Overview
Availability
- Dr Yujun Cai is:
- Available for supervision
Qualifications
- Doctor of Philosophy of Electrical Engineering and Computer Science, Nanyang Technological University
Works
Search Professor Yujun Cai’s works on UQ eSpace
2026
Conference Publication
STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
Li, Zehao, Jiang, Hao, Cai, Yujun, Chen, Jianing, Bi, Baolong, Gao, Shuqin, Zhao, Honglong, Wang, Yiwei, Mao, Tianlu and Wang, Zhaoqi (2026). STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering. New York, NY, USA: ACM. doi: 10.1145/3767308.3836162
2026
Conference Publication
Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise
Lian, Puwei, Cai, Yujun, Li, Songze and Bao, Bingkun (2026). Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise. New York, NY, USA: ACM. doi: 10.1145/3767308.3836139
2026
Journal Article
Visual CoT makes VLMs smarter but more fragile
Xu, Chunxue, Wang, Yiwei, Cai, Yujun, Hooi, Bryan and Li, Songze (2026). Visual CoT makes VLMs smarter but more fragile. Pattern Recognition, 184 115251, 115251-115251. doi: 10.1016/j.patcog.2026.115251
2026
Conference Publication
HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
Chen, Jianing, Li, Zehao, Cai, Yujun, Jiang, Hao, Qian, Chengxuan, Kang, Juyuan, Gao, Shuqin, Zhao, Honglong, Mao, Tianlu and Zhang, Yucheng (2026). HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA, U.S.A. and Mexico City, Mexico, 2-7 December 2025 and 30 November -5 December 2025. Neural Information Processing Systems Foundation, Inc. (NeurIPS). doi: 10.52202/085713-4184
2026
Conference Publication
Beyond query bias: candidate-aware iterative refinement for zero-shot composed image retrieval
Sun, Nan, Tang, Jing, Sun, Lei, Chen, Rui, Lu, Yuxing, Chu, Xiangxiang, Ling, Hefei and Cai, Yujun (2026). Beyond query bias: candidate-aware iterative refinement for zero-shot composed image retrieval. 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), San Diego, CA, United States, 2-7 July 2026. Kerrville, Texas, United States: Association for Computational Linguistics (ACL). doi: 10.18653/v1/2026.findings-acl.1120
2026
Conference Publication
ReCon: Active defense against large vision-language model jailbreaks via reverse safety concept injection
He, Zheng, Wang, Yiwei, Wang, Hongxing and Cai, Yujun (2026). ReCon: Active defense against large vision-language model jailbreaks via reverse safety concept injection. 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), San Diego, CA, United States, 2-7 July 2026. Kerrville, Texas, United States: Association for Computational Linguistics (ACL). doi: 10.18653/v1/2026.findings-acl.1173
2026
Conference Publication
Viewfusion: structured spatial thinking chains for multi-view reasoning
Tao, Xingjian, Wang, Yiwei, Cai, Yujun, Song, Yifan and Tang, Jing (2026). ViewFusion: Structured Spatial Thinking Chains for Multi-view Reasoning. Springer Science and Business Media Deutschland GmbH. doi: 10.1007/978-3-032-37447-9_8
2026
Conference Publication
Mitigating coordinate prediction bias from positional encoding failures
Tao, Xingjian, Wang, Yiwei, Cai, Yujun, Luo, Yihong, Han, Kai and Tang, Jing (2026). Mitigating coordinate prediction bias from positional encoding failures. 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), San Diego, CA, United States, 2-7 July 2026. Kerrville, Texas, United States: Association for Computational Linguistics (ACL). doi: 10.18653/v1/2026.findings-acl.1034
2026
Book Chapter
HighlightBench: Benchmarking and Diagnosing Markup-Driven Table Reasoning in Scientific Documents
Wang, Lexin, Liu, Shenghua, Wang, Yiwei, Cai, Yujun, Ge, Yuyao, Yao, Jiayu, Guo, Jiafeng and Cheng, Xueqi (2026). HighlightBench: Benchmarking and Diagnosing Markup-Driven Table Reasoning in Scientific Documents. Lecture Notes in Computer Science. (pp. 301-317) Cham: Springer Nature Switzerland. doi: 10.1007/978-3-032-37135-5_17
2025
Conference Publication
LatentHOI: on the generalizable hand object motion generation with latent hand diffusion
Li, Muchen, Christen, Sammy, Wan, Chengde, Cai, Yujun, Liao, Renjie, Sigal, Leonid and Ma, Shugao (2025). LatentHOI: on the generalizable hand object motion generation with latent hand diffusion. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, United States, 10-17 June 2025. Washington, DC, United States: IEEE Computer Society. doi: 10.1109/CVPR52734.2025.01623
2025
Conference Publication
Vulnerability of LLMs to vertically aligned text manipulations
Li, Zhecheng, Wang, Yiwei, Hooi, Bryan, Cai, Yujun, Xiong, Zhen, Peng, Nanyun and Chang, Kai-Wei (2025). Vulnerability of LLMs to vertically aligned text manipulations. 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, 27 July-1 August 2025. Stroudsburg, PA USA: Association for Computational Linguistics. doi: 10.18653/v1/2025.acl-long.978
2025
Conference Publication
Exploring visual vulnerabilities via multi-loss adversarial search for jailbreaking vision-language models
Hao, Shuyang, Hooi, Bryan, Liu, Jun, Chang, Kai-Wei, Huang, Zi and Cai, Yujun (2025). Exploring visual vulnerabilities via multi-loss adversarial search for jailbreaking vision-language models. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TX, United States, 10 - 17 June 2025. Washington, DC, United States: I E E E Computer Society. doi: 10.1109/cvpr52734.2025.01852
2025
Journal Article
SED-MVS: segmentation-driven and edge-aligned deformation multi-view stereo with depth restoration and occlusion constraint
Yuan, Zhenlong, Yang, Zhidong, Cai, Yujun, Wu, Kuangxin, Liu, Mufan, Zhang, Dapeng, Jiang, Hao, Li, Zhaoxin and Wang, Zhaoqi (2025). SED-MVS: segmentation-driven and edge-aligned deformation multi-view stereo with depth restoration and occlusion constraint. IEEE Transactions on Circuits and Systems for Video Technology, 35 (11), 11244-11257. doi: 10.1109/TCSVT.2025.3574473
2025
Conference Publication
Dimo-gui: advancing test-time scaling in gui grounding via modality-aware visual reasoning
Wu, Hang, Chen, Hongkai, Cai, Yujun, Liu, Chang, Ye, Qingwen, Yang, Ming-Hsuan and Wang, Yiwei (2025). DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning. Association for Computational Linguistics (ACL). doi: 10.18653/v1/2025.emnlp-main.1334
2025
Conference Publication
Energy-Calibrated VAE with Test Time Free Lunch
Luo, Yihong, Qiu, Siya, Tao, Xingjian, Cai, Yujun and Tang, Jing (2025). Energy-Calibrated VAE with Test Time Free Lunch. 18th European Conference on Computer Vision (ECCV), Milan Italy, Sep 29-Oct 04, 2024. Heidelberg, Germany: Springer. doi: 10.1007/978-3-031-73013-9_19
2025
Conference Publication
Mapping the minds of LLMs: a graph-based analysis of reasoning LLMs
Xiong, Zhen, Cai, Yujun, Li, Zhecheng and Wang, Yiwei (2025). Mapping the minds of LLMs: a graph-based analysis of reasoning LLMs. The 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China, 4-9 November, 2025. Stroudsburg, PA, United States: Association for Computational Linguistics. doi: 10.18653/v1/2025.emnlp-main.896
2025
Conference Publication
Tricking retrievers with influential tokens: an efficient black-box corpus poisoning attack
Wang, Cheng, Wang, Yiwei, Cai, Yujun and Hooi, Bryan (2025). Tricking retrievers with influential tokens: an efficient black-box corpus poisoning attack. 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, Albuquerque, New Mexico, 29 April-4 May 2025. Albuquerque, New Mexico: Association for Computational Linguistics (ACL). doi: 10.18653/v1/2025.naacl-long.210
2025
Conference Publication
Vistawise: building cost-effective agent with cross-modal knowledge graph for minecraft
Fu, Honghao, Ren, Junlong, Chai, Qi, Ye, Deheng, Cai, Yujun and Wang, Hao (2025). VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft. Association for Computational Linguistics (ACL). doi: 10.18653/v1/2025.emnlp-main.1111
2025
Conference Publication
SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
Li, Sifan, Cai, Yujun and Wang, Yiwei (2025). SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking. The 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China, 4 - 9 November , 2025. Stroudsburg, PA, United States: Association for Computational Linguistics. doi: 10.18653/v1/2025.emnlp-main.1381
2025
Conference Publication
CON-RECALL: Detecting Pre-training Data in LLMs via Contrastive Decoding
Wang, Cheng, Wang, Yiwei, Hooi, Bryan, Cai, Yujun, Peng, Nanyun and Chang, Kai-Wei (2025). CON-RECALL: Detecting Pre-training Data in LLMs via Contrastive Decoding. 31st International Conference on Computational Linguistics, Abu Dhabi, United Arab Emirates, 19-24 January 2025. Stroudsburg, PA, United States: Association for Computational Linguistics (ACL).
Funding
Current funding
Supervision
Availability
- Dr Yujun Cai is:
- Available for supervision
Looking for a supervisor? Read our advice on how to choose a supervisor.
Available projects
-
Multi-Modal Perception for Context-Aware Systems
Develop algorithms for multi-modal perception, integrating visual, textual and other data modalities to enhance contextual understanding.
Supervision history
Current supervision
-
Doctor Philosophy
Multi-Modal Perception for Context-Aware Systems
Principal Advisor
Other advisors: Associate Professor Miao Xu
-
Doctor Philosophy
Multi-Modal Perception for Context-Aware Systems
Associate Advisor
Other advisors: Associate Professor Miao Xu
-
Doctor Philosophy
Towards Scalable Sign Language Understanding: From Streaming Translation to Low Resource Transfer
Associate Advisor
Other advisors: Dr Heming Du, Associate Professor Xin Yu
-
Doctor Philosophy
Multimodal Learning for Advanced Graph Data Analysis
Associate Advisor
Other advisors: Professor Helen Huang, Dr Ruihong Qiu
Media
Enquiries
For media enquiries about Dr Yujun Cai's areas of expertise, story ideas and help finding experts, contact our Media team: