Yiqi Lin

PhD Student
Show Lab · National University of Singapore
Multimodal Learning · Video Understanding & Generation · Robotics
Profile

Bio

I am a PhD student at Show Lab, National University of Singapore. My research lies in multimodal learning, with a focus on video generation and editing, vision-language models, and robot learning.

Recent Publications

CVPR '26
Demo2Tutorial: From Human Experience to Multimodal Software Tutorials
Zechen Bai, Zhiheng Chen, Yiqi Lin, Kevin Qinghong Lin, Difei Gao, Xiangwu Guo, Xin Wang & Mike Zheng Shou
paper code
Preprint '26
Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
Ziyun Zeng, Yiqi Lin, Guoqiang Liang & Mike Zheng Shou
paper project
Preprint '26
Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
Yiqi Lin, Guoqiang Liang, Ziyun Zeng, Zechen Bai, Yanzhe Chen & Mike Zheng Shou
paper project code demo
ICML '26
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
Yanzhe Chen, Kevin Yuchen Ma, Qi Lv, Yiqi Lin, Zechen Bai, Chen Gao & Mike Zheng Shou
CVPR '25
LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale
Joya Chen*, Ziyun Zeng*, Yiqi Lin*, Wei Li, Zejun Ma & Mike Zheng Shou
paper project code
ECCV '24
oral
Parrot Captions Teach CLIP to Spot Text
Yiqi Lin, Conghui He, Alex Jinpeng Wang, Bin Wang, Weijia Li & Mike Zheng Shou
paper project code

For the complete and most up-to-date list, please see Google Scholar.