Publication

• SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding [ paper ]
  Mingze Xu*, Mingfei Gao*, Shiyu Li*, Jiasen Lu, Zhe Gan, Zhengfeng Lai, Meng Cao, Kai Kang, Yinfei Yang, Afshin Dehghan
  arXiv preprint, 2025. *Equal contribution.
• MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning [ paper ]
  Haotian Zhang*, Mingfei Gao*, Zhe Gan*, Philipp Dufter, Nina Wenzel, Forrest Huang, Dhruti Shah, Xianzhi Du, Bowen Zhang, Yanghao Li, Sam Dodge, Keen You, Zhen Yang, Aleksei Timofeev, Mingze Xu, Hong-You Chen, Jean-Philippe Fauconnier, Zhengfeng Lai, Haoxuan You, Zirui Wang, Afshin Dehghan, Peter Grasch, Yinfei Yang
  International Conference on Learning Representations (ICLR), 2025. *Equal contribution.
• SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models [ paper ][ code ]
  Mingze Xu*, Mingfei Gao*, Zhe Gan, Hong-You Chen, Zhengfeng Lai, Haiming Gang, Kai Kang, Afshin Dehghan
  arXiv preprint, 2024. *Equal contribution.
• 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities [ paper ][ project page ][ code ]
  Roman Bachmann*, Oğuzhan Fatih Kar*, David Mizrahi*, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir
  Conference on Neural Information Processing Systems (NeurIPS), 2024. *Equal contribution.
• 4M: Massively Multimodal Masked Modeling [ paper ][ project page ][ code ]
  David Mizrahi*, Roman Bachmann*, Oğuzhan Fatih Kar, Teresa Yeo, Mingfei Gao, Afshin Dehghan, Amir Zamir
  Conference on Neural Information Processing Systems (NeurIPS), 2023 (Spotlight). *Equal contribution.
• ULIP: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding [ pdf ][ code ][ project page ]
  Le Xue, Mingfei Gao, Chen Xing, Roberto Martín-Martín, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, Silvio Savarese
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
• Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations [ pdf ][ code ][ project page ]
  Vibashan VS, Ning Yu, Chen Xing, Can Qin, Mingfei Gao, Juan Carlos Niebles, Vishal M. Patel, Ran Xu
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
• TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation [ pdf ][ code ]
  Jun Wang, Mingfei Gao, Yuqian Hu, Ramprasaath R. Selvaraju, Chetan Ramaiah, Ran Xu, Joseph F. JaJa, Larry S. Davis
  British Machine Vision Conference (BMVC), 2022.
• Open Vocabulary Object Detection with Pseudo Bounding-Box Labels [ pdf ][ code ][ blog ]
  Mingfei Gao*, Chen Xing*, Juan Carlos Niebles, Junnan Li, Ran Xu, Wenhao Liu, Caiming Xiong
  European Conference on Computer Vision (ECCV), 2022. *Equal contribution.
• Burn After Reading: Online Adaptation for Cross-domain Streaming Data [ pdf ][ code ]
  Luyu Yang, Mingfei Gao, Zeyuan Chen, Ran Xu, Abhinav Shrivastava, Chetan Ramaiah
  European Conference on Computer Vision (ECCV), 2022.
• DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents [ pdf ][ code ]
  Mingfei Gao*, Le Xue*, Chetan Ramaiah, Chen Xing, Ran Xu, Caiming Xiong
  International Conference on Computational Linguistics (COLING), 2022. *Equal contribution.
• Field Extraction from Forms with Unlabeled Data [ pdf ] [ dataset ][ code ]
  Mingfei Gao, Zeyuan Chen, Nikhil Naik, Kazuma Hashimoto, Caiming Xiong, Ran Xu
  ACL Workshop on Spa-NLP, 2022.
• Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation [ pdf ][ code ]
  Luyu Yang, Yan Wang, Mingfei Gao, Abhinav Shrivastava, Kilian Q. Weinberger, Wei-Lun Chao, Ser-Nam Lim
  International Conference on Computer Vision (ICCV), 2021.
• WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos [ pdf ][ code ]
  Mingfei Gao, Yingbo Zhou, Ran Xu, Richard Socher, Caiming Xiong
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
• Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks [ pdf ]
  Le Xue*, Mingfei Gao*, Zeyuan Chen, Caiming Xiong, Ran Xu
  International Conference on Document Analysis and Recognition (ICDAR), 2023 (Oral). *Equal contribution.
• InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling [ pdf ]
  Jun Wang*, Shiyi Lan*, Mingfei Gao, Larry S. Davis
  European Conference on Computer Vision (ECCV), 2020. *Equal contribution.
• Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost [ pdf ]
  Mingfei Gao, Zizhao Zhang, Guo Yu, Sercan O. Arik, Larry S. Davis, Tomas Pfister
  European Conference on Computer Vision (ECCV), 2020.
• StartNet: Online Detection of Action Start in Untrimmed Videos [ pdf ]
  Mingfei Gao, Mingze Xu, Larry S. Davis, Richard Socher, Caiming Xiong
  International Conference on Computer Vision (ICCV), 2019.
• Temporal Recurrent Networks for Online Action Detection [ pdf ][ code ]
  Mingze Xu*, Mingfei Gao*, Yi-Ting Chen, Larry S. Davis, David J. Crandall
  International Conference on Computer Vision (ICCV), 2019. *Equal contribution.
• WSLLN: Weakly Supervised Natural Language Localization Networks [ pdf ]
  Mingfei Gao, Larry S. Davis, Richard Socher, Caiming Xiong
  Empirical Methods in Natural Language Processing (EMNLP) short, 2019.
• Goal-oriented Object Importance Estimation in On-road Driving Videos[ pdf ]
  Mingfei Gao, Ashish Tawari, Sujitha Martin
  IEEE International Conference on Robotics and Automation (ICRA), 2019.
• C-WSL: Count-guided Weakly Supervised Localization [ pdf ]
  Mingfei Gao, Ang Li, Ruichi Yu, Vlad I. Morariu, Larry S. Davis
  European Conference on Computer Vision (ECCV), 2018.
• Dynamic Zoom-in Network for Fast Object Detection in Large Images [ pdf ]
  Mingfei Gao, Ruichi Yu, Ang Li, Vlad I. Morariu, Larry S. Davis
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
• NISP: Pruning Networks using Neuron Importance Score Propagation [ pdf ]
  Ruichi Yu, Ang Li, Chun-Fu Chen, Jui-Hsin Lai, Vlad I. Morariu, Xintong Han, Mingfei Gao, Ching-Yung Lin, Larry S. Davis
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
• Learning discriminative occlusion feature for depth ordering inference on monocular image
  Anlong Ming, Baofeng Xun, Jia Ni, Mingfei Gao, Yu Zhou
  IEEE International Conference on Image Processing (ICIP), 2015.