Rusheb Shah

According to our database1, Rusheb Shah authored at least 6 papers between 2023 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

2023
2024
0
1
2
3
4
5
2
3
1

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Frontier Models are Capable of In-context Scheming.
CoRR, 2024

Towards evaluations-based safety cases for AI scheming.
CoRR, 2024

2023
Structured World Representations in Maze-Solving Transformers.
CoRR, 2023

Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.
CoRR, 2023

A Configurable Library for Generating and Manipulating Maze Datasets.
CoRR, 2023

Linearly Structured World Representations in Maze-Solving Transformers.
Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models, 2023


  Loading...