Yadi Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yadi Cao has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
Chenfanfu Jiang
University of California, Los Angeles, Los Angeles, USA
2 shared publications- Minchen Li
Carnegie Mellon University
2 shared publications - Yin Yang
University of Utah, Salt Lake City, USA
2 shared publications - Brian Sammuli
General Atomics 1 , San Diego, California 92121
1 shared publication - Chenfanfu Jiang
University of California Los Angeles
1 shared publication Demetri Terzopoulos
University of California, Los Angeles, Los Angeles, USA
1 shared publication
Latest Publications
- Open Access
- 19 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (6) , 1-29
DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations
Molecular dynamics (MD) simulations are crucial for understanding and predicting the behavior of molecular systems in biology and chemistry. Yet, predicting long-term dynamics is still challenging. On one hand, it is hard to employ small-timestep models for long-term prediction, due to substantial rollout errors accumulated at each step, not to mention their extremely high time complexity due to the large number of rollout steps. On the other hand, it is hard to use large-timestep models to achieve high accuracy, due to their inability to capture subtle details of the dynamics. To bridge this dichotomy, we propose DoMiNO , a multi-scale framework that decomposes MD dynamics into several temporal resolutions, each governed by a neural graph ordinary differential equation (GraphODE) and are adaptively fused for final predictions. Concretely, DoMiNO operates through three key components: (1) an E(n)-equivariant graph neural network (EGNN) encoder that initializes latent states from a single observed molecular structure, maintaining SE(3) symmetries throughout; (2) a hierarchy of GraphODEs where each level captures scale-specific dynamics over normalized local time intervals, ranging from slow global motions to fast bond vibrations; and (3) an attention-based fusion module that adaptively combines multi-level predictions and reconstructs SE(3)-equivariant 3D coordinates. This design enables each hierarchical level to specialize in its characteristic timescale while preserving molecular symmetries. During inference, DoMiNO flexibly assembles predictions across different temporal resolutions, providing superior performance over both short-term and long-term dynamics. Empirical results on challenging MD benchmarks demonstrate that DoMiNO achieves significant improvements in prediction accuracy, particularly for molecules with pronounced timescale separation. The method exhibits significantly slower error growth over extended horizons compared to both single-scale baselines and state-of-the-art multi-step approaches. Our implementation is available at https://github.com/FrancoTSolis/DoMiNO-TKDD-Code .
- 19 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (6) , 1-29
Open AccessDoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations
Molecular dynamics (MD) simulations are crucial for understanding and predicting the behavior of molecular systems in biology and chemistry. Yet, predicting long-term dynamics is still challenging. On one hand, it is hard to employ small-timestep models for long-term prediction, due to substantial rollout errors accumulated at each step, not to mention their extremely high time complexity due to the large number of rollout steps. On the other hand, it is hard to use large-timestep models to achieve high accuracy, due to their inability to capture subtle details of the dynamics. To bridge this dichotomy, we propose DoMiNO , a multi-scale framework that decomposes MD dynamics into several temporal resolutions, each governed by a neural graph ordinary differential equation (GraphODE) and are adaptively fused for final predictions. Concretely, DoMiNO operates through three key components: (1) an E(n)-equivariant graph neural network (EGNN) encoder that initializes latent states from a single observed molecular structure, maintaining SE(3) symmetries throughout; (2) a hierarchy of GraphODEs where each level captures scale-specific dynamics over normalized local time intervals, ranging from slow global motions to fast bond vibrations; and (3) an attention-based fusion module that adaptively combines multi-level predictions and reconstructs SE(3)-equivariant 3D coordinates. This design enables each hierarchical level to specialize in its characteristic timescale while preserving molecular symmetries. During inference, DoMiNO flexibly assembles predictions across different temporal resolutions, providing superior performance over both short-term and long-term dynamics. Empirical results on challenging MD benchmarks demonstrate that DoMiNO achieves significant improvements in prediction accuracy, particularly for molecules with pronounced timescale separation. The method exhibits significantly slower error growth over extended horizons compared to both single-scale baselines and state-of-the-art multi-step approaches. Our implementation is available at https://github.com/FrancoTSolis/DoMiNO-TKDD-Code .
- Open Access
- 17 June 2026
- Published by IOP Publishing in Nuclear Fusion
- Vol. 66 (7) , 076031
TGLF-WINN: data-efficient deep learning surrogate for turbulent transport modeling in fusion
The trapped Gyro-Landau Fluid (TGLF) model provides fast, accurate predictions of turbulent transport in tokamaks, but whole device simulations requiring thousands of evaluations remain computationally expensive. Neural network (NN) surrogates offer accelerated inference with fully differentiable approximations that enable gradient-based coupling but typically require large training datasets to capture transport flux variations across plasma conditions, creating significant training burden and limiting applicability to expensive gyrokinetic simulations. We propose TGLF-WINN (Wavenumber-Informed NN) with three key innovations: (1) principled feature engineering that reduces target prediction range, simplifying the learning task; (2) physics-guided wavenumber-resolved regularization to improve generalization under sparse data; and (3) Bayesian active learning (BAL) to strategically select training samples based on model uncertainty, reducing data requirements while maintaining accuracy. TGLF-WINN is engineered for data-efficient and robust surrogate training. Feature tuning and wavenumber regularization together deliver a 12.5% relative RMSLE reduction over TGLF-NN when trained on the complete dataset; more importantly, under sparse, unfiltered training conditions (approximately 1 / 9 the full dataset size) these two ingredients yield an order-of-magnitude smaller RMSLE degradation than TGLF-NN, a robustness attributable to the wavenumber-informed regularization imposing a physics-guided constraint on per-mode flux contributions. Adding BAL on top, TGLF-WINN matches TGLF-NN’s full-data offline accuracy using only 25% of the training data, reaching RMSLE within 2.8% of TGLF-NN’s full-data baseline and within 4.3% of our own full-data result. We further demonstrate practicality in a downstream flux-matching workflow: the NN surrogate provides a 45 × speedup over TGLF while maintaining comparable reconstruction accuracy.
- 17 June 2026
- Published by IOP Publishing in Nuclear Fusion
- Vol. 66 (7) , 076031
Open AccessTGLF-WINN: data-efficient deep learning surrogate for turbulent transport modeling in fusion
The trapped Gyro-Landau Fluid (TGLF) model provides fast, accurate predictions of turbulent transport in tokamaks, but whole device simulations requiring thousands of evaluations remain computationally expensive. Neural network (NN) surrogates offer accelerated inference with fully differentiable approximations that enable gradient-based coupling but typically require large training datasets to capture transport flux variations across plasma conditions, creating significant training burden and limiting applicability to expensive gyrokinetic simulations. We propose TGLF-WINN (Wavenumber-Informed NN) with three key innovations: (1) principled feature engineering that reduces target prediction range, simplifying the learning task; (2) physics-guided wavenumber-resolved regularization to improve generalization under sparse data; and (3) Bayesian active learning (BAL) to strategically select training samples based on model uncertainty, reducing data requirements while maintaining accuracy. TGLF-WINN is engineered for data-efficient and robust surrogate training. Feature tuning and wavenumber regularization together deliver a 12.5% relative RMSLE reduction over TGLF-NN when trained on the complete dataset; more importantly, under sparse, unfiltered training conditions (approximately 1 / 9 the full dataset size) these two ingredients yield an order-of-magnitude smaller RMSLE degradation than TGLF-NN, a robustness attributable to the wavenumber-informed regularization imposing a physics-guided constraint on per-mode flux contributions. Adding BAL on top, TGLF-WINN matches TGLF-NN’s full-data offline accuracy using only 25% of the training data, reaching RMSLE within 2.8% of TGLF-NN’s full-data baseline and within 4.3% of our own full-data result. We further demonstrate practicality in a downstream flux-matching workflow: the NN surrogate provides a 45 × speedup over TGLF while maintaining comparable reconstruction accuracy.
- 23 July 2024
- Published by Springer Nature in Computational Mechanics
- Vol. 75 (2) , 655-678
Unstructured moving least squares material point methods: a stable kernel approach with continuous gradient reconstruction on general unstructured tessellations
- 23 July 2024
- Published by Springer Nature in Computational Mechanics
- Vol. 75 (2) , 655-678
Unstructured moving least squares material point methods: a stable kernel approach with continuous gradient reconstruction on general unstructured tessellations
- 14 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 30 (8) , 5596-5608
Augmented Incremental Potential Contact for Sticky Interactions
We introduce a variational formulation for simulating sticky interactions between elastoplastic solids. Our method brings a wider range of material behaviors into the reach of the Incremental Potential Contact (IPC) solver recently developed by [1]. Extending IPC requires several contributions. We first augment IPC with the classical Raous-Cangemi-Cocou (RCC) adhesion model. This allows us to robustly simulate the sticky interactions between arbitrary codimensional-0, 1, and 2 geometries. To enable user-friendly practical adoptions of our method, we further introduce a physically parametrized, easily controllable normal adhesion formulation based on the unsigned distance , which is fully compatible with IPC's barrier formulation. Furthermore, we propose a smoothly clamped tangential adhesion model that naturally models intricate behaviors including debonding. Lastly, we perform benchmark studies comparing our method with the classical models as well as real-world experimental results to demonstrate the efficacy of our method.
- 14 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 30 (8) , 5596-5608
Augmented Incremental Potential Contact for Sticky Interactions
We introduce a variational formulation for simulating sticky interactions between elastoplastic solids. Our method brings a wider range of material behaviors into the reach of the Incremental Potential Contact (IPC) solver recently developed by [1]. Extending IPC requires several contributions. We first augment IPC with the classical Raous-Cangemi-Cocou (RCC) adhesion model. This allows us to robustly simulate the sticky interactions between arbitrary codimensional-0, 1, and 2 geometries. To enable user-friendly practical adoptions of our method, we further introduce a physically parametrized, easily controllable normal adhesion formulation based on the unsigned distance , which is fully compatible with IPC's barrier formulation. Furthermore, we propose a smoothly clamped tangential adhesion model that naturally models intricate behaviors including debonding. Lastly, we perform benchmark studies comparing our method with the classical models as well as real-world experimental results to demonstrate the efficacy of our method.
- Open Access
- 13 May 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 41 (5) , 1-13
An Efficient B-Spline Lagrangian/Eulerian Method for Compressible Flow, Shock Waves, and Fracturing Solids
This study presents a new method for modeling the interaction between compressible flow, shock waves, and deformable structures, emphasizing destructive dynamics. Extending advances in time-splitting compressible flow and the Material Point Methods (MPM), we develop a hybrid Eulerian and Lagrangian/Eulerian scheme for monolithic flow-structure interactions. We adopt the second-order WENO scheme to advance the continuity equation. To stably resolve deforming boundaries with sub-cell particles, we propose a blending treatment of reflective and passable boundary conditions inspired by the theory of porous media. The strongly coupled velocity-pressure system is discretized with a new mixed-order finite element formulation employing B-spline shape functions. Shock wave propagation, temperature/density-induced buoyancy effects, and topology changes in solids are unitedly captured.
- 13 May 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 41 (5) , 1-13
Open AccessAn Efficient B-Spline Lagrangian/Eulerian Method for Compressible Flow, Shock Waves, and Fracturing Solids
This study presents a new method for modeling the interaction between compressible flow, shock waves, and deformable structures, emphasizing destructive dynamics. Extending advances in time-splitting compressible flow and the Material Point Methods (MPM), we develop a hybrid Eulerian and Lagrangian/Eulerian scheme for monolithic flow-structure interactions. We adopt the second-order WENO scheme to advance the continuity equation. To stably resolve deforming boundaries with sub-cell particles, we propose a blending treatment of reflective and passable boundary conditions inspired by the theory of porous media. The strongly coupled velocity-pressure system is discretized with a new mixed-order finite element formulation employing B-spline shape functions. Shock wave propagation, temperature/density-induced buoyancy effects, and topology changes in solids are unitedly captured.
- 1 September 2018
- Published by AIP Publishing in Physics of Fluids
- Vol. 30 (9) , 093605
A liquid plug moving in an annular pipe—Flow analysis
The flow in a liquid plug moving in an annular pipe is analytically solved. The interaction with the two concentric walls of the annular pipe results in two toroidal vortexes within the concentric plug. Focus is put on long plugs with aspect ratio β > 2, which have vortex circulation flow rates and volume ratio independent of the plug length. Based on the analytical results, correlations are derived for the circulation flow rates of the plug and each vortex and for the volume ratio of the two vortexes. Correlations are also developed for evaluating the radial transport of the plug flow. The friction factor for concentric plugs is a function of the aspect ratio and the radius ratio. For very long plugs with β ≫ 1, the friction factor approaches that of the fully developed continuous flow in the annular pipe.
- 1 September 2018
- Published by AIP Publishing in Physics of Fluids
- Vol. 30 (9) , 093605
A liquid plug moving in an annular pipe—Flow analysis
The flow in a liquid plug moving in an annular pipe is analytically solved. The interaction with the two concentric walls of the annular pipe results in two toroidal vortexes within the concentric plug. Focus is put on long plugs with aspect ratio β > 2, which have vortex circulation flow rates and volume ratio independent of the plug length. Based on the analytical results, correlations are derived for the circulation flow rates of the plug and each vortex and for the volume ratio of the two vortexes. Correlations are also developed for evaluating the radial transport of the plug flow. The friction factor for concentric plugs is a function of the aspect ratio and the radius ratio. For very long plugs with β ≫ 1, the friction factor approaches that of the fully developed continuous flow in the annular pipe.