Author

Jiayu Xiao

Observed name: Xiao, Jiayu

Institutions: Chinese University of Hong Kong, Shenzhen, Alibaba Group (China)

Observed institutions: Institute of Computing Technology, Chinese University of Hong Kong, Shenzhen, University of Chinese Academy of Sciences, Alibaba Group (China)

ORCID: 0009-0007-3510-8301

Observed ORCID: 0009-0007-3510-8301

OpenAlex ID: A5115604719

Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization

2024 · Henglei Lv, Jiayu Xiao, et al. · ACM International Conference on Multimedia (ACM MM) · 10

When Shards Fly: Cross-Tensor In-Flight Conversion for Low-Latency, Low-Memory Weight Updates in Disaggregated RL

2026 · Xiao, Jiayu, Wang, Ye, et al. · arXiv (Cornell University)

TAG: Calibrating SAM3 for Universal Image Segmentation without Dense Supervision

2026 · Zhu, Hao, Sun, Heyu, et al. · arXiv (Cornell University)

Works count: 3

Citation count: 10

H-index: 1

I10-index: 1