Weiyang is currently a doctoral researcher at the University of Cambridge under the Cambridge-Tübingen Program. His research interests broadly lie in deep learning, representation learning, interactive machine learning and causality. Recently, he is particularly interested in applying causality to overcome fundamental challenges in deep learning. Prior to joining Cambridge, Weiyang conducted research at Georgia Institute of Technology and served as a research intern at Google Brain, Nvidia Research, and MERL.
Whilst at Leverhulme CFI he will be part of the Trust and Transparency research programme.
Liu, W., Liu, Z., Wang, H., Paull, L., Schölkopf, B., Weller, A. (2021). Iterative Teaching by Label Synthesis. In Neural Information Processing Systems (NeurIPS).
Iterative Teaching by Label Synthesis. In Neural Information Processing Systems (NeurIPS), 2021 [selected for spotlight presentation]. Abstract: In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. In contrast to previous methods that have to scan over the entire pool and select teaching examples from […]
This project is developing processes to ensure that AI systems are transparent, reliable and trustworthy. As AI systems are widely deployed in real-world settings, it is critical for us to understand the mechanisms by which they take decisions, when they can be trusted to perform well, and when they may fail. This project addresses these […]
