Lingwei Dang

“We can only see a short distance ahead, but we can see plenty there that needs to be done.” — Alan Turing, Computing Machinery and Intelligence (1950)

Research Interests: Computer vision, Multimodal learning, etc.

Email Google Scholar Github

Education

	South China University of Technology Ph.D. student in Software Engineering 2024.09 – Present Advised by Prof. Qingyao Wu; privileged to be co-advised by Prof. Yebin Liu of Tsinghua University.	2024.09 – Present
	South China University of Technology M.E. in Computer Technology 2020.09 – 2023.06 Advised by Assoc. Prof. Yongwei Nie; co-advised by Chengjiang Long, Tech Leader at ByteDance, USA.	2020.09 – 2023.06
	Shanghai University B.S. in Computer Science and Technology 2016.09 – 2020.06 Advised by Assoc. Prof. Yan Sun and Prof. Yuchun Fang.	2016.09 – 2020.06

Work Experience

	Kuaishou Technology · Kling Team Research Intern 2026.05 – Present	2026.05 – Present
	Ant Group AI Engineer 2023.07 – 2024.06 Supervised by Jingting Ding and Chenguang Ma.	2023.07 – 2024.06
	Tencent · Technology Engineering Group (TEG) AI Research Intern 2022.05 – 2022.07 Mentored by Haozhe Xie and Hong Shang.	2022.05 – 2022.07

Research

2026

	HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis Lingwei Dang, Juntong Li, Zonghan Li, Hongwen Zhang, Liang An, Wei Min, Yebin Liu, Qingyao Wu The 19th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH Asia), 1th Dec. 2026, KLCC, Kuala Lumpur, Malaysia. 24.5%=322/1315 project page \| arXiv \| code
	Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling Juntong Li^, Lingwei Dang^(Equal Contribution & Project Leader), Haomin Wu, Ziyan Qiu, Qingxin Xiao, Qingyao Wu The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 6th Dec. 2026, Sydney, Australia. 25.73%=7900/30709 project page \| arXiv
	Video Anomaly Detection with Semantics-Aware Information Bottleneck Juntong Li^, Lingwei Dang^(Equal Contribution), Qingxin Xiao, Shishuo Shang, Jiajia Cheng, Haomin Wu, Yun Hao, Qingyao Wu IEEE International Conference on Multimedia and Expo (ICME), July 5-9, 2026, Bangkok, Thailand project page \| arXiv
	Registration-free visible-thermal fusion for UAV detection Shenghui Huang, Yuqi Wang, Longkun Zou, Lingwei Dang, Hongyu Chi, Xiaopei Chen, Ke Chen, Qingyao Wu Journal of Information Fusion, IF=17.4, 2026 Paper \| PDF
	Not Just Detection: Aligned-Driven Purification of Indirect Prompt Injection for Reliable Agent Interaction Qingxin Xiao, Boyang Zhang, Ziqian Zeng, Zhengle Ding, Xin Cheng, Lingwei Dang, Jinhui Wu, Yangyang Zhao, Qingyao Wu 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 4-8, 2026, Barcelona, Spain Paper \| PDF
	ExPart3D: Exclusive Part Aggregation for Zero-shot Point Cloud Learning Yun Hao, Jiaju Wu, Zhongneng Ma, Lingwei Dang, Yukun Su Qingyao Wu Expert Systems with Applications, Available online 7 April 2026, 132370 Paper \| PDF

2025

	SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios Lingwei Dang^, Ruizhi Shao^, Hongwen Zhang, Wei MIN, Yebin Liu, Qingyao Wu The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS, Spotlight), 3.19%=688/21575, 7th Dec. 2025, San Diego Convention Center project page \| arXiv \| video \| code
	SCAM-Net: Unifying Box Annotations and Pixel-Level Masks for Fundus Image Segmentation Meiju Hu, Lingwei Dang, Xin Cheng, Yun Hao, Yuning Wang, Pengshuai Yin, Yanwu Xu, Qingyao Wu PRCV, Oct. 15-18, 2025 Paper \| PDF
	Beyond game environments: Evolutionary algorithms with parameter space noise for task-oriented dialogue policy exploration Qingxin Xiao, Yangyang Zhao, Lingwei Dang, Yun Hao, Le Che, Qingyao Wu Neurocomputing, May 28, 2025, (IF 5.5) Paper \| PDF

2022

	Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space Lingwei Dang, Yongwei Nie, Chengjiang Long, Qing Zhang, Guiqing Li Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), Lisbon, Portugal, Oct 10-14, 2022. Top 1 Conference in Multimeida, accepted paper: 690, acceptance rate: 27.9% project page \| arXiv \| video \| code
	A Fine Three-dimensional Adaptive Color Segmentation Algorithm for Real-time Vision System of Soccer Robot Yan Sun^✉, Lingwei Dang Proceedings of the 4th International Conference on Communications, Information System and Computer Engineering (CISCE), Shenzhen, China, Jun 24-26, 2022. PDF

2021

MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
Lingwei Dang, Yongwei Nie, Chengjiang Long, Qing Zhang, Guiqing Li
Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, Oct 11-17, 2021.
Top 3 Conferences in Computer Vision, accepted paper: 1617, acceptance rate: 25.9%
project page | arXiv | video | code

Service

Conference Reviewer	CVPR, ICCV, ICLR, ICML
Journal Reviewer	TMM, TVCG

Template adapted from Ye Yuan and jonbarron. Many thanks ❤️.