Author

Yiyang Cai

Observed name: Cai, Yiyang

Institutions: Hong Kong University of Science and Technology, Fudan University, University of Hong Kong

Observed institutions: Hong Kong University of Science and Technology, Fudan University, University of Hong Kong

OpenAlex ID: A5139308057

ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships

2026 · Liu, Xinyu, Li, Shihao, et al. · arXiv (Cornell University) · 4

The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction

2026 · Zhou, Xunzhe, Cai, Yiyang, et al. · arXiv (Cornell University) · 2

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement

2026 · Cai, Yiyang, Chen, Nan, et al. · arXiv (Cornell University) · 2

MoCaP: Mobile Code-as-Policies for Zero-Shot Mobile Manipulation from Passive Human Videos

2026 · Cai, Yiyang, Kamijo, Tatsuya, et al. · arXiv (Cornell University) · 1

Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement

2026 · Jiang, Chunyang, Zhang, Pingping, et al. · arXiv (Cornell University) · 1

DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation

2026 · Chen, Nan, Cai, Yiyang, et al. · arXiv (Cornell University) · 1

Works count: 6

Citation count: 11

H-index: 2

I10-index: