MT
Max Tegmark
astro-phcs.LGastro-ph.COcs.AIhep-thastro-ph.IMgr-qchep-phstat.MLquant-ph
On Valency
published · living versionsW_r645usyg·v1 · currentpublished
Baryon Acoustic Oscillations in the Sloan Digital Sky Survey Data Release 7 Galaxy Sample
with Will J. Percival, Beth A. Reid, Daniel J. Eisenstein, Neta A. Bahcall +23
1 version
Preprints & journals
316 papers in the corpus · 1993–2026Variational Continuation for Double Pendulum Periodic Orbits2609.05337v1 · Leo Yao, Ziming Liu, Max Tegmark2026 · 0 citationsarXiv
The 2026 Singapore Consensus on Global AI Safety Research Priorities2608.14611v1 · Stephen Casper, Oskar Galeev, Yoshua Bengio et al.2026 · 0 citationsarXiv
Sycophancy Towards Researchers Drives Performative Misalignment2606.08629v1 · David D. Baek, Xinnuo Li, Anay Gupta et al.2026 · 0 citationsarXiv
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring2602.23163v3 · Usman Anwar, Julianna Piskorz, David D. Baek et al.2026 · 0 citationsarXiv
A Definition of AGI2510.18212v3 · Dan Hendrycks, Dawn Song, Christian Szegedy et al.2025 · 3 citationsarXiv
A benchmark for vericoding: formally verified program synthesis2509.22908v1 · Sergiu Bursuc (BAIF), Theodore Ehrenborg (BAIF), Shaowei Lin (BAIF) et al.2025 · 1 citationarXiv
The Singapore Consensus on Global AI Safety Research Priorities2506.20702v2 · Yoshua Bengio, Tegan Maharaj, Luke Ong et al.2025 · 5 citationsarXiv
Dense SAE Latents Are Features, Not Bugs2506.15679v2 · Xiaoqing Sun, Alessandro Stolfo, Joshua Engels et al.2025 · 0 citationsarXiv
On the creation of narrow AI: hierarchy and nonlocality of neural network skills2505.15811v2 · Eric J. Michaud, Asher Parker-Sartori, Max Tegmark2025 · 2 citationsarXiv
Symbolic Learning of Topological Bands in Photonic Crystals2505.10485v2 · Ali Ghorashi, Sachin Vaidya, Ziming Liu et al.2025 · 1 citationarXiv
Neural Thermodynamic Laws for Large Language Model Training2505.10559v1 · Ziming Liu, Yizhou Liu, Jeff Gore et al.2025 · 0 citationsarXiv
Scaling Laws For Scalable Oversight2504.18530v3 · Joshua Engels, David D. Baek, Subhash Kantamneni et al.2025 · 5 citationsNeurIPS 2025 (Spotlight)
Do Two AI Scientists Agree?2504.02822v1 · Xinghong Fu, Ziming Liu, Max Tegmark2025 · 0 citationsarXiv
The Geometry of Concepts: Sparse Autoencoder Feature Structure.40282579 · Li, Yuxiao, Michaud, Eric J, Baek, David D et al.2026 · 14 citationsEntropy (Basel, Switzerland). 2025;27(4)
Towards Understanding Distilled Reasoning Models: A Representational Approach2503.03730v2 · David D. Baek, Max Tegmark2025 · 0 citationsICLR 2025 Workshop on Building Trust in Language Models and Applications
GenEFT: Understanding statics and dynamics of model generalization via physics-inspired effective theory.40247517 · Baek, David D, Liu, Ziming, Tegmark, Max2025 · 0 citationsPhysical review. E. 2025;111(3-2):035307
Are Sparse Autoencoders Useful? A Case Study in Sparse Probing2502.16681v1 · Subhash Kantamneni, Joshua Engels, Senthooran Rajamanoharan et al.2025 · 0 citationsarXiv
Harmonic Loss Trains Interpretable AI Models2502.01628v2 · David D. Baek, Ziming Liu, Riya Tyagi et al.2025 · 0 citationsarXiv
Language Models Use Trigonometry to Do Addition2502.00873v1 · Subhash Kantamneni, Max Tegmark2025 · 5 citationsarXiv
Discovering candidates for integrable systems via backpropagation.40103091 · Kantamneni, Subhash, Liu, Ziming, Tegmark, Max2025 · 3 citationsPhysical review. E. 2025;111(2-2):025303
Low-Rank Adapting Models for Sparse Autoencoders2501.19406v2 · Matthew Chen, Joshua Engels, Max Tegmark2025 · 1 citationarXiv
Open Problems in Mechanistic Interpretability2501.16496v1 · Lee Sharkey, Bilal Chughtai, Joshua Batson et al.2025 · 11 citationsarXiv
Physics of Skill Learning2501.12391v1 · Ziming Liu, Yizhou Liu, Eric J. Michaud et al.2025 · 0 citationsarXiv
Opening the AI Black Box: Distilling Machine-Learned Algorithms into Code.39766675 · Michaud, Eric J, Liao, Isaac, Lad, Vedang et al.2025 · 2 citationsEntropy (Basel, Switzerland). 2024;26(12)
How Do Transformers Model Physics? Investigating the Simple Harmonic Oscillator.39593941 · Kantamneni, Subhash, Liu, Ziming, Tegmark, Max2026 · 0 citationsEntropy (Basel, Switzerland). 2024;26(11)
Fault-tolerant neural networks from biological error correction codes.39690671 · Zlokapa, Alexander, Tan, Andrew K, Martyn, John M et al.2024 · 7 citationsPhysical review. E. 2024;110(5-1):054303
Decomposing The Dark Matter of Sparse Autoencoders2410.14670v2 · Joshua Engels, Logan Riggs, Max Tegmark2024 · 1 citationarXiv
Efficient Dictionary Learning with Switch Sparse Autoencoders2410.08201v2 · Anish Mudide, Joshua Engels, Eric J. Michaud et al.2024 · 0 citationsarXiv
Investigating Representation Universality: Case Study on Genealogical Representations2410.08255v2 · David D. Baek, Yuxiao Li, Max Tegmark2024 · 0 citationsNeurIPS 2025 Workshop on Responsible Foundation Models
KAN 2.0: Kolmogorov-Arnold Networks Meet Science2408.10205v1 · Ziming Liu, Pingchuan Ma, Yixuan Wang et al.2024 · 294 citationsarXiv
The Remarkable Robustness of LLMs: Stages of Inference?2406.19384v3 · Vedang Lad, Jin Hwa Lee, Wes Gurnee et al.2024 · 0 citationsarXiv
DafnyBench: A Benchmark for Formal Software Verification2406.08467v1 · Chloe Loughridge, Qinyi Sun, Seth Ahrenbach et al.2024 · 6 citationsarXiv
Survival of the Fittest Representation: A Case Study with Modular Addition2405.17420v1 · Xiaoman Delores Ding, Zifan Carl Guo, Eric J. Michaud et al.2024 · 0 citationsarXiv
Not All Language Model Features Are One-Dimensionally Linear2405.14860v3 · Joshua Engels, Eric J. Michaud, Isaac Liao et al.2024 · 4 citationsarXiv
How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator2405.17209v1 · Subhash Kantamneni, Ziming Liu, Max Tegmark2024 · 0 citationsarXiv
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems2405.06624v3 · David "davidad" Dalrymple, Joar Skalse, Yoshua Bengio et al.2024 · 12 citationsarXiv
OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration2405.04484v1 · Subhash Kantamneni, Ziming Liu, Max Tegmark2024 · 1 citationarXiv
KAN: Kolmogorov-Arnold Networks2404.19756v5 · Ziming Liu, Yixuan Wang, Sachin Vaidya et al.2024 · 852 citationsarXiv
Opening the AI black box: program synthesis via mechanistic interpretability2402.05110v1 · Eric J. Michaud, Isaac Liao, Vedang Lad et al.2024 · 3 citationsarXiv
A Resource Model For Neural Scaling Law2402.05164v2 · Jinyeop Song, Ziming Liu, Max Tegmark et al.2024 · 0 citationsarXiv
Interpretable conservation laws as sparse invariants.38491673 · Liu, Ziming, Sturm, Patrick Obin, Bharadwaj, Saketh et al.2024 · 12 citationsPhysical review. E. 2024;109(2):L023301
Black-Box Access is Insufficient for Rigorous AI Audits2401.14446v3 · Stephen Casper, Carson Ezell, Charlotte Siegmann et al.2024 · 79 citationsThe 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT '24), June 3-6, 2024, Rio de Janeiro, Brazil
Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability.38248167 · Liu, Ziming, Gan, Eric, Tegmark, Max2024 · 28 citationsEntropy (Basel, Switzerland). 2023;26(1)
Generating Interpretable Networks using Hypernetworks2312.03051v1 · Isaac Liao, Ziming Liu, Max Tegmark2023 · 1 citationarXiv
Growing Brains: Co-emergence of Anatomical and Functional Modularity in Recurrent Neural Networks2310.07711v1 · Ziming Liu, Mikail Khona, Ila R. Fiete et al.2023 · 0 citationsarXiv
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets2310.06824v3 · Samuel Marks, Max Tegmark2023 · 21 citationsarXiv
Grokking as Compression: A Nonlinear Complexity Perspective2310.05918v1 · Ziming Liu, Ziqian Zhong, Max Tegmark2023 · 0 citationsarXiv
Divide-and-Conquer Dynamics in AI-Driven Disempowerment2310.06009v2 · Peter S. Park, Max Tegmark2023 · 0 citationsarXiv
Language Models Represent Space and Time2310.02207v3 · Wes Gurnee, Max Tegmark2023 · 46 citationsarXiv
A Neural Scaling Law from Lottery Ticket Ensembling2310.02258v2 · Ziming Liu, Max Tegmark2023 · 0 citationsarXiv
Career total: 595 works. 316 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.