Liwei Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liwei Wang has a total of 551 co-authors. Here are the top co-authors by number of shared publications:
- Di He
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China
30 shared publications - Hongfang Liu
Department of Quantitative and Systems Health Sciences, University of Texas at Austin Dell Medical School, Austin, TX 78712, USA
18 shared publications - Andrew Wen
McWilliams School of Biomedical Informatics, UTHealth Houston, Houston, USA
15 shared publications - Sijia Liu
Michigan State University
11 shared publications Ruichen Li
Bytedance
10 shared publications- Tie-Yan Liu
Zhongguancun Academy, Beijing, China
10 shared publications
Latest Publications
- Open Access
- 24 October 2026
- Published by Springer Nature in Nature Communications
Spin-adapted neural network wavefunctions in real space
- 24 October 2026
- Published by Springer Nature in Nature Communications
Open AccessSpin-adapted neural network wavefunctions in real space
- Open Access
- 21 October 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 11000
Author Correction: Solving the Hubbard model with neural quantum states
- 21 October 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 11000
Open AccessAuthor Correction: Solving the Hubbard model with neural quantum states
- Open Access
- 6 October 2026
- Published by American Physical Society (APS) in PRX Intelligence
- Vol. 1 (2) , 023001
Pareto Frontier of Neural Quantum States: Scalable, Affordable, and Accurate Convolutional Backflow for Strongly Correlated Lattice Fermions
The recent development of Neural Quantum States (NQS) has established them as one of the most accurate methods for studying strongly correlated many-fermion systems, outperforming existing many-body approaches for large systems. However, NQS calculations are currently highly resource intensive. In this work, we introduce an improved Pareto frontier of efficiency and accuracy for NQS in the simulation of strongly correlated lattice fermions. This frontier is defined by two complementary backflow-related architectures: the Sparse Convolutional Ansatz for Lattice Electrons (SCALE), which achieves high computational efficiency, and the Accurate Convolutional ansatz for lattice Electrons (ACE), which delivers high variational accuracy, based on benchmark results on the Hubbard model and the t – J model on large lattice sizes. SCALE utilizes a tailored convolutional design to enable an efficient local update based on the low-rank update of determinants. This structure reduces the computational scaling from O ( N 4 ) to O ( N 3 ) in backflow methods, resulting in a practical speedup exceeding 40 × in our test cases while retaining accurate variational accuracy. As an application, we study the 1 / 8 -doped pure Hubbard model up to size 32 × 32 and find no significant energy difference between the horizontal and vertical unit-filled stripe states, in contrast to the half-filled stripe state when next-nearest-neighbor hoppings are included. ACE, conversely, employs a deep convolutional stack to maximize expressive power, achieving high accuracy on large systems. We perform extensive benchmark calculations on the Hubbard and t – J models with the two architectures. On the challenging repulsive Hubbard model, SCALE achieves variational energies competitive with leading methods at a fraction of the computational cost. Meanwhile, ACE achieves lower variational energies than previously reported results while requiring only one-sixth of the run-time for system size 16 × 4 . These NQS approaches provide , , and tools for exploring the rich physics of strongly correlated fermionic systems.
- 6 October 2026
- Published by American Physical Society (APS) in PRX Intelligence
- Vol. 1 (2) , 023001
Open AccessPareto Frontier of Neural Quantum States: Scalable, Affordable, and Accurate Convolutional Backflow for Strongly Correlated Lattice Fermions
The recent development of Neural Quantum States (NQS) has established them as one of the most accurate methods for studying strongly correlated many-fermion systems, outperforming existing many-body approaches for large systems. However, NQS calculations are currently highly resource intensive. In this work, we introduce an improved Pareto frontier of efficiency and accuracy for NQS in the simulation of strongly correlated lattice fermions. This frontier is defined by two complementary backflow-related architectures: the Sparse Convolutional Ansatz for Lattice Electrons (SCALE), which achieves high computational efficiency, and the Accurate Convolutional ansatz for lattice Electrons (ACE), which delivers high variational accuracy, based on benchmark results on the Hubbard model and the t – J model on large lattice sizes. SCALE utilizes a tailored convolutional design to enable an efficient local update based on the low-rank update of determinants. This structure reduces the computational scaling from O ( N 4 ) to O ( N 3 ) in backflow methods, resulting in a practical speedup exceeding 40 × in our test cases while retaining accurate variational accuracy. As an application, we study the 1 / 8 -doped pure Hubbard model up to size 32 × 32 and find no significant energy difference between the horizontal and vertical unit-filled stripe states, in contrast to the half-filled stripe state when next-nearest-neighbor hoppings are included. ACE, conversely, employs a deep convolutional stack to maximize expressive power, achieving high accuracy on large systems. We perform extensive benchmark calculations on the Hubbard and t – J models with the two architectures. On the challenging repulsive Hubbard model, SCALE achieves variational energies competitive with leading methods at a fraction of the computational cost. Meanwhile, ACE achieves lower variational energies than previously reported results while requiring only one-sixth of the run-time for system size 16 × 4 . These NQS approaches provide , , and tools for exploring the rich physics of strongly correlated fermionic systems.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10785-10794
MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10785-10794
Open AccessMammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis
- 10 July 2026
- Published by Springer Nature in Nature Computational Science
- Vol. 6 (9) , 1005-1014
Empowering neural network-based quantum Monte Carlo with local pseudopotentials
Neural network-based quantum Monte Carlo (NNQMC), an emerging method for solving many-body quantum systems with high accuracy, has been mainly applied to small systems owing to demanding computation requirements. Here we introduce a framework based on local pseudopotentials to break through such limitation, improving the computational efficiency and scalability of NNQMC. The incorporation of local pseudopotentials reduces the number of electrons treated in neural network and also achieves better relative energy accuracy than all electron NNQMC calculations for complex systems. This counterintuitive outcome is made possible by the distinctive characteristics inherent to NNQMC. Notably, by avoiding costly integration terms, this approach is also substantially more efficient than its widely used semilocal counterparts. Our approach enables the reliable treatment of large and challenging systems, such as the \({\text{Fe}}_{4}{\text{S}}_{4}{({\text{SCH}}_{3})}_{4}\) iron–sulfur cluster. Overall, our findings demonstrate that the synergy between NNQMC and local pseudopotentials substantially expands the scope of accurate ab initio calculations.- 10 July 2026
- Published by Springer Nature in Nature Computational Science
- Vol. 6 (9) , 1005-1014
Empowering neural network-based quantum Monte Carlo with local pseudopotentials
Neural network-based quantum Monte Carlo (NNQMC), an emerging method for solving many-body quantum systems with high accuracy, has been mainly applied to small systems owing to demanding computation requirements. Here we introduce a framework based on local pseudopotentials to break through such limitation, improving the computational efficiency and scalability of NNQMC. The incorporation of local pseudopotentials reduces the number of electrons treated in neural network and also achieves better relative energy accuracy than all electron NNQMC calculations for complex systems. This counterintuitive outcome is made possible by the distinctive characteristics inherent to NNQMC. Notably, by avoiding costly integration terms, this approach is also substantially more efficient than its widely used semilocal counterparts. Our approach enables the reliable treatment of large and challenging systems, such as the \({\text{Fe}}_{4}{\text{S}}_{4}{({\text{SCH}}_{3})}_{4}\) iron–sulfur cluster. Overall, our findings demonstrate that the synergy between NNQMC and local pseudopotentials substantially expands the scope of accurate ab initio calculations.- Open Access
- 22 June 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Solving the Hubbard model with neural quantum states
The rapid development of neural quantum states (NQS) has established it as a promising framework for studying quantum many-body systems. In this work, by leveraging the transformer-based architectures and developing efficient optimization algorithms, we achieve the state-of-the-art results for the doped two-dimensional (2D) Hubbard model, arguably the minimum model for high-Tc superconductivity. Interestingly, we find different attention heads in the NQS ansatz can directly encode correlations at different scales, making it capable of capturing long-range correlations in strongly correlated systems. With these advances, we find evidence for the half-filled stripe in the ground state of 2D Hubbard model with the next nearest neighboring hopping, consistent with experimental observations in cuprates. Our work establishes NQS as a powerful tool for solving challenging many-fermions systems.
- 22 June 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessSolving the Hubbard model with neural quantum states
The rapid development of neural quantum states (NQS) has established it as a promising framework for studying quantum many-body systems. In this work, by leveraging the transformer-based architectures and developing efficient optimization algorithms, we achieve the state-of-the-art results for the doped two-dimensional (2D) Hubbard model, arguably the minimum model for high-Tc superconductivity. Interestingly, we find different attention heads in the NQS ansatz can directly encode correlations at different scales, making it capable of capturing long-range correlations in strongly correlated systems. With these advances, we find evidence for the half-filled stripe in the ground state of 2D Hubbard model with the next nearest neighboring hopping, consistent with experimental observations in cuprates. Our work establishes NQS as a powerful tool for solving challenging many-fermions systems.
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2918-2926
Semantic-Anchored Multi-State Retrieval for Robust 3D Perception
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2918-2926
Open AccessSemantic-Anchored Multi-State Retrieval for Robust 3D Perception
- 7 April 2026
- Published by Springer Nature in Nature Biomedical Engineering
A foundation generative model for breast ultrasound image analysis
Foundation models have emerged as powerful tools for addressing various tasks in clinical settings. However, their potential development for breast ultrasound analysis remains untapped. Here we present BUSGen, the first foundation generative model designed for breast ultrasound image analysis. Pretrained on over 3.5 million breast ultrasound images, BUSGen has acquired extensive knowledge of breast structures, pathological features and clinical variations. With few-shot adaptation, BUSGen can generate repositories of realistic and informative task-specific data, facilitating the development of models for a wide range of downstream tasks. Extensive experiments highlight BUSGen's exceptional adaptability, significantly exceeding real-data-trained foundation models in breast cancer screening, diagnosis and prognosis. In breast cancer early diagnosis, our approach outperformed all board-certified radiologists (n = 9), achieving an average sensitivity improvement of 16.5% (P < 0.0001). In addition, we characterized the scaling effect of using synthetic data. Finally, BUSGen enabled de-identified data sharing, making progress forward in secure medical data utilization.
- 7 April 2026
- Published by Springer Nature in Nature Biomedical Engineering
A foundation generative model for breast ultrasound image analysis
Foundation models have emerged as powerful tools for addressing various tasks in clinical settings. However, their potential development for breast ultrasound analysis remains untapped. Here we present BUSGen, the first foundation generative model designed for breast ultrasound image analysis. Pretrained on over 3.5 million breast ultrasound images, BUSGen has acquired extensive knowledge of breast structures, pathological features and clinical variations. With few-shot adaptation, BUSGen can generate repositories of realistic and informative task-specific data, facilitating the development of models for a wide range of downstream tasks. Extensive experiments highlight BUSGen's exceptional adaptability, significantly exceeding real-data-trained foundation models in breast cancer screening, diagnosis and prognosis. In breast cancer early diagnosis, our approach outperformed all board-certified radiologists (n = 9), achieving an average sensitivity improvement of 16.5% (P < 0.0001). In addition, we characterized the scaling effect of using synthetic data. Finally, BUSGen enabled de-identified data sharing, making progress forward in secure medical data utilization.
- Open Access
- 6 February 2026
- Published by Springer Nature in Scientific Data
- Vol. 13 (1)
A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories
Breast ultrasound (BUS) is an essential tool for diagnosing breast lesions, with millions of examinations per year. However, publicly available high-quality BUS benchmarks for AI development are limited in data scale and annotation richness. In this work, we present BUS-CoT, a BUS dataset for chain-of-thought (CoT) reasoning analysis, which contains 11,439 ultrasound images from 11,850 lesions and 4,838 patients, covering all 99 WHO-defined histopathology categories. For model training and evaluation, we provide a curated high-quality subset of 5,163 lesion-focused images annotated by experienced radiologists. To facilitate research on incentivizing CoT reasoning, we construct the reasoning processes based on observation, feature, diagnosis and pathology labels, annotated and verified by experienced experts. Moreover, by covering lesions of all histopathology types, we aim to facilitate robust AI systems in rare cases, which can be error-prone in clinical practice. The data and code are publicly available at https://doi.org/10.6084/m9.figshare.30838715.
- 6 February 2026
- Published by Springer Nature in Scientific Data
- Vol. 13 (1)
Open AccessA Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories
Breast ultrasound (BUS) is an essential tool for diagnosing breast lesions, with millions of examinations per year. However, publicly available high-quality BUS benchmarks for AI development are limited in data scale and annotation richness. In this work, we present BUS-CoT, a BUS dataset for chain-of-thought (CoT) reasoning analysis, which contains 11,439 ultrasound images from 11,850 lesions and 4,838 patients, covering all 99 WHO-defined histopathology categories. For model training and evaluation, we provide a curated high-quality subset of 5,163 lesion-focused images annotated by experienced radiologists. To facilitate research on incentivizing CoT reasoning, we construct the reasoning processes based on observation, feature, diagnosis and pathology labels, annotated and verified by experienced experts. Moreover, by covering lesions of all histopathology types, we aim to facilitate robust AI systems in rare cases, which can be error-prone in clinical practice. The data and code are publicly available at https://doi.org/10.6084/m9.figshare.30838715.
- Open Access
Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remain unclear in theory. We study Muon in a linear associative memory model with softmax retrieval and a hierarchical frequency spectrum over query-answer pairs, with and without label noise. In this setting, we show that Gradient Descent (GD) learns frequency components at highly imbalanced rates, leading to slow convergence bottlenecked by low-frequency components. In contrast, the Muon optimizer mitigates this imbalance, leading to faster and more uniform progress. Specifically, in the noiseless case, Muon achieves an exponential speedup over GD; in the noisy case with a power-decay frequency spectrum, we derive Muon's optimization scaling law and demonstrate its superior scaling efficiency over GD. Furthermore, we show that Muon can be interpreted as an implicit matrix preconditioner arising from adaptive task alignment and block-symmetric gradient structure. In contrast, the preconditioner with coordinate-wise sign operator could match Muon under oracle access to unknown task representations, which is infeasible for SignGD in practice. Experiments on synthetic long-tail classification and LLaMA-style pre-training corroborate the theory.
Open AccessMuon in Associative Memory Learning: Training Dynamics and Scaling Laws
Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remain unclear in theory. We study Muon in a linear associative memory model with softmax retrieval and a hierarchical frequency spectrum over query-answer pairs, with and without label noise. In this setting, we show that Gradient Descent (GD) learns frequency components at highly imbalanced rates, leading to slow convergence bottlenecked by low-frequency components. In contrast, the Muon optimizer mitigates this imbalance, leading to faster and more uniform progress. Specifically, in the noiseless case, Muon achieves an exponential speedup over GD; in the noisy case with a power-decay frequency spectrum, we derive Muon's optimization scaling law and demonstrate its superior scaling efficiency over GD. Furthermore, we show that Muon can be interpreted as an implicit matrix preconditioner arising from adaptive task alignment and block-symmetric gradient structure. In contrast, the preconditioner with coordinate-wise sign operator could match Muon under oracle access to unknown task representations, which is infeasible for SignGD in practice. Experiments on synthetic long-tail classification and LLaMA-style pre-training corroborate the theory.