Chris Cundy
~Chris_Cundy1
5
论文总数
2.5
年均投稿
平均评分
接收情况3/5
会议分布
NeurIPS
2
ICLR
2
COLM
1
发表论文 (5 篇)
20254 篇
4
Preference Learning with Lie Detectors can Induce Honesty or Evasion
NeurIPS 2025Poster
4
Planning in a recurrent neural network that plays Sokoban
ICLR 2025Rejected
4
Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
COLM 2025Poster
4
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
NeurIPS 2025Rejected