Xuchan (Jenny) Bao

Xuchan (Jenny) Bao

jennybao at cs dot toronto dot edu

I am a PhD student at the University of Toronto and the Vector Institute. I am fortunate to be supervised by Prof. Roger Grosse. My research interests lie broadly in neural network training dynamics, AI safety, control theory and optimization.

I obtained my B.A.Sc in Engineering Science (robotics option) at the University of Toronto. During my undergraduate years, I interned at Dessa and was a summer research student at Prof. Angela Schoellig's lab. I was also part of The University Of Toronto Self-Driving Car Team.

Google Scholar / Twitter / Github

Research

	Extending the Noisy Quadratic Models using Linear Matrix Inequalities Xuchan Bao, John W. Simpson-Porco , Roger Grosse pre-print, 2025
	Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs Jan Betley, Danial Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Martín Soto, Nathan Labenz, Owain Evans ICML, 2025*
	Tell me about yourself: LLMs are aware of their learned behaviors Jan Betley, Xuchan Bao, Martín Soto, Anna Sztyber-Betley, James Chua, Owain Evans ICLR, 2025*
	Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance Xuchan Bao, Judith Yue Li, Zhong Yi Wan, Kun Su, Timo Denk, Joonseok Lee, Dima Kuzmin, Fei Sha IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025
	Statistics estimation in neural network training: a recursive identification approach Ruth Crasto, Xuchan Bao, Roger Grosse ICML 2023 Workshop on New Frontiers in Learning, Control, and Dynamical Systems
	Hessian Inertia in Neural Networks Xuchan Bao, Alberto Bietti, Aaron Defazio, Vivien Cabannes ICML 2023 Workshop on High-dimensional Learning Dynamics
	Finding and Only Finding Differential Nash Equilibria by Both Pretending to be a Follower Xuchan Bao, Guodong Zhang Transactions on Machine Learning Research (TMLR), 2023 Featured certification (awarded to papers that are very high quality, approximately equal to oral/spotlight in top-tier conferences)
	Learning to Elect Cem Anil, Xuchan Bao NeurIPS, 2021
	A unified analysis of first-order methods for smooth games via integral quadratic constraints Guodong Zhang, Xuchan Bao, Laurent Lessard, Roger Grosse JMLR, 2021
	Regularized linear autoencoders recover the principal components, eventually Xuchan Bao, James Lucas, Sushant Sachdeva, Roger Grosse NeurIPS, 2020 poster / code
	Benchmarking model-based reinforcement learning Tingwu Wang, Xuchan Bao, Clavera Ignasi, Jerrick Hoang, Yeming Wen, Eric Langlois, Shunshi Zhang, Guodong Zhang, Pieter Abbeel, Jimmy Ba arXiv pre-print, 2019 code
	Timbretron: A wavenet (cyclegan (cqt (audio))) pipeline for musical timbre transfer Sicong Huang, Qiyang Li, Cem Anil, Xuchan Bao, Sageev Oore, Roger B Grosse ICLR, 2019 project page
	Deep neural networks for improved, impromptu trajectory tracking of quadrotors Qiyang Li, Jingxing Qian, Zining Zhu, Xuchan Bao, Mohamed K Helwa, Angela P Schoellig ICRA, 2017 proceeding

Teaching

I was a teaching assistant for the following courses:

CSC2541: Topics in Machine Learning: Neural Net Training Dynamics. Winter 2022.

CSC413/421/2516: Neural Networks. Winter 2021 / Winter 2020 / Winter 2019.

CSC311/2515: Introduction to Machine Learning. Fall 2021 / Fall 2020 / Fall 2019.

CSC180: Introduction to Programming. Fall 2016.

Website design and source code from Jon Barron.