David D. Baek

PhD student, EECS, Massachusetts Institute of Technology

Joined

February 2024

Names

David D. Baek (Preferred)

Emails

****@mit.edu (Confirmed)

Personal Links

Google Scholar

Career & Education History

PhD student

EECS, Massachusetts Institute of Technology (mit.edu)

2023 – 2028

Advisors, Relations & Conflicts

PhD Advisor

Max Tegmark

2023 – 2028

Expertise

Mechanistic Interpretability

Present

Representation Learning

Present

Scalable Oversight

Present

AI Safety Alignment

Present

LLM Post-training

Present

Publications

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Usman Anwar, Julianna Piskorz, David D. Baek, David Demitri Africa, Jim Weatherall, Max Tegmark, Christian Schroeder de Witt, Mihaela van der Schaar, David Krueger
- ICLR 2026 AIWILD
- Readers: Everyone
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Usman Anwar, Julianna Piskorz, David D. Baek, David Demitri Africa, Jim Weatherall, Max Tegmark, Christian Schroeder de Witt, Mihaela van der Schaar, David Krueger
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
Jiawei Zhang, Andrew Estornell, David D. Baek, Bo Li, Xiaojun Xu
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Investigating Representation Universality: Case Study on Genealogical Representations
David D. Baek, Yuxiao Li, Max Tegmark
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Harmonic Loss Trains Interpretable AI Models
David D. Baek, Ziming Liu, Riya Tyagi, Max Tegmark
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
Jiawei Zhang, Andrew Estornell, David D. Baek, Bo Li, Xiaojun Xu
- ICLR 2026 Poster
- Readers: Everyone
Harmonic Loss Trains Interpretable AI Models
David D. Baek, Ziming Liu, Riya Tyagi, Max Tegmark
- Accepted by TMLR
- Readers: Everyone
Scaling Laws For Scalable Oversight
Joshua Engels, David D. Baek, Subhash Kantamneni, Max Tegmark
- NeurIPS 2025 spotlight
- Readers: Everyone
Towards Understanding Distilled Reasoning Models: A Representational Approach
David D. Baek, Max Tegmark
- BuildingTrust
- Readers: Everyone
The Geometry of Concepts: Sparse Autoencoder Feature Structure
Yuxiao Li, Eric J Michaud, David D. Baek, Joshua Engels, Xiaoqing Sun, Max Tegmark
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

View all 11 publications

David D. Baek

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors