ML Anthology
Authors
Search
About
Panda, Ayush
2 publications
ICLRW
2025
Patterns and Mechanisms of Contrastive Activation Engineering
Yixiong Hao
,
Ayush Panda
,
Stepan Shabalin
,
Sheikh Abdur Raheem Ali
NeurIPSW
2023
Eliciting Language Model Behaviors Using Reverse Language Models
Jacob Pfau
,
Alex Infanger
,
Abhay Sheshadri
,
Ayush Panda
,
Julian Michael
,
Curtis Huebner