Xuchan Bao
4
Papers
163
Total Citations
Papers (4)
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
ICML 2025arXiv
110
citations
Tell me about yourself: LLMs are aware of their learned behaviors
ICLR 2025arXiv
53
citations
Regularized linear autoencoders recover the principal components, eventually
NeurIPS 2020arXiv
0
citations
Learning to Elect
NeurIPS 2021arXiv
0
citations