|
Yiwei Liu | 刘益伟 I am a fourth-year undergrad student majoring in Software Engineering at Sichuan University. Currently, I am a research assistant at National University of Singapore advised by Prof. Lin Shao (邵林). I'm looking for Ph.D. program opportunities in General Artificial Intelligence on 25fall or 26spring. If you are interested in collaborating, just feel free to contact me. |
|
Research (* denotes equal contribution)I'm interested in Computer Vision, Embodied AI, and AI4Science. |
|
Bi-Adapt: Few-shot Bimanual Adaptation for Novel Categories of 3D Objects via Semantic Correspondence
Jinxian Zhou, Ruihai Wu, Yiwei Liu, Yiwen Hou, Xunzhe Zhou, Checheng Yu, Licheng Zhong, Lin Shao Submitted to ICCV 2025 We propose a foundation model for robots to leverage prior knowledge for adaptively exploring unseen scenarios, thereby enhancing the generalization of interactions across categories in complex bi-manual manipulation tasks. |
|
|
Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models
Chenrui Tie*, Shengxiang Sun*, Jinxuan Zhu, Yiwei Liu, Jingxiang Guo, Yue Hu, Haonan Chen, Junting Chen, Ruihai Wu, Lin Shao Submitted to RSS 2025 arXiv / website / bibtex A novel framework that enables robots to autonomously perform complex assembly tasks in real-life guided by high-level manual instructions. |
|
|
MetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model
Haonan Chen*, Junxiao Li*, Ruihai Wu, Yiwei Liu, Chongkai Gao, Zhixuan Xu, Yiwen Hou, Jingxiang Guo, Zhenyu Wei, Siang Chen, Chenting Wang, Shensi Xu, Jiaqi Huang, Weidong Wang, Lin Shao Submitted to IROS 2025 arXiv / website / bibtex MetaFold employs language-guided point cloud trajectories for task planning and a foundation model for action prediction, enabling better generalization across garments and instructions. |
|
|
Multi-level Sentiment Analysis for Bond Default Risk based on LLMs
Yiwei Liu, Junbo Wang, Lei Long, Shutong Zhou, Xin Li, Ruiting Ma, Yuankai Wu, Xuebin Chen A paper is on going code We propose a novel analytical paradigm using LLMs for bond default analysis, fine-tuning two BERT models for firm-specific sentiment at the micro-level, and exploring industry-specific sentiment based on RAG at the meso-level. |
|
|
Memory-based Ensemble Learning in CMR Semantic Segmentation
Yiwei Liu, Ziyi Wu, Liang Zhong, Lingyi Wen, Yuankai Wu Submitted to MICCAI 2025 arXiv / code / bibtex We propose an ensemble learning paradigm, Streaming, to enhance end-slice accuracy while maintaining near-SOTA DSC performance on cardiac MRI datasets. |
|
Education |
|
National University of Singapore
Aug 2024 - May 2025, Visiting Student (NGNE), School of Computing. May 2023 - Aug 2023, Summer Workshop (First Prize, A+ Student), School of Computing. |
|
|
Sichuan University
Jul 2022 - Jun 2025, Bachelor of Software Engineering, College of Software Engineering. Sep 2021 - Jul 2022, Bachelor of Materials (General Track), College of Materials Science and Engineering. spotlight project (304189030, Data Visualization) |
|
Internship |
|
Siemens Electronics Works Smart Manufacturing Base (SEWC), Chengdu
Jan 2024 - Jun 2024, Embodied AI Intern, IF. demo / testimonial |
|
Miscellanea
|
Visitors |