Thomas Kwa

According to our database, Thomas Kwa authored at least 4 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification.

Thomas Kwa, Drake Thomas, Adrià Garriga-Alonso

CoRR, 2024

InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques.

Rohan Gupta, Iván Arcuschin, Thomas Kwa, Adrià Garriga-Alonso

CoRR, 2024

Compact Proofs of Model Performance via Mechanistic Interpretability.

Jason Gross, Rajashree Agrawal, Thomas Kwa, Euan Ong, Chun Hei Yip, Alex Gibson, Soufiane Noubir, Lawrence Chan

CoRR, 2024

2020

Securing Smart Home Edge Devices against Compromised Cloud Servers.

Rahmadi Trimananda, Ali Younis, Thomas Kwa, Brian Demsky, Harry Xu

CoRR, 2020