Luke Marks

Publication Activity (10 Years)

Years Active: 2023-2024
Publications (10 Years): 2

Top Topics

Partial Information

Language Modelling

Top Venues

Publications

Luke Marks
Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations. CoRR (2024)
Luke Marks, Amir Abdullah, Luna Mendez, Rauno Arike, Philip H. S. Torr, Fazl Barez
Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders. CoRR (2023)