Shi, Xiangyu

3 publications

ICLR 2026 Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization Simon Sinong Zhan, Qingyuan Wu, Philip Wang, Frank Yang, Xiangyu Shi, Chao Huang, Qi Zhu

ICLR 2026 KVComm: Enabling Efficient LLM Communication Through Selective KV Sharing Xiangyu Shi, Marco Chiesa, Gerald Q. Maguire Jr., Dejan Kostic

ECCVW 2024 Improving Online Source-Free Domain Adaptation for Object Detection by Unsupervised Data Acquisition Xiangyu Shi, Yanyuan Qiao, Qi Wu, Lingqiao Liu, Feras Dayoub