Scholar
Xuchan Bao
Google Scholar ID: gnBwBZ4AAAAJ
University of Toronto
Deep Learning
Control Theory
Reinforcement Learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
927
H-index
8
i10-index
8
Publications
13
Co-authors
0
Publications
2 items
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
2025
Cited
0
Tell me about yourself: LLMs are aware of their learned behaviors
2025
Cited
0
