David D. Baek

According to our database, David D. Baek authored at least 8 papers between 2024 and 2026.

Collaborative distances:

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

2026

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

Usman Anwar, Julianna Piskorz, David D. Baek, David Africa, James Weatherall, Max Tegmark, Christian Schroeder de Witt, Mihaela van der Schaar, David Krueger

CoRR, February, 2026

2025

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth.

Jiawei Zhang, Andrew Estornell, David D. Baek, Bo Li, Xiaojun Xu

CoRR, October, 2025

Scaling Laws For Scalable Oversight.

Joshua Engels, David D. Baek, Subhash Kantamneni, Max Tegmark

CoRR, April, 2025

Towards Understanding Distilled Reasoning Models: A Representational Approach.

David D. Baek, Max Tegmark

CoRR, March, 2025

Harmonic Loss Trains Interpretable AI Models.

David D. Baek, Ziming Liu, Riya Tyagi, Max Tegmark

Trans. Mach. Learn. Res., 2025

The Geometry of Concepts: Sparse Autoencoder Feature Structure.

Yuxiao Li, Eric J. Michaud, David D. Baek, Joshua Engels, Xiaoqing Sun, Max Tegmark

Entropy, 2025

2024

Generalization from Starvation: Hints of Universality in LLM Knowledge Graph Learning.

David D. Baek, Yuxiao Li, Max Tegmark

CoRR, 2024

GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory.

David D. Baek, Ziming Liu, Max Tegmark

CoRR, 2024