@comment{@article{qu2024lmc,
 author = {Qu, Haoxuan and Hui, Xiaofei and Cai, Yujun and Liu, Jun},
 journal = {Advances in Neural Information Processing Systems (NeurIPS)},
 title = {Lmc: Large model collaboration with cross-assessment for training-free open-set object recognition},
 volume = {36},
 url = {https://proceedings.neurips.cc/paper_files/paper/2023/file/91813e5ddd9658b99be4c532e274b49c-Paper-Conference.pdf}
 year = {2023}
}}

@inproceedings{cai2018weakly,
 author = {Cai, Yujun and Ge, Liuhao and Cai, Jianfei and Yuan, Junsong},
 booktitle = {Proceedings of the European conference on computer vision (ECCV)},
 doi = {10.1007/978-3-030-01231-1_41},
 pages = {666--682},
 title = {Weakly-supervised 3d hand pose estimation from monocular rgb images},
 url = {https://doi.org/10.1007/978-3-030-01231-1_41},
 year = {2018}
}

@inproceedings{cai2019exploiting,
 author = {Cai, Yujun and Ge, Liuhao and Liu, Jun and Cai, Jianfei and Cham, Tat-Jen and Yuan, Junsong and Thalmann, Nadia Magnenat},
 booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR)},
 doi = {10.1109/iccv.2019.00236},
 pages = {2272--2281},
 title = {Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks},
 url = {https://doi.org/10.1109/iccv.2019.00236},
 year = {2019}
}

@article{cai20203d,
 author = {Cai, Yujun and Ge, Liuhao and Cai, Jianfei and Thalmann, Nadia Magnenat and Yuan, Junsong},
 doi = {10.1109/tpami.2020.2993627},
 journal = {IEEE transactions on pattern analysis and machine intelligence},
 number = {11},
 pages = {3739--3753},
 publisher = {IEEE},
 title = {3D hand pose estimation using synthetic data and weakly labeled RGB images},
 url = {https://doi.org/10.1109/tpami.2020.2993627},
 volume = {43},
 year = {2020}
}

@inproceedings{cai2020learning,
 author = {Cai, Yujun and Huang, Lin and Wang, Yiwei and Cham, Tat-Jen and Cai, Jianfei and Yuan, Junsong and Liu, Jun and Yang, Xu and Zhu, Yiheng and Shen, Xiaohui and others},
 booktitle = {Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VII 16},
 doi = {10.1007/978-3-030-58571-6_14},
 organization = {Springer International Publishing},
 pages = {226--242},
 title = {Learning progressive joint propagation for human motion prediction},
 url = {https://link.springer.com/chapter/10.1007/978-3-030-58571-6_14},
 year = {2020}
}

@inproceedings{cai2021unified,
 author = {Cai, Yujun and Wang, Yiwei and Zhu, Yiheng and Cham, Tat-Jen and Cai, Jianfei and Yuan, Junsong and Liu, Jun and Zheng, Chuanxia and Yan, Sijie and Ding, Henghui and others},
 booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR)},
 doi = {10.1109/iccv48922.2021.01144},
 pages = {11645--11655},
 title = {A unified 3d human motion synthesis model via conditional variational auto-encoder},
 url = {https://doi.org/10.1109/iccv48922.2021.01144},
 year = {2021}
}

@inproceedings{chen2022geometry,
 author = {Chen, Mingfei and Zhang, Jianfeng and Xu, Xiangyu and Liu, Lijuan and Cai, Yujun and Feng, Jiashi and Yan, Shuicheng},
 booktitle = {European Conference on Computer Vision},
 doi = {10.1007/978-3-031-20050-2_14},
 organization = {Springer Nature Switzerland Cham},
 pages = {222--239},
 title = {Geometry-guided progressive nerf for generalizable and efficient neural human rendering},
 url = {https://doi.org/10.1007/978-3-031-20050-2_14},
 year = {2022}
}

@article{fu2025vistawise,
 author = {Fu, Honghao and Ren, Junlong and Chai, Qi and Ye, Deheng and Cai, Yujun and Wang, Hao},
 journal = {EMNLP},
 title = {VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft},
 url = {https://arxiv.org/abs/2508.18722},
 year = {2025}
}

@inproceedings{ge2018hand,
 author = {Ge, Liuhao and Cai, Yujun and Weng, Junwu and Yuan, Junsong},
 booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)},
 doi = {10.1109/cvpr.2018.00878},
 pages = {8417--8426},
 title = {Hand pointnet: 3d hand pose estimation using point sets},
 url = {https://doi.org/10.1109/cvpr.2018.00878},
 year = {2018}
}

@article{ge2025mrfd,
 author = {Ge, Haonan and Wang, Yiwei and Yang, Ming-Hsuan and Cai, Yujun},
 journal = {EMNLP},
 title = {MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs},
 url = {https://arxiv.org/abs/2508.10264},
 year = {2025}
}

@inproceedings{han2022umetrack,
 author = {Han, Shangchen and Wu, Po-chen and Zhang, Yubo and Liu, Beibei and Zhang, Linguang and Wang, Zheng and Si, Weiguang and Zhang, Peizhao and Cai, Yujun and Hodan, Tomas and others},
 booktitle = {SIGGRAPH Asia 2022 conference papers},
 doi = {10.1145/3550469.3555378},
 pages = {1--9},
 title = {UmeTrack: Unified multi-view end-to-end hand tracking for VR},
 url = {https://doi.org/10.1145/3550469.3555378},
 year = {2022}
}

@article{hao2024exploring,
 author = {Hao, Shuyang and Hooi, Bryan and Liu, Jun and Chang, Kai-Wei and Huang, Zi and Cai, Yujun},
 journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
 title = {Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models},
 url = {https://arxiv.org/abs/2411.18000},
 year = {2025}
}

@article{hao2025making,
 author = {Hao, Shuyang and Wang, Yiwei and Hooi, Bryan and Liu, Jun and Chen, Muhao and Huang, Zi and Cai, Yujun},
 journal = {EMNLP},
 title = {Making every step effective: Jailbreaking large vision-language models through hierarchical kv equalization},
 url = {https://arxiv.org/abs/2503.11750},
 year = {2025}
}

@inproceedings{kin2024stmg,
 author = {Kin, Kenrick and Wan, Chengde and Koh, Ken and Marin, Andrei and Camgoz, Necati Cihan and Zhang, Yubo and Cai, Yujun and Kovalev, Fedor and Ben-Zacharia, Moshe and Hoople, Shannon and others},
 booktitle = {Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI)},
 doi = {10.1145/3613904.3642702},
 pages = {1--15},
 title = {STMG: A Machine Learning Microgesture Recognition System for Supporting Thumb-Based VR/AR Input},
 url = {https://doi.org/10.1145/3613904.3642702},
 year = {2024}
}

@article{li2024drs,
 author = {Li, Zhecheng and Wang, Yiwei and Hooi, Bryan and Cai, Yujun and Peng, Nanyun and Chang, Kai-Wei},
 journal = {ACL},
 title = {DRS: Deep Question Reformulation With Structured Output},
 url = {https://arxiv.org/abs/2411.17993},
 year = {2025}
}

@article{li2024gradiseg,
 author = {Li, Zehao and Han, Wenwei and Cai, Yujun and Jiang, Hao and Bi, Baolong and Gao, Shuqin and Zhao, Honglong and Wang, Zhaoqi},
 journal = {arXiv preprint arXiv:2412.00392},
 title = {GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision},
 url = {https://arxiv.org/abs/2412.00392},
 year = {2024}
}

@article{li2024think,
 author = {Li, Zhecheng and Wang, Yiwei and Hooi, Bryan and Cai, Yujun and Cheung, Naifan and Peng, Nanyun and Chang, Kai-wei},
 journal = {arXiv preprint arXiv:2410.20021},
 title = {Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization},
 url = {https://arxiv.org/abs/2410.20021},
 year = {2024}
}

@article{li2024vulnerability,
 author = {Li, Zhecheng and Wang, Yiwei and Hooi, Bryan and Cai, Yujun and Xiong, Zhen and Peng, Nanyun and Chang, Kai-wei},
 journal = {ACL},
 title = {Vulnerability of LLMs to Vertically Aligned Text Manipulations},
 url = {https://arxiv.org/abs/2410.20016},
 year = {2025}
}

@article{li2024vulnerability,
 author = {Li, Zhecheng and Wang, Yiwei and Hooi, Bryan and Cai, Yujun and Xiong, Zhen and Peng, Nanyun and Chang, Kai-Wei},
 journal = {ACL},
 title = {Vulnerability of LLMs to Vertically Aligned Text Manipulations},
 url = {https://arxiv.org/abs/2410.20016},
 year = {2024}
}

@article{li2025fact,
 author = {Li, Jiaxi and Wang, Yiwei and Zhang, Kai and Cai, Yujun and Hooi, Bryan and Peng, Nanyun and Chang, Kai-Wei and Lu, Jin},
 journal = {arXiv preprint arXiv:2502.14275},
 title = {Fact or Guesswork? Evaluating Large Language Model's Medical Knowledge with Structured One-Hop Judgment},
 url = {https://arxiv.org/abs/2502.14275},
 year = {2025}
}

@article{li2025hyliformer,
 author = {Li, Yue and Qu, Haoxuan and Liu, Mengyuan and Liu, Jun and Cai, Yujun},
 journal = {arXiv preprint arXiv:2502.05869},
 title = {HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition},
 url = {https://arxiv.org/abs/2502.05869},
 year = {2025}
}

@article{li2025semvink,
 author = {Li, Sifan and Cai, Yujun and Wang, Yiwei},
 journal = {EMNLP},
 title = {SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking},
 url = {https://arxiv.org/abs/2506.02803},
 year = {2025}
}

@inproceedings{li2025texture,
 author = {Li, Zhecheng and Song, Guoxian and Cai, Yujun and Xiong, Zhen and Yuan, Junsong and Wang, Yiwei},
 booktitle = {COLM},
 title = {Texture or Semantics? Vision-Language Models Get Lost in Font Recognition},
 url = {https://arxiv.org/pdf/2503.23768?},
 year = {2025}
}

@article{lilatentHOI,
 author = {Li, Muchen and Christen, Sammy and Wan, Chengde and Cai, Yujun and Liao, Renjie  and Sigal, Leonid and Ma, Shugao},
 doi = {10.1109/cvpr52734.2025.01623},
 journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
 title = {LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion},
 url = {https://doi.org/10.1109/cvpr52734.2025.01623},
 year = {2025}
}

@inproceedings{luo2025energy,
 author = {Luo, Yihong and Qiu, Siya and Tao, Xingjian and Cai, Yujun and Tang, Jing},
 booktitle = {European Conference on Computer Vision (ECCV)},
 code_url = {https://github.com/Luo-Yihong/EC-VAE},
 organization = {Springer, Cham},
 pages = {326--344},
 title = {Energy-Calibrated VAE with Test Time Free Lunch},
 url = {https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/11433.pdf},
 year = {2024}
}

@article{qu2022heatmap,
 author = {Qu, Haoxuan and Xu, Li and Cai, Yujun and Foo, Lin Geng and Liu, Jun},
 journal = {Advances in Neural Information Processing Systems},
 pages = {24327--24339},
 title = {Heatmap distribution matching for human pose estimation},
 volume = {35},
 year = {2022}
}

@inproceedings{qu2023characteristic,
 author = {Qu, Haoxuan and Cai, Yujun and Foo, Lin Geng and Kumar, Ajay and Liu, Jun},
 booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
 doi = {10.1109/cvpr52729.2023.01250},
 pages = {13009--13018},
 title = {A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation},
 url = {https://openaccess.thecvf.com/content/CVPR2023/papers/Qu_A_Characteristic_Function-Based_Method_for_Bottom-Up_Human_Pose_Estimation_CVPR_2023_paper.pdf},
 year = {2023}
}

@article{qu2024disc,
 author = {Qu, Haoxuan and Li, Zhuoling and Rahmani, Hossein and Cai, Yujun and Liu, Jun},
 journal = {Advances in Neural Information Processing Systems (NeurIPS)},
 title = {DisC-GS: Discontinuity-aware Gaussian Splatting},
 url = {https://arxiv.org/abs/2405.15196},
 year = {2024}
}

@inproceedings{qu2024llms,
 author = {Qu, Haoxuan and Cai, Yujun and Liu, Jun},
 booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
 doi = {10.1109/cvpr52733.2024.01741},
 pages = {18395--18406},
 title = {Llms are good action recognizers},
 url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Qu_LLMs_are_Good_Action_Recognizers_CVPR_2024_paper.pdf},
 year = {2024}
}

@article{qu2024off,
 author = {Qu, Haoxuan and He, Zhaoyang and Hu, Zeyu and Cai, Yujun and Liu, Jun},
 journal = {arXiv preprint arXiv:2405.15267},
 title = {Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictor},
 url = {https://arxiv.org/abs/2405.15267},
 year = {2024}
}

@article{salter2024emg2pose,
 author = {Salter, Sasha and Warren, Richard and Schlager, Collin and Spurr, Adrian and Han, Shangchen and Bhasin, Rohin and Cai, Yujun and Walkington, Peter and Bolarinwa, Anuoluwapo and Wang, Robert and others},
 journal = {Advances in Neural Information Processing Systems Dataset and Benmark Track (NeurIPS)},
 title = {emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation},
 url = {https://arxiv.org/abs/2412.02725},
 year = {2024}
}

@inproceedings{tanke2023social,
 author = {Tanke, Julian and Zhang, Linguang and Zhao, Amy and Tang, Chengcheng and Cai, Yujun and Wang, Lezi and Wu, Po-Chen and Gall, Juergen and Keskin, Cem},
 booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR)},
 doi = {10.1109/iccv51070.2023.00880},
 pages = {9601--9611},
 title = {Social diffusion: Long-term multiple human motion anticipation},
 url = {https://openaccess.thecvf.com/content/ICCV2023/papers/Tanke_Social_Diffusion_Long-term_Multiple_Human_Motion_Anticipation_ICCV_2023_paper.pdf},
 year = {2023}
}

@article{tao2024llms,
 author = {Tao, Xingjian and Wang, Yiwei and Cai, Yujun and Yang, Zhicheng and Tang, Jing},
 journal = {arXiv preprint arXiv:2412.20846},
 title = {Are LLMs Really Not Knowledgable? Mining the Submerged Knowledge in LLMs' Memory},
 url = {https://arxiv.org/abs/2412.20846},
 year = {2024}
}

@article{tao2025understanding,
 author = {Tao, Xingjian and Wang, Yiwei and Cai, Yujun and Yang, Zhicheng and Tang, Jing},
 journal = {EMNLP},
 title = {Understanding GUI Agent Localization Biases through Logit Sharpness},
 url = {https://arxiv.org/abs/2506.15425},
 year = {2025}
}

@inproceedings{wang2020detecting,
 author = {Wang, Yiwei and Wang, Wei and Ca, Yujun and Hooi, Bryan and Ooi, Beng Chin},
 booktitle = {2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE)},
 doi = {10.1109/issre5003.2020.00037},
 organization = {IEEE},
 pages = {313--324},
 title = {Detecting implementation bugs in graph convolutional network based node classifiers},
 url = {https://doi.org/10.1109/issre5003.2020.00037},
 year = {2020}
}

@article{wang2020graphcrop,
 author = {Wang, Yiwei and Wang, Wei and Liang, Yuxuan and Cai, Yujun and Hooi, Bryan},
 journal = {arXiv preprint arXiv:2009.10564},
 title = {Graphcrop: Subgraph cropping for graph classification},
 url = {https://arxiv.org/abs/2009.10564},
 year = {2020}
}

@inproceedings{wang2020nodeaug,
 author = {Wang, Yiwei and Wang, Wei and Liang, Yuxuan and Cai, Yujun and Liu, Juncheng and Hooi, Bryan},
 booktitle = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
 doi = {10.1145/3394486.3403063},
 pages = {207--217},
 title = {Nodeaug: Semi-supervised node classification with data augmentation},
 url = {https://doi.org/10.1145/3394486.3403063},
 year = {2020}
}

@article{wang2021adaptive,
 author = {Wang, Yiwei and Cai, Yujun and Liang, Yuxuan and Ding, Henghui and Wang, Changhu and Bhatia, Siddharth and Hooi, Bryan},
 journal = {Advances in Neural Information Processing Systems},
 pages = {1440--1452},
 title = {Adaptive data augmentation on temporal graphs},
 volume = {34},
 year = {2021}
}

@inproceedings{wang2021curgraph,
 author = {Wang, Yiwei and Wang, Wei and Liang, Yuxuan and Cai, Yujun and Hooi, Bryan},
 booktitle = {Proceedings of the Web Conference 2021},
 doi = {10.1145/3442381.3450025},
 pages = {1238--1248},
 title = {Curgraph: Curriculum learning for graph classification},
 url = {https://doi.org/10.1145/3442381.3450025},
 year = {2021}
}

@inproceedings{wang2021mixup,
 author = {Wang, Yiwei and Wang, Wei and Liang, Yuxuan and Cai, Yujun and Hooi, Bryan},
 booktitle = {Proceedings of the Web Conference 2021},
 doi = {10.1145/3442381.3449796},
 pages = {3663--3674},
 title = {Mixup for node and graph classification},
 url = {https://doi.org/10.1145/3442381.3449796},
 year = {2021}
}

@inproceedings{wang2021progressive,
 author = {Wang, Yiwei and Wang, Wei and Liang, Yuxuan and Cai, Yujun and Hooi, Bryan},
 booktitle = {Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2020, Ghent, Belgium, September 14--18, 2020, Proceedings, Part I},
 doi = {10.1007/978-3-030-67658-2_16},
 organization = {Springer International Publishing},
 pages = {266--281},
 title = {Progressive supervision for node classification},
 url = {https://doi.org/10.1007/978-3-030-67658-2_16},
 year = {2021}
}

@article{wang2021structure,
 author = {Wang, Yiwei and Cai, Yujun and Liang, Yuxuan and Wang, Wei and Ding, Henghui and Chen, Muhao and Tang, Jing and Hooi, Bryan},
 journal = {arXiv preprint arXiv:2112.00499},
 title = {Structure-aware label smoothing for graph neural networks},
 url = {https://arxiv.org/abs/2112.00499},
 year = {2021}
}

@article{wang2021time,
 author = {Wang, Yiwei and Cai, Yujun and Liang, Yuxuan and Ding, Henghui and Wang, Changhu and Hooi, Bryan},
 journal = {The 2022 International Joint Conference on Neural Networks (IJCNN)},
 title = {Time-aware neighbor sampling for temporal graph networks},
 url = {https://arxiv.org/abs/2112.09845},
 year = {2021}
}

@article{wang2022graphcache,
 author = {Wang, Yiwei and Chen, Muhao and Zhou, Wenxuan and Cai, Yujun and Liang, Yuxuan and Hooi, Bryan},
 journal = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
 title = {Graphcache: Message passing as caching for sentence-level relation extraction},
 url = {https://arxiv.org/abs/2205.03786},
 year = {2022}
}

@article{wang2022should,
 author = {Wang, Yiwei and Chen, Muhao and Zhou, Wenxuan and Cai, Yujun and Liang, Yuxuan and Liu, Dayiheng and Yang, Baosong and Liu, Juncheng and Hooi, Bryan},
 journal = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
 title = {Should we rely on entity mentions for relation extraction? debiasing relation extraction with counterfactual analysis},
 url = {https://arxiv.org/abs/2205.03784},
 year = {2022}
}

@inproceedings{wang2022time,
 author = {Wang, Yiwei and Cai, Yujun and Liang, Yuxuan and Ding, Henghui and Wang, Changhu and Hooi, Bryan},
 booktitle = {2022 International Joint Conference on Neural Networks (IJCNN)},
 doi = {10.1109/ijcnn55064.2022.9892942},
 organization = {IEEE},
 pages = {1--8},
 title = {Time-Aware Neighbor Sampling on Temporal Graphs},
 url = {https://doi.org/10.1109/ijcnn55064.2022.9892942},
 year = {2022}
}

@article{wang2023fragile,
 author = {Wang, Yiwei and Hooi, Bryan and Wang, Fei and Cai, Yujun and Liang, Yuxuan and Zhou, Wenxuan and Tang, Jing and Duan, Manjuan and Chen, Muhao},
 journal = {CONLL},
 title = {How Fragile is Relation Extraction under Entity Replacements?},
 url = {https://arxiv.org/abs/2305.13551},
 year = {2023}
}

@article{wang2023primacy,
 author = {Wang, Yiwei and Cai, Yujun and Chen, Muhao and Liang, Yuxuan and Hooi, Bryan},
 journal = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
 title = {Primacy effect of chatgpt},
 url = {https://arxiv.org/abs/2310.13206},
 year = {2023}
}

@article{wang2024recall,
 author = {Wang, Cheng and Wang, Yiwei and Hooi, Bryan and Cai, Yujun and Peng, Nanyun and Chang, Kai-Wei},
 journal = {International Conference on Computational Linguistics (COLING)},
 title = {Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding},
 url = {https://arxiv.org/abs/2409.03363},
 year = {2025}
}

@article{wang2024recall,
 author = {Wang, Cheng and Wang, Yiwei and Cai, Yujun and Hooi, Bryan},
 doi = {10.18653/v1/2025.naacl-long.210},
 journal = {Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
 title = {Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack},
 url = {https://doi.org/10.18653/v1/2025.naacl-long.210},
 year = {2025}
}

@inproceedings{wang2025text,
 author = {Wang, Zhaochen and Hooi, Bryan and Wang, Yiwei and Yang, Ming-Hsuan and Huang, Zi and Cai, Yujun},
 booktitle = {COLM},
 title = {Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models},
 url = {https://arxiv.org/pdf/2504.01589},
 year = {2025}
}

@article{wu2025dimo,
 author = {Wu, Hang and Chen, Hongkai and Cai, Yujun and Liu, Chang and Ye, Qingwen and Yang, Ming-Hsuan and Wang, Yiwei},
 journal = {EMNLP},
 title = {DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning},
 url = {https://arxiv.org/abs/2507.00008},
 year = {2025}
}

@article{xin2022monago,
 author = {Xin, Ziyin and Cai, Yujun and Dang, Louis T and Burke, Hannah MS and Revote, Jerico and Charitakis, Natalie and Bienroth, Denis and Nim, Hieu T and Li, Yuan-Fang and Ramialison, Mirana},
 doi = {10.1186/s12859-022-04594-1},
 journal = {BMC bioinformatics},
 number = {1},
 pages = {69},
 publisher = {Springer},
 title = {MonaGO: a novel gene ontology enrichment analysis visualisation system},
 url = {https://doi.org/10.1186/s12859-022-04594-1},
 volume = {23},
 year = {2022}
}

@article{xiong2025enhancing,
 author = {Xiong, Zhen and Cai, Yujun and Hooi, Bryan and Peng, Nanyun and Chang, Kai-Wei and Li, Zhecheng and Wang, Yiwei},
 journal = {arXiv preprint arXiv:2502.08180},
 title = {Enhancing LLM Character-Level Manipulation via Divide and Conquer},
 url = {https://arxiv.org/abs/2502.08180},
 year = {2025}
}

@article{xiong2025mapping,
 author = {Xiong, Zhen and Cai, Yujun and Li, Zhecheng and Wang, Yiwei},
 journal = {EMNLP},
 title = {Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM},
 url = {https://arxiv.org/abs/2505.13890},
 year = {2025}
}

@inproceedings{xu20246d,
 author = {Xu, Li and Qu, Haoxuan and Cai, Yujun and Liu, Jun},
 booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
 doi = {10.1109/cvpr52733.2024.00924},
 pages = {9676--9686},
 title = {6d-diff: A keypoint diffusion framework for 6d object pose estimation},
 url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Xu_6D-Diff_A_Keypoint_Diffusion_Framework_for_6D_Object_Pose_Estimation_CVPR_2024_paper.pdf},
 year = {2024}
}

@inproceedings{xu2025does,
 author = {Xu, Chunxue and Wang, Yiwei and Hooi, Bryan and Cai, Yujun and Li, Songze},
 booktitle = {COLM},
 title = {How does Watermarking Affect Visual Language Models in Document Understanding?},
 url = {https://arxiv.org/pdf/2504.01048},
 year = {2025}
}

@article{you2025lost,
 author = {You, Wenhao and Hooi, Bryan and Wang, Yiwei and Choo, Euijin and Yang, Ming-Hsuan and Yuan, Junsong and Huang, Zi and Cai, Yujun},
 journal = {arXiv preprint arXiv:2502.04364},
 title = {Lost in Edits? A λ-Compass for AIGC Provenance},
 url = {https://arxiv.org/abs/2502.04364},
 year = {2025}
}

@inproceedings{zhang2020deepemd,
 author = {Zhang, Chi and Cai, Yujun and Lin, Guosheng and Shen, Chunhua},
 booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR)},
 doi = {10.1109/cvpr42600.2020.01222},
 pages = {12203--12213},
 title = {Deepemd: Few-shot image classification with differentiable earth mover's distance and structured classifiers},
 url = {https://doi.org/10.1109/cvpr42600.2020.01222},
 year = {2020}
}

@article{zhang2021direct,
 author = {Zhang, Jianfeng and Cai, Yujun and Yan, Shuicheng and Feng, Jiashi and others},
 journal = {Advances in Neural Information Processing Systems},
 pages = {13153--13164},
 title = {Direct multi-view multi-person 3d pose estimation},
 volume = {34},
 year = {2021}
}

@article{zhang2022deepemd,
 author = {Zhang, Chi and Cai, Yujun and Lin, Guosheng and Shen, Chunhua},
 doi = {10.1109/tpami.2022.3217373},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
 number = {5},
 pages = {5632--5648},
 publisher = {IEEE},
 title = {Deepemd: Differentiable earth mover's distance for few-shot learning},
 url = {https://doi.org/10.1109/tpami.2022.3217373},
 volume = {45},
 year = {2022}
}