Zhifeng Hao

ChorusTIC achieves strong multivariate time series classification without the need for retraining on specific tasks, revolutionizing how we approach classification in heterogeneous data environments.

IADD-TR reveals that decoupling action dynamics from environmental evolution can drastically enhance sample efficiency in model-based reinforcement learning.

CDFM outperforms traditional causal discovery algorithms by leveraging a unified framework that adapts to diverse datasets without the need for extensive retraining.