UA

Usman Anwar

0009-0004-7229-2337

cs.LGcs.AIcs.CLcs.ITmath.ITcs.CRcs.MAcs.ROcs.SYeess.SY

On Valency

published · living versions

Monitorability Is Trainable: Post-Training for Chain-of-Thought Monitorability

with Tim Bakker, Christos Louizos, David Krueger

1 version

W_938rdgm8v1 · current

Preprints & journals

8 papers in the corpus · 2020–2026

Monitorability Is Trainable: Post-Training for Chain-of-Thought Monitorability

Usman Anwar, Tim Bakker, Christos Louizos et al.

0 citations

2610.29734v12026arXiv

Training LLMs to Verbalize Evaluation Awareness

Usman Anwar, Sahar Abdelnabi, David Krueger

0 citations

2609.36316v12026arXiv

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

Usman Anwar, Julianna Piskorz, David D. Baek et al.

0 citations

2602.23163v32026arXiv

Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory

Usman Anwar, Tim Bakker, Dana Kianfar et al.

0 citations

2602.18297v22026arXiv

Interpreting Emergent Planning in Model-Free Reinforcement Learning

Thomas Bush, Stephen Chung, Usman Anwar et al.

0 citations

2504.01871v12025arXiv

The Reality of AI and Biorisk

Aidan Peppin, Anka Reuel, Stephen Casper et al.

8 citations

2412.01946v32024arXiv

Inverse Constrained Reinforcement Learning

Usman Anwar, Shehryar Malik, Alireza Aghasi et al.

7 citations

2011.09999v32020arXiv

Learning To Solve Differential Equations Across Initial Conditions

Shehryar Malik, Usman Anwar, Ali Ahmed et al.

3 citations

2003.12159v22020arXiv

Career total: 9 works. 8 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.