default search action
Max Tegmark
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j12]Ziming Liu, Eric Gan, Max Tegmark
:
Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability. Entropy 26(1): 41 (2024) - [c14]Stephen Casper
Black-Box Access is Insufficient for Rigorous AI Audits. FAccT 2024: 2254-2272 - [c13]Wes Gurnee, Max Tegmark:
Language Models Represent Space and Time. ICLR 2024 - [i61]Stephen Casper, Carson Ezell, Charlotte Siegmann, Noam Kolt, Taylor Lynn Curtis, Benjamin Bucknall, Andreas Alexander Haupt, Kevin Wei, Jérémy Scheurer, Marius Hobbhahn, Lee Sharkey, Satyapriya Krishna, Marvin Von Hagen
Black-Box Access is Insufficient for Rigorous AI Audits. CoRR abs/2401.14446 (2024) - [i60]Eric J. Michaud, Isaac Liao, Vedang Lad, Ziming Liu, Anish Mudide, Chloe Loughridge, Zifan Carl Guo, Tara Rezaei Kheirkhah, Mateja Vukelic, Max Tegmark:
Opening the AI black box: program synthesis via mechanistic interpretability. CoRR abs/2402.05110 (2024) - [i59]Jinyeop Song, Ziming Liu, Max Tegmark, Jeff Gore:
A Resource Model For Neural Scaling Law. CoRR abs/2402.05164 (2024) - [i58]David D. Baek, Ziming Liu, Max Tegmark:
GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory. CoRR abs/2402.05916 (2024) - [i57]Ziming Liu, Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Soljacic, Thomas Y. Hou, Max Tegmark:
KAN: Kolmogorov-Arnold Networks. CoRR abs/2404.19756 (2024) - [i56]Subhash Kantamneni, Ziming Liu, Max Tegmark:
OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration. CoRR abs/2405.04484 (2024) - [i55]David Dalrymple, Joar Skalse, Yoshua Bengio, Stuart Russell, Max Tegmark, Sanjit Seshia, Steve Omohundro, Christian Szegedy, Ben Goldhaber, Nora Ammann, Alessandro Abate, Joe Halpern, Clark W. Barrett, Ding Zhao, Tan Zhi-Xuan, Jeannette Wing, Joshua B. Tenenbaum:
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems. CoRR abs/2405.06624 (2024) - [i54]Joshua Engels, Isaac Liao, Eric J. Michaud, Wes Gurnee, Max Tegmark:
Not All Language Model Features Are Linear. CoRR abs/2405.14860 (2024) - [i53]Subhash Kantamneni, Ziming Liu, Max Tegmark:
How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator. CoRR abs/2405.17209 (2024) - [i52]Xiaoman Delores Ding, Zifan Carl Guo, Eric J. Michaud, Ziming Liu, Max Tegmark:
Survival of the Fittest Representation: A Case Study with Modular Addition. CoRR abs/2405.17420 (2024) - [i51]Chloe Loughridge, Qinyi Sun, Seth Ahrenbach, Federico Cassano, Chuyue Sun, Ying Sheng, Anish Mudide, Md Rakib Hossain Misu, Nada Amin, Max Tegmark:
DafnyBench: A Benchmark for Formal Software Verification. CoRR abs/2406.08467 (2024) - [i50]Vedang Lad, Wes Gurnee, Max Tegmark:
The Remarkable Robustness of LLMs: Stages of Inference? CoRR abs/2406.19384 (2024) - [i49]Ziming Liu, Pingchuan Ma, Yixuan Wang, Wojciech Matusik, Max Tegmark:
KAN 2.0: Kolmogorov-Arnold Networks Meet Science. CoRR abs/2408.10205 (2024) - [i48]Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schröder de Witt:
Efficient Dictionary Learning with Switch Sparse Autoencoders. CoRR abs/2410.08201 (2024) - [i47]David D. Baek, Yuxiao Li, Max Tegmark:
Generalization from Starvation: Hints of Universality in LLM Knowledge Graph Learning. CoRR abs/2410.08255 (2024) - [i46]Joshua Engels, Logan Riggs, Max Tegmark:
Decomposing The Dark Matter of Sparse Autoencoders. CoRR abs/2410.14670 (2024) - [i45]Yuxiao Li, Eric J. Michaud, David D. Baek, Joshua Engels, Xiaoqing Sun, Max Tegmark:
The Geometry of Concepts: Sparse Autoencoder Feature Structure. CoRR abs/2410.19750 (2024) - 2023
- [j11]Eric J. Michaud, Ziming Liu, Max Tegmark
Precision Machine Learning. Entropy 25(1): 175 (2023) - [c12]Ziming Liu, Eric J. Michaud, Max Tegmark:
Omnigrok: Grokking Beyond Algorithmic Data. ICLR 2023 - [c11]Yilun Xu, Ziming Liu, Yonglong Tian, Shangyuan Tong, Max Tegmark, Tommi S. Jaakkola:
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models. ICML 2023: 38566-38591 - [c10]Eric J. Michaud, Ziming Liu, Uzay Girit, Max Tegmark:
The Quantization Model of Neural Scaling. NeurIPS 2023 - [c9]Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas:
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks. NeurIPS 2023 - [i44]Yilun Xu, Ziming Liu, Yonglong Tian, Shangyuan Tong, Max Tegmark, Tommi S. Jaakkola:
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models. CoRR abs/2302.04265 (2023) - [i43]Eric J. Michaud, Ziming Liu, Uzay Girit, Max Tegmark:
The Quantization Model of Neural Scaling. CoRR abs/2303.13506 (2023) - [i42]Ziming Liu, Di Luo, Yilun Xu, Tommi S. Jaakkola, Max Tegmark:
GenPhys: From Physical Processes to Generative Models. CoRR abs/2304.02637 (2023) - [i41]Ziming Liu, Eric Gan, Max Tegmark:
Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability. CoRR abs/2305.08746 (2023) - [i40]Ziming Liu, Patrick Obin Sturm, Saketh Bharadwaj, Sam Silva, Max Tegmark:
Discovering New Interpretable Conservation Laws as Sparse Invariants. CoRR abs/2305.19525 (2023) - [i39]Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas:
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks. CoRR abs/2306.17844 (2023) - [i38]Max Tegmark, Steve Omohundro:
Provably safe systems: the only path to controllable AGI. CoRR abs/2309.01933 (2023) - [i37]Wes Gurnee, Max Tegmark:
Language Models Represent Space and Time. CoRR abs/2310.02207 (2023) - [i36]Ziming Liu, Max Tegmark:
A Neural Scaling Law from Lottery Ticket Ensembling. CoRR abs/2310.02258 (2023) - [i35]Ziming Liu, Ziqian Zhong, Max Tegmark:
Grokking as Compression: A Nonlinear Complexity Perspective. CoRR abs/2310.05918 (2023) - [i34]Peter S. Park, Max Tegmark:
Divide-and-Conquer Dynamics in AI-Driven Disempowerment. CoRR abs/2310.06009 (2023) - [i33]Samuel Marks, Max Tegmark:
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets. CoRR abs/2310.06824 (2023) - [i32]Ziming Liu, Mikail Khona, Ila R. Fiete, Max Tegmark:
Growing Brains: Co-emergence of Anatomical and Functional Modularity in Recurrent Neural Networks. CoRR abs/2310.07711 (2023) - [i31]Isaac Liao, Ziming Liu, Max Tegmark:
Generating Interpretable Networks using Hypernetworks. CoRR abs/2312.03051 (2023) - 2022
- [j10]Michael Skuhersky, Tailin Wu, Eviatar Yemini, Amin Nejatbakhsh, Edward S. Boyden, Max Tegmark:
Toward a more accurate 3D atlas of C. elegans neurons. BMC Bioinform. 23(1): 195 (2022) - [j9]Andrew K. Tan, Max Tegmark
Pareto-Optimal Clustering with the Primal Deterministic Information Bottleneck. Entropy 24(6): 771 (2022) - [c8]Ziming Liu, Ouail Kitouni, Niklas Nolte, Eric J. Michaud, Max Tegmark, Mike Williams:
Towards Understanding Grokking: An Effective Theory of Representation Learning. NeurIPS 2022 - [c7]Yilun Xu, Ziming Liu, Max Tegmark, Tommi S. Jaakkola:
Poisson Flow Generative Models. NeurIPS 2022 - [i30]Alexander Zlokapa, Andrew K. Tan, John M. Martyn, Max Tegmark, Isaac L. Chuang:
Biological error correction codes generate fault-tolerant neural networks. CoRR abs/2202.12887 (2022) - [i29]Ziming Liu, Varun Madhavan, Max Tegmark:
AI Poincaré 2.0: Machine Learning Conservation Laws from Differential Equations. CoRR abs/2203.12610 (2022) - [i28]Andrew K. Tan, Max Tegmark, Isaac L. Chuang:
Pareto-optimal clustering with the primal deterministic information bottleneck. CoRR abs/2204.02489 (2022) - [i27]Ziming Liu, Ouail Kitouni, Niklas Nolte, Eric J. Michaud, Max Tegmark, Mike Williams:
Towards Understanding Grokking: An Effective Theory of Representation Learning. CoRR abs/2205.10343 (2022) - [i26]Yilun Xu, Ziming Liu, Max Tegmark, Tommi S. Jaakkola:
Poisson Flow Generative Models. CoRR abs/2209.11178 (2022) - [i25]Ziming Liu, Eric J. Michaud, Max Tegmark:
Omnigrok: Grokking Beyond Algorithmic Data. CoRR abs/2210.01117 (2022) - [i24]Eric J. Michaud, Ziming Liu, Max Tegmark:
Precision Machine Learning. CoRR abs/2210.13447 (2022) - 2021
- [i23]Ziming Liu, Bohan Wang, Qi Meng, Wei Chen, Max Tegmark, Tie-Yan Liu:
Machine-Learning Non-Conservative Dynamics for New-Physics Detection. CoRR abs/2106.00026 (2021) - [i22]Samantha D'Alonzo, Max Tegmark:
Machine-Learning media bias. CoRR abs/2109.00024 (2021) - [i21]Ziming Liu, Max Tegmark:
Machine-learning hidden symmetries. CoRR abs/2109.09721 (2021) - [i20]Ziming Liu, Yunyue Chen, Yuanqi Du, Max Tegmark:
Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed Learning. CoRR abs/2109.13901 (2021) - 2020
- [j8]Max Tegmark
Pareto-Optimal Data Compression for Binary Classification Tasks. Entropy 22(1): 7 (2020) - [c6]Silviu-Marian Udrescu, Andrew K. Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, Max Tegmark:
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity. NeurIPS 2020 - [i19]Silviu-Marian Udrescu, Max Tegmark:
Symbolic Pregression: Discovering Physical Laws from Raw Distorted Video. CoRR abs/2005.11212 (2020) - [i18]Silviu-Marian Udrescu, Andrew K. Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, Max Tegmark:
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity. CoRR abs/2006.10782 (2020) - [i17]Ziming Liu, Max Tegmark:
AI Poincaré: Machine Learning Conservation Laws from Trajectories. CoRR abs/2011.04698 (2020)
2010 – 2019
- 2019
- [j7]Tailin Wu, Ian S. Fischer
Learnability for the Information Bottleneck. Entropy 21(10): 924 (2019) - [j6]Li Jing, Çaglar Gülçehre
Gated Orthogonal Recurrent Units: On Learning to Forget. Neural Comput. 31(4) (2019) - [c5]Tailin Wu, Ian S. Fischer, Isaac L. Chuang, Max Tegmark:
Learnability for the Information Bottleneck. UAI 2019: 1050-1060 - [i16]Ricardo Vinuesa, Hossein Azizpour, Iolanda Leite, Madeline Balaam, Virginia Dignum, Sami Domisch
The role of artificial intelligence in achieving the Sustainable Development Goals. CoRR abs/1905.00501 (2019) - [i15]Silviu-Marian Udrescu, Max Tegmark:
AI Feynman: a Physics-Inspired Method for Symbolic Regression. CoRR abs/1905.11481 (2019) - [i14]Tailin Wu, Ian S. Fischer, Isaac L. Chuang, Max Tegmark:
Learnability for the Information Bottleneck. CoRR abs/1907.07331 (2019) - [i13]Max Tegmark, Tailin Wu:
Pareto-optimal data compression for binary classification tasks. CoRR abs/1908.08961 (2019) - 2018
- [c4]Li Jing, Çaglar Gülçehre, John Peurifoy, Yichen Shen, Max Tegmark, Marin Soljacic, Yoshua Bengio:
Gated Orthogonal Recurrent Units: On Learning to Forget. AAAI Workshops 2018: 720-726 - [c3]David Rolnick, Max Tegmark:
The power of deeper networks for expressing natural functions. ICLR (Poster) 2018 - [i12]Tailin Wu, John Peurifoy, Isaac L. Chuang, Max Tegmark:
Meta-learning autoencoders for few-shot prediction. CoRR abs/1807.09912 (2018) - [i11]Tailin Wu, Max Tegmark:
Toward an AI Physicist for Unsupervised Learning. CoRR abs/1810.10525 (2018) - 2017
- [j5]Henry W. Lin
Critical Behavior in Physics and Probabilistic Formal Languages. Entropy 19(7): 299 (2017) - [c2]Li Jing, Yichen Shen, Tena Dubcek, John Peurifoy, Scott A. Skirlo, Yann LeCun, Max Tegmark, Marin Soljacic:
Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs. ICML 2017: 1733-1741 - [i10]Ben Garfinkel, Miles Brundage, Daniel Filan, Carrick Flynn, Jelena Luketina, Michael Page, Anders Sandberg, Andrew Snyder-Beattie, Max Tegmark:
On the Impossibility of Supersized Machines. CoRR abs/1703.10987 (2017) - [i9]David Rolnick, Max Tegmark:
The power of deeper networks for expressing natural functions. CoRR abs/1705.05502 (2017) - [i8]Li Jing, Çaglar Gülçehre, John Peurifoy, Yichen Shen, Max Tegmark, Marin Soljacic, Yoshua Bengio:
Gated Orthogonal Recurrent Units: On Learning to Forget. CoRR abs/1706.02761 (2017) - 2016
- [j4]Max Tegmark:
Improved Measures of Integrated Information. PLoS Comput. Biol. 12(11) (2016) - [i7]Stuart Russell, Daniel Dewey, Max Tegmark:
Research Priorities for Robust and Beneficial Artificial Intelligence. CoRR abs/1602.03506 (2016) - [i6]Henry Lin, Max Tegmark:
Critical Behavior from Deep Dynamics: A Hidden Dimension in Natural Language. CoRR abs/1606.06737 (2016) - [i5]Henry W. Lin, Max Tegmark:
Why does deep and cheap learning work so well? CoRR abs/1608.08225 (2016) - [i4]Li Jing, Yichen Shen, Tena Dubcek, John Peurifoy, Scott A. Skirlo, Max Tegmark, Marin Soljacic:
Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNN. CoRR abs/1612.05231 (2016) - 2015
- [j3]Stuart Russell, Daniel Dewey, Max Tegmark:
Research Priorities for Robust and Beneficial Artificial Intelligence. AI Mag. 36(4): 105-114 (2015) - [c1]Max Tegmark:
Friendly Artificial Intelligence: The Physics Challenge. AAAI Workshop: AI and Ethics 2015 - [i3]Max Tegmark:
Nuclear War from a Cosmic Perspective. CoRR abs/1505.00246 (2015) - 2014
- [i2]Max Tegmark:
Friendly Artificial Intelligence: the Physics Challenge. CoRR abs/1409.0813 (2014)
2000 – 2009
- 2000
- [j2]Max Tegmark:
Why the brain is probably not a quantum computer. Inf. Sci. 128(3-4): 155-179 (2000)
1990 – 1999
- 1999
- [i1]Max Tegmark:
The importance of quantum decoherence in brain processes. CoRR quant-ph/9907009 (1999) - 1994
- [j1]Harold S. Shapiro, Max Tegmark:
An Elementary Proof That the Biharmonic Green Function of an Eccentric Ellipse Changes Sign. SIAM Rev. 36(1): 99-101 (1994)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-01 00:12 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: