Tianyi Zhou

My research interests are in machine learning, optimization, and natural language processing. I have published ~130 papers in ML (NeurIPS, ICML, ICLR), NLP (ACL, EMNLP, NAACL), CV (CVPR, ICCV, ECCV), DM (KDD, ICDM), AI (AAAI, IJCAI) conferences, and journals as Machine Learning (Springer), IEEE TPAMI/TIP/TNNLS/TKDE, etc.

Our recent works study (1) How, why, and when to transfer human learning (e.g., curriculum, retention, sub-tasking, curiosity, exemplar selection, collaboration, etc.) to improve machine learning and generalization in the wild (e.g., with unlabeled, biased, noisy, redundant, or distributed data, in unseen tasks/environments); (2) Controllable Generative AI in both training and inference/adaptation; (3) Synthetic data, self-evolving AI, and auto-benchmarking; and (4) Human-AI teaming and hybrid agent with personalization. We are developing these methods with LLMs, multi-modality foundation models, and RL, to address practical challenges in education, design, medical health, visualization, embodied intelligence, autonomous driving, etc. Our goal is to develop efficient, versatile, trustworthy, and environmentally-friendly hybrid-intelligence based on coevolution between human and machine. The code/data/models can be found at Tianyi Lab's GitHub and HF.