yonatan Dukler Alessandro Achille Hao Yang 0043 Varsha Vivek Luca Zancato Benjamin Bowman Avinash Ravichandran Charless C. Fowlkes Ashwin Swaminathan Stefano Soatto Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models. 2023 abs/2303.04105 CoRR https://doi.org/10.48550/arXiv.2303.04105 db/journals/corr/corr2303.html#abs-2303-04105

Zhaoyang Zhang Yantao Shen 0002 Kunyu Shi Zhaowei Cai Jun Fang Siqi Deng Hao Yang 0043 Davide Modolo Zhuowen Tu Stefano Soatto Musketeer (All for One, and One for All): A Generalist Vision-Language Model with Task Explanation Prompts. 2023 abs/2305.07019 CoRR https://doi.org/10.48550/arXiv.2305.07019 db/journals/corr/corr2305.html#abs-2305-07019

Pei Wang Zhaowei Cai Hao Yang 0043 Gurumurthy Swaminathan Nuno Vasconcelos Bernt Schiele Stefano Soatto Omni-DETR: Omni-Supervised Object Detection with Transformers. 9357-9366 2022 CVPR https://doi.org/10.1109/CVPR52688.2022.00915 conf/cvpr/2022 db/conf/cvpr/cvpr2022.html#WangCYSVSS22 Kibok Lee 0003 Hao Yang 0043 Satyaki Chakraborty Zhaowei Cai Gurumurthy Swaminathan Avinash Ravichandran Onkar Dabeer Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark. 366-382 2022 ECCV (20) https://doi.org/10.1007/978-3-031-20044-1_21 conf/eccv/2022-20 db/conf/eccv/eccv2022-20.html#LeeYCCSRD22

Pei Wang Zhaowei Cai Hao Yang 0043 Gurumurthy Swaminathan Nuno Vasconcelos Bernt Schiele Stefano Soatto Omni-DETR: Omni-Supervised Object Detection with Transformers. 2022 abs/2203.16089 CoRR https://doi.org/10.48550/arXiv.2203.16089 db/journals/corr/corr2203.html#abs-2203-16089

Kibok Lee 0003 Hao Yang 0043 Satyaki Chakraborty Zhaowei Cai Gurumurthy Swaminathan Avinash Ravichandran Onkar Dabeer Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark. 2022 abs/2207.11169 CoRR https://doi.org/10.48550/arXiv.2207.11169 db/journals/corr/corr2207.html#abs-2207-11169

Achin Jain Kibok Lee 0003 Gurumurthy Swaminathan Hao Yang 0043 Bernt Schiele Avinash Ravichandran Onkar Dabeer ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers. 2022 abs/2209.05654 CoRR https://doi.org/10.48550/arXiv.2209.05654 db/journals/corr/corr2209.html#abs-2209-05654

Hao Li Pratik Chaudhari Hao Yang 0043 Michael Lam Avinash Ravichandran Rahul Bhotika Stefano Soatto Rethinking the Hyperparameters for Fine-tuning. 2020 ICLR https://openreview.net/forum?id=B1g8VkHFPH conf/iclr/2020 db/conf/iclr/iclr2020.html#LiCYLRBS20

Xialei Liu Hao Yang 0043 Avinash Ravichandran Rahul Bhotika Stefano Soatto Continual Universal Object Detection. 2020 abs/2002.05347 CoRR https://arxiv.org/abs/2002.05347 db/journals/corr/corr2002.html#abs-2002-05347

Hao Li Pratik Chaudhari Hao Yang 0043 Michael Lam Avinash Ravichandran Rahul Bhotika Stefano Soatto Rethinking the Hyperparameters for Fine-tuning. 2020 abs/2002.11770 CoRR https://arxiv.org/abs/2002.11770 db/journals/corr/corr2002.html#abs-2002-11770

Alessandro Achille Rahul Bhotika Benjamin Bowman Zhaowei Cai Satyaki Chakraborty Pratik Chaudhari Yuxiao Chen Onkar Dabeer Siqi Deng Qihua Dong Yonatan Dukler Jun Fang Paolo Favaro Charless C. Fowlkes Varad Gunjal Hrayr Harutyunyan Achin Jain Prannay Kaul Gukyeong Kwon Michael Lam Kibok Lee 0003 Hao Li Xinyu Li 0003 Zhizhong Li 0001 Xialei Liu R. Manmatha Davide Modolo Avinash Ravichandran Gozde Sahin Bernt Schiele Yantao Shen 0002 Kunyu Shi Robik Shrestha Stefano Soatto Ashwin Swaminathan Gurumurthy Swaminathan Chaofan Tao C. J. Taylor Colin J. Taylor Zhuowen Tu Nuno Vasconcelos Varsha Vivek Jue Wang 0010 Pei Wang Jingru Yi Jianbo Yuan Luca Zancato Xu Zhang Zhaoyang Zhang Zhikang Zhang Yang Zou