Yicheng Qiao | 乔亦诚
My Story
I am Yicheng Qiao, born on November 30th, 2001, in Kaifeng City, China. As the Chinese proverb goes, "The movement of heaven is full of power; thus the superior man makes himself strong and untiring." This philosophy underpins my approach to life. My passion for artificial intelligence began in middle school. Ever since AlphaGo defeated the world's strongest Go player, I have been determined to pursue a career in AI and aspired to study a related field at university.
Research Interest and Plan
I am a joint program student at Tsinghua University and Beijing Sport University. I earned my degree in Data Science and Big Data Technology at Beijing Sport University and completed the joint educational program at Tsinghua University's School of Vehicle and Mobility.
- I am keenly interested in the intersection of multimodal learning, multi-task learning, and AI agents driven by large languagemodels (LLMs) and generative models. Humans naturally integrate vision, speech, and action. As AI research shifts toward more generalizable models, I strive to develop solutions that can interpret diverse inputs, handle multiple tasks, and ultimately improve people’s lives.
Publications & Preprints (Incl. Conference, Journal and Chinese Core Journal)
- C1: Liu, W.*, Wang, W., Yicheng Qiao*, Guo, Q., Zhu, J., Li, P., Chen, Z., Yang, H., Li, Z., Wang, L., Tan, T., Liu, H. “MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception,” in Conference on Computer Vision and Pattern Recognition (CVPR), 2025,* Main authors. [Github]
- C2: Liu, W., Yicheng Qiao, Wang, Z., Guo, Q., Chen, Z., Zhou, M., Li, X., Wang, L., Li, Z., Liu, H., Wang, W. “TEM3-Learning: Time-Efficient Multimodal Multi-Task Learning for Advanced Assistive Driving” under review IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025. [Github]
- J1: Liu, W.*, Yicheng Qiao*, Li, Z., Zhang, W., Zhu, J., Wang, L., Wang, H., Liu, H., and Wang, K. “UDM-Net: Unified Assistive Driving Multi-task Perception Network based on Multimodal Fusion,” in IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2025,* Co-first authors (JCR-Q1). [Github]
- J2: Yang, H.*, Liu, W.*, Yicheng Qiao*, Li, Z., Wang, W., Tan, T., Liu, H. “CrossRay3D: Geometry and Distribution Guidance for Efficient Cross-Modal 3D Detection” under review IEEE Transactions On Circuits And Systems For Video Technoloy (TCSVT), 2025,* Co-first authors (JCR-Q1).
- J3: Liu, W., Lu, J., Liao, J., Yicheng Qiao*, Zhang, G., Zhu, J., Zhang, G., Zhu, J., Xu, B., and Li, Z. “FMDNet: Feature attention embedding based Multimodal fusion Driving behavior classification Network,” in IEEE Transactions on Computational Social Systems (TCSS), 2024, *Corresponding author (JCR-Q1). [Github] [PDF]
- J4: Liu, W., Wang, H., Yicheng Qiao, Yang, J., Zhang, H. “DLAFNet: Direct LiDAR-Aerial Fusion Network for Semantic Segmentation of 2D Multispectral Aerial Image and 3D LiDAR Point Cloud,” in IEEE Journal Of Selected Topics In Applied Earth Observations And Remote Sensing (J-STARS), 2024 (JCR-Q1). [Github] [PDF]
- J5: Tan, Q., Liu, W., Bi, H., Yicheng Qiao, Jiang, Y., Guo, Q., Liu, H., Li, Z., Qiu, C. “SAMOccNet: Refined SAM-based Surrounding Semantic Occupancy Perception for Autonomous Driving,” under review in NEUROCOMPUTING, 2025 (JCR-Q1).
- C3: Yicheng Qiao, Liu, W., Liang, B., Wang, P., Zhang, H. and Yang, J. “SeMask-Mask2Former: A Semantic Segmentation Model for High Resolution Remote Sensing Images,” in IEEE Aerospace Conference (AeroConf), 2023. [Github] [PDF]
- C4: Liu, W., Wang, H., Yicheng Qiao, Liang, B., Zhang, H. and Yang, J. “DLAFNET: A Direct Fusion Method Of 2D Aerial Image And 3D Lidar Point Cloud For Semantic Segmentation,” in International Geoscience and Remote Sensing Symposium (IGARSS Oral), 2023. [Github] [PDF]
- CJ1: Liu, W., Yicheng Qiao, Yin, X., Liu, J., Gan, Y., Li, Z., Zhang, G. “Froth edge segmentation in flotation images [J].” Nonferrous Metals (Mineral Processing Section), 2024(4):67-76.
- CJ2: Yin, M., Yicheng Qiao, Zhang, D., Guo, J., Zhu, M., Wang, C. “Data Augmentation Based on Style Transfer,” in Information Technology and Informatization, Issue 11, 2023.