Ziming Liu
Research Subjects
Ziming Liu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Max Tegmark
Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
3 shared publications - Pingchuan Ma
Massachusetts Institute of Technology
1 shared publication - Subhash Kantamneni
Massachusetts Institute of Technology
1 shared publication - Wojciech Matusik
MIT CSAIL, Cambridge, USA
1 shared publication - Yixuan Wang
California Institute of Technology
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 17 December 2025
- Published by American Physical Society (APS) in Physical Review X
- Vol. 15 (4)
Kolmogorov-Arnold Networks Meet Science
A major challenge of AI plus science lies in its inherent incompatibility: Today’s AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold networks (KANs) and science. The framework highlights KANs’ usage for three aspects of scientific discovery: identifying relevant features, revealing modular structures, and discovering symbolic formulas. The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs). We highlight major new functionalities in : (1) MultKAN, KANs with multiplication nodes, (2) kanpiler, a KAN compiler that compiles symbolic formulas into KANs; (3) tree converter, convert KANs (or any neural networks) into tree graphs. Based on these tools, we demonstrate KANs’ capability to discover various types of physical laws, including conserved quantities, Lagrangians, symmetries, and constitutive laws.
- 17 December 2025
- Published by American Physical Society (APS) in Physical Review X
- Vol. 15 (4)
Top Cited PapersOpen AccessKolmogorov-Arnold Networks Meet Science
A major challenge of AI plus science lies in its inherent incompatibility: Today’s AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold networks (KANs) and science. The framework highlights KANs’ usage for three aspects of scientific discovery: identifying relevant features, revealing modular structures, and discovering symbolic formulas. The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs). We highlight major new functionalities in : (1) MultKAN, KANs with multiplication nodes, (2) kanpiler, a KAN compiler that compiles symbolic formulas into KANs; (3) tree converter, convert KANs (or any neural networks) into tree graphs. Based on these tools, we demonstrate KANs’ capability to discover various types of physical laws, including conserved quantities, Lagrangians, symmetries, and constitutive laws.
- 10 February 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 111 (2) , 025303
Discovering candidates for integrable systems via backpropagation
Integrable partial differential equation (PDE) systems are of great interest in natural science, but are exceedingly rare and difficult to discover. To this end, we introduce OptPDE, a numerical approach that Optimizes PDEs' coefficients via automatic differentiation to maximize their number of conserved quantities, n_{CQ}, and thus discover candidates for integrable systems. The algorithm discovers four families of PDEs with at least one nontrivial conserved quantity. We analytically study one new candidate u_{t}=u_{x}^{3}, revealing its interesting properties. It is worth mentioning that our approach aims to discover systems with as many conserved quantities as possible, which does not guarantee integrability. Despite this limitation, our humble effort suggests that numerical algorithms that leverage automatic differentiation are potentially useful for discovering candidates for integrable systems.
- 10 February 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 111 (2) , 025303
Discovering candidates for integrable systems via backpropagation
Integrable partial differential equation (PDE) systems are of great interest in natural science, but are exceedingly rare and difficult to discover. To this end, we introduce OptPDE, a numerical approach that Optimizes PDEs' coefficients via automatic differentiation to maximize their number of conserved quantities, n_{CQ}, and thus discover candidates for integrable systems. The algorithm discovers four families of PDEs with at least one nontrivial conserved quantity. We analytically study one new candidate u_{t}=u_{x}^{3}, revealing its interesting properties. It is worth mentioning that our approach aims to discover systems with as many conserved quantities as possible, which does not guarantee integrability. Despite this limitation, our humble effort suggests that numerical algorithms that leverage automatic differentiation are potentially useful for discovering candidates for integrable systems.
- 6 May 2022
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 128 (18) , 180201
Machine Learning Hidden Symmetries
We present an automated method for finding hidden symmetries, defined as symmetries that become manifest only in a new coordinate system that must be discovered. Its core idea is to quantify asymmetry as violation of certain partial differential equations, and to numerically minimize such violation over the space of all invertible transformations, parametrized as invertible neural networks. For example, our method rediscovers the famous Gullstrand-Painlevé metric that manifests hidden translational symmetry in the Schwarzschild metric of nonrotating black holes, as well as Hamiltonicity, modularity, and other simplifying traits not traditionally viewed as symmetries.
- 6 May 2022
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 128 (18) , 180201
Machine Learning Hidden Symmetries
We present an automated method for finding hidden symmetries, defined as symmetries that become manifest only in a new coordinate system that must be discovered. Its core idea is to quantify asymmetry as violation of certain partial differential equations, and to numerically minimize such violation over the space of all invertible transformations, parametrized as invertible neural networks. For example, our method rediscovers the famous Gullstrand-Painlevé metric that manifests hidden translational symmetry in the Schwarzschild metric of nonrotating black holes, as well as Hamiltonicity, modularity, and other simplifying traits not traditionally viewed as symmetries.