关注
Joan Velja
标题
引用次数
引用次数
年份
Dynamic Vocabulary Pruning in Early-Exit LLMs
J Vincenti*, KA Sadek*, J Velja*, M Nulli*, M Jazbec
Efficient Natural Language and Speech Processing (ENLSP-IV) Workshop NeurIPS …, 2024
2024
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
Y Mathew*, O Matthews*, R McCarthy*, J Velja*, CS de Witt, D Cope, ...
arXiv preprint arXiv:2410.03768, 2024
2024
'Explaining RL Decisions with Trajectories': A Reproducibility Study
K Abdel Sadek*, M Nulli*, J Velja*, J Vincenti
Published in Transactions on Machine Learning Research (05/2024), arXiv …, 2024
2024
Emergence of Steganography Between Large Language Models
Y Mathew, R McCarthy, J Velja, O Matthews, N Schoots, D Cope
Workshop on Socially Responsible Language Modelling Research, 0
系统目前无法执行此操作,请稍后再试。
文章 1–4