Xiaotian Han

@misc{ai2024dreamclear,
  title = {DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation},
  author = {Yuang, Ai and Xiaoqiang, Zhou and Huaibo, Huang and Xiaotian, Han and Zhengyu, Chen and Quanzeng, You and Hongxia, Yang},
  year = {2024},
  journal = {Advances in Neural Information Processing Systems},
  url = {https://arxiv.org/abs/2410.18666},
}

@misc{han2024infimmwebmath40badvancingmultimodalpretraining,
  title = {InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning},
  author = {Han, Xiaotian and Jian, Yiren and Hu, Xuefeng and Liu, Haogeng and Wang, Yiqi and Fan, Qihang and Ai, Yuang and Huang, Huaibo and He, Ran and Yang, Zhenheng and You, Quanzeng},
  year = {2024},
  eprint = {2409.12568},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2409.12568},
}

@inproceedings{liu-etal-2024-infimm,
  author = {Liu, Haogeng and You, Quanzeng and Han, Xiaotian and Wang, Yiqi and Zhai, Bohan and Liu, Yongfei and Chen, Wentao and Jian, Yiren and Tao, Yunzhe and Yuan, Jianbo and He, Ran and Yang, Hongxia},
  title = {InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model},
  booktitle = {Findings of the Association for Computational Linguistics ACL 2024},
  year = {2024},
  pages = {485--492},
  address = {Bangkok, Thailand and virtual meeting},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.findings-acl.27},
}

@misc{fan2024vitar,
  title = {ViTAR: Vision Transformer with Any Resolution},
  author = {Fan, Qihang and You, Quanzeng and Han, Xiaotian and Liu, Yongfei and Tao, Yunzhe and Huang, Huaibo and He, Ran and Yang, Hongxia},
  year = {2024},
  eprint = {2403.18361},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2403.18361},
}

@misc{liu2024infimmhd,
  title = {InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding},
  author = {Liu, Haogeng and You, Quanzeng and Han, Xiaotian and Wang, Yiqi and Zhai, Bohan and Liu, Yongfei and Tao, Yunzhe and Huang, Huaibo and He, Ran and Yang, Hongxia},
  year = {2024},
  eprint = {2403.01487},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2403.01487},
}

@misc{han2024coco,
  title = {COCO is "ALL'' You Need for Visual Instruction Fine-tuning},
  author = {Han, Xiaotian and Wang, Yiqi and Zhai, Bohan and You, Quanzeng and Yang, Hongxia},
  year = {2024},
  eprint = {2401.08968},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2401.08968},
}

@misc{wang2024exploring,
  title = {Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning},
  author = {Wang, Yiqi and Chen, Wentao and Han, Xiaotian and Lin, Xudong and Zhao, Haiteng and Liu, Yongfei and Zhai, Bohan and Yuan, Jianbo and You, Quanzeng and Yang, Hongxia},
  year = {2024},
  eprint = {2401.06805},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2401.06805},
}

@misc{han2023infimmeval,
  title = {InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models},
  author = {Han, Xiaotian and You, Quanzeng and Liu, Yongfei and Chen, Wentao and Zheng, Huangjie and Mrini, Khalil and Lin, Xudong and Wang, Yiqi and Zhai, Bohan and Yuan, Jianbo and Wang, Heng and Yang, Hongxia},
  year = {2023},
  eprint = {2311.11567},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://infimm.github.io/InfiMM-Eval/},
}

@inproceedings{Han_2023_WACV,
  author = {Han, Xiaotian and You, Quanzeng and Wang, Chunyu and Zhang, Zhizheng and Chu, Peng and Hu, Houdong and Wang, Jiang and Liu, Zicheng},
  title = {MMPTRACK: Large-Scale Densely Annotated Multi-Camera Multiple People Tracking Benchmark},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year = {2023},
  pages = {4860-4869},
  url = {https://arxiv.org/abs/2111.15157},
}

@misc{han2021image,
  title = {Image Scene Graph Generation (SGG) Benchmark},
  author = {Han, Xiaotian and Yang, Jianwei and Hu, Houdong and Zhang, Lei and Gao, Jianfeng and Zhang, Pengchuan},
  year = {2021},
  eprint = {2107.12604},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2107.12604},
}