John Hughes
4
Papers
62
Total Citations
Papers (4)
Looking Inward: Language Models Can Learn About Themselves by Introspection
ICLR 2025arXiv
40
citations
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
ICLR 2025
22
citations
Debating with More Persuasive LLMs Leads to More Truthful Answers
ICML 2024
0
citations
Hierarchical Quantized Autoencoders
NeurIPS 2020
0
citations