Zhiqi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Zhiqi Li has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Bo Zhu
Georgia Institute of Technology, Atlanta, USA
12 shared publications - Duowen Chen
Georgia Institute of Technology, Atlanta, USA
11 shared publications - Jinjin He
Georgia Institute of Technology, Atlanta, USA
6 shared publications - Sinan Wang
Georgia Institute of Technology, Atlanta, USA
5 shared publications - Yuchen Sun
Georgia Institute of Technology, Atlanta, USA
5 shared publications - Junwei Zhou
Computer Science and Engineering University of Michigan Ann Arbor Michigan USA
4 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Unified Long-Short Flow Maps for Fast Generation
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessUnified Long-Short Flow Maps for Fast Generation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-20
Hamiltonian Two-Way Coupling of Nonlinear Waves and 3D Flows
Simulating large-scale free-surface flow by coupling a localized 3D fluid solver to a cheaper 2D surface model has long faced a mismatch in wave dynamics: efficient 2D wave models used in graphics are typically either linear or non-dispersive. These models are fast, simple, and accurate for calm, small-amplitude seas, but coupling them to strongly nonlinear 3D solvers produces visible reflections and artifacts at the 2D-3D interface. We address this problem by introducing a nonlinear and dispersive 2D wave model based on the canonical Zakharov formulation. Its Hamiltonian structure enables canonically consistent two-way coupling, allowing information to pass smoothly across the 2D-3D interface. Our 2D solver reduces mean wave-height error by factors of 1.7–5× relative to SWE, BEM, and Airy baselines while running more than 10 3 × faster than BEM; it achieves greater nonlinear accuracy and coupling fidelity than SWE and Airy, with minor losses in speed and stability. Coupling it with a 3D Navier-Stokes solver yields a full system that suppresses visible seam artifacts across a range of experiments, including dispersion-matching and Kelvin-wake tests, and runs over 4× faster than a full-domain GPU NB-FLIP simulation.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-20
Open AccessHamiltonian Two-Way Coupling of Nonlinear Waves and 3D Flows
Simulating large-scale free-surface flow by coupling a localized 3D fluid solver to a cheaper 2D surface model has long faced a mismatch in wave dynamics: efficient 2D wave models used in graphics are typically either linear or non-dispersive. These models are fast, simple, and accurate for calm, small-amplitude seas, but coupling them to strongly nonlinear 3D solvers produces visible reflections and artifacts at the 2D-3D interface. We address this problem by introducing a nonlinear and dispersive 2D wave model based on the canonical Zakharov formulation. Its Hamiltonian structure enables canonically consistent two-way coupling, allowing information to pass smoothly across the 2D-3D interface. Our 2D solver reduces mean wave-height error by factors of 1.7–5× relative to SWE, BEM, and Airy baselines while running more than 10 3 × faster than BEM; it achieves greater nonlinear accuracy and coupling fidelity than SWE and Airy, with minor losses in speed and stability. Coupling it with a 3D Navier-Stokes solver yields a full system that suppresses visible seam artifacts across a range of experiments, including dispersion-matching and Kelvin-wake tests, and runs over 4× faster than a full-domain GPU NB-FLIP simulation.
- Open Access
- 13 October 2026
- Published by Wiley in International Journal for Numerical Methods in Engineering
- Vol. 127 (20) , e70441
A Level Set Method on Particle Flow Maps
Accurate interface tracking is central to numerical simulations involving moving boundaries, including multiphase flows, free‐surface dynamics, phase‐change problems, and other interface‐driven processes in computational mechanics. Although, level set methods provide a flexible implicit representation of evolving interfaces, their grid‐based advection and reinitialization procedures often introduce numerical diffusion, volume loss, and degradation of thin or highly curved structures. This paper introduces a particle flow map level set (PFM‐LS) method that addresses these limitations by transporting interface geometry through particle‐carried bidirectional flow maps. In contrast to particle level set methods that use particles mainly as corrective markers, PFM‐LS uses particles as primary carriers of level‐set values, gradients, and Hessians within a narrow band around the interface. The method combines long‐range flow‐map transport, high‐order particle‐grid reconstruction, adaptive particle control, and a hybrid particle‐grid redistancing scheme to preserve both signed‐distance consistency and sub‐grid geometric features. Numerical benchmarks in two and three dimensions, including topology‐change tests, chamfer and Hausdorff shape‐error metrics, and coupling to an incompressible free‐surface flow solver, show that PFM‐LS achieves strong volume preservation, high shape fidelity, and near fourth‐order convergence, outperforming a broad range of existing level set and reference‐map‐based methods.
- 13 October 2026
- Published by Wiley in International Journal for Numerical Methods in Engineering
- Vol. 127 (20) , e70441
Open AccessA Level Set Method on Particle Flow Maps
Accurate interface tracking is central to numerical simulations involving moving boundaries, including multiphase flows, free‐surface dynamics, phase‐change problems, and other interface‐driven processes in computational mechanics. Although, level set methods provide a flexible implicit representation of evolving interfaces, their grid‐based advection and reinitialization procedures often introduce numerical diffusion, volume loss, and degradation of thin or highly curved structures. This paper introduces a particle flow map level set (PFM‐LS) method that addresses these limitations by transporting interface geometry through particle‐carried bidirectional flow maps. In contrast to particle level set methods that use particles mainly as corrective markers, PFM‐LS uses particles as primary carriers of level‐set values, gradients, and Hessians within a narrow band around the interface. The method combines long‐range flow‐map transport, high‐order particle‐grid reconstruction, adaptive particle control, and a hybrid particle‐grid redistancing scheme to preserve both signed‐distance consistency and sub‐grid geometric features. Numerical benchmarks in two and three dimensions, including topology‐change tests, chamfer and Hausdorff shape‐error metrics, and coupling to an incompressible free‐surface flow solver, show that PFM‐LS achieves strong volume preservation, high shape fidelity, and near fourth‐order convergence, outperforming a broad range of existing level set and reference‐map‐based methods.
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-13
A Few-Step Generative Model on Cumulative Flow Maps
We propose a unified, few-step generative modeling framework based on cumulative flow maps for long-range transport in probability space, inspired by flow-map techniques for physical transport and dynamics. At its core is a cumulative-flow abstraction that connects local, instantaneous updates with finite-time transport, enabling generative models to reason about global state transitions. This perspective yields a unified few-step framework built on cumulative transport and cumulative parameterization that applies broadly to existing diffusion- and flow-based models without being tied to a specific prediction instantiation. Our formulation supports few-step and even one-step generation while preserving synthesis quality, requiring only minimal changes to time embeddings and training objectives, and no increase in model capacity. We demonstrate its effectiveness across diverse tasks, including image generation, geometric distribution modeling, joint prediction, and SDF generation, with reduced inference cost.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-13
Open AccessA Few-Step Generative Model on Cumulative Flow Maps
We propose a unified, few-step generative modeling framework based on cumulative flow maps for long-range transport in probability space, inspired by flow-map techniques for physical transport and dynamics. At its core is a cumulative-flow abstraction that connects local, instantaneous updates with finite-time transport, enabling generative models to reason about global state transitions. This perspective yields a unified few-step framework built on cumulative transport and cumulative parameterization that applies broadly to existing diffusion- and flow-based models without being tied to a specific prediction instantiation. Our formulation supports few-step and even one-step generation while preserving synthesis quality, requiring only minimal changes to time embeddings and training objectives, and no increase in model capacity. We demonstrate its effectiveness across diverse tasks, including image generation, geometric distribution modeling, joint prediction, and SDF generation, with reduced inference cost.
- Open Access
- 10 February 2026
- Published by Elsevier in SSRN Electronic Journal
A Level Set Method on Particle Flow Maps
This paper introduces a Particle Flow Map Level Set (PFM-LS) method for highfidelity interface tracking. We store level-set values, gradients, and Hessians on particles concentrated in a narrow band around the interface, advecting them via bidirectional flow maps while using a conventional grid-based representation elsewhere. By interpreting the level set value as a 3-form and its gradient as a 1-form, PFM-LS achieves exceptional geometric fidelity during complex deformations and preserves sub-grid features that traditional methods cannot capture. Our dual-timescale approach utilizes long-range maps for values and gradients, with frequent reinitialization of short-range maps for the distortion-sensitive Hessian, alongside adaptive particle control that maintains sufficient density within the narrow band. We also develop a hybrid particle-grid quasi-Newton redistancing scheme that preserves finescale features while enforcing the signed-distance property. Benchmark comparisons in 2D and 3D demonstrate that PFM-LS achieves state-of-the-art volume preservation and shape fidelity against a broad range of existing level-set methods.
- 10 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Level Set Method on Particle Flow Maps
This paper introduces a Particle Flow Map Level Set (PFM-LS) method for highfidelity interface tracking. We store level-set values, gradients, and Hessians on particles concentrated in a narrow band around the interface, advecting them via bidirectional flow maps while using a conventional grid-based representation elsewhere. By interpreting the level set value as a 3-form and its gradient as a 1-form, PFM-LS achieves exceptional geometric fidelity during complex deformations and preserves sub-grid features that traditional methods cannot capture. Our dual-timescale approach utilizes long-range maps for values and gradients, with frequent reinitialization of short-range maps for the distortion-sensitive Hessian, alongside adaptive particle control that maintains sufficient density within the narrow band. We also develop a hybrid particle-grid quasi-Newton redistancing scheme that preserves finescale features while enforcing the signed-distance property. Benchmark comparisons in 2D and 3D demonstrate that PFM-LS achieves state-of-the-art volume preservation and shape fidelity against a broad range of existing level-set methods.
- Open Access
- 10 February 2026
- Published by Elsevier in SSRN Electronic Journal
An Impulse-formed Navier-Stokes Solver based on Long-range Particle Flow Maps
We present a particle–grid characteristic-mapping framework that extends long-range characteristic mapping from inviscid flows to general Navier–Stokes dynamics with viscosity, body forces, and complex boundaries. Unlike traditional grid-based and vorticity-centered characteristic methods, our method is built on the observation that particle trajectories naturally provide the long-range flow map, enabling geometric quantities and their gradients to be transported in a direct and effective manner. We identify the impulse, the gauge variable of the velocity field, as the primary quantity mapped along characteristics while remaining compatible with standard velocity-based incompressible solvers. Using the 1-form representation of the impulse equation, we derive an integral formulation that decomposes the impulse evolution into a component transported geometrically along the particle flow map and a complementary component generated by viscosity and body forces evaluated through path integrals accumulated along particle trajectories. These components together yield a unified characteristic-mapping solver capable of handling incompressible Navier–Stokes flows with viscosity and body forces while maintaining the accuracy and geometric fidelity of characteristic transport.
- 10 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAn Impulse-formed Navier-Stokes Solver based on Long-range Particle Flow Maps
We present a particle–grid characteristic-mapping framework that extends long-range characteristic mapping from inviscid flows to general Navier–Stokes dynamics with viscosity, body forces, and complex boundaries. Unlike traditional grid-based and vorticity-centered characteristic methods, our method is built on the observation that particle trajectories naturally provide the long-range flow map, enabling geometric quantities and their gradients to be transported in a direct and effective manner. We identify the impulse, the gauge variable of the velocity field, as the primary quantity mapped along characteristics while remaining compatible with standard velocity-based incompressible solvers. Using the 1-form representation of the impulse equation, we derive an integral formulation that decomposes the impulse evolution into a component transported geometrically along the particle flow map and a complementary component generated by viscosity and body forces evaluated through path integrals accumulated along particle trajectories. These components together yield a unified characteristic-mapping solver capable of handling incompressible Navier–Stokes flows with viscosity and body forces while maintaining the accuracy and geometric fidelity of characteristic transport.
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
An Adjoint Method for Differentiable Fluid Simulation on Flow Maps
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessAn Adjoint Method for Differentiable Fluid Simulation on Flow Maps
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2186-2199
Improving Model Fusion by Training-Time Neuron Alignment With Fixed Neuron Anchors
Model fusion aims to integrate several deep neural network (DNN) models’ knowledge into one by fusing parameters, and it has promising applications, such as improving the generalization of foundation models and parameter averaging in federated learning. However, models under different settings (data, hyperparameter, etc.) have diverse neuron permutations; in other words, from the perspective of loss landscape, they reside in different loss basins, thus hindering model fusion performances. To alleviate this issue, previous studies highlighted the role of permutation invariance and have developed methods to find correct network permutations for neuron alignment after training. Orthogonal to previous attempts, this paper studies training-time neuron alignment, improving model fusion without the need for post-matching. Training-time alignment is cheaper than post-alignment and is applicable in various model fusion scenarios. Starting from fundamental hypotheses and theorems, a simple yet lossless algorithm called TNA-PFN is introduced. TNA-PFN utilizes partially fixed neuron weights as anchors to reduce the potential of training-time permutations, and it is empirically validated in reducing the barriers of linear mode connectivity and multi-model fusion. It is also validated that TNA-PFN can improve the fusion of pretrained models under the setting of model soup (vision transformers) and ColD fusion (pretrained language models). Based on TNA-PFN, two federated learning methods, FedPFN and FedPNU, are proposed, showing the prospects of training-time neuron alignment. FedPFN and FedPNU reach state-of-the-art performances in federated learning under heterogeneous settings and can be compatible with the server-side algorithm.
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2186-2199
Improving Model Fusion by Training-Time Neuron Alignment With Fixed Neuron Anchors
Model fusion aims to integrate several deep neural network (DNN) models’ knowledge into one by fusing parameters, and it has promising applications, such as improving the generalization of foundation models and parameter averaging in federated learning. However, models under different settings (data, hyperparameter, etc.) have diverse neuron permutations; in other words, from the perspective of loss landscape, they reside in different loss basins, thus hindering model fusion performances. To alleviate this issue, previous studies highlighted the role of permutation invariance and have developed methods to find correct network permutations for neuron alignment after training. Orthogonal to previous attempts, this paper studies training-time neuron alignment, improving model fusion without the need for post-matching. Training-time alignment is cheaper than post-alignment and is applicable in various model fusion scenarios. Starting from fundamental hypotheses and theorems, a simple yet lossless algorithm called TNA-PFN is introduced. TNA-PFN utilizes partially fixed neuron weights as anchors to reduce the potential of training-time permutations, and it is empirically validated in reducing the barriers of linear mode connectivity and multi-model fusion. It is also validated that TNA-PFN can improve the fusion of pretrained models under the setting of model soup (vision transformers) and ColD fusion (pretrained language models). Based on TNA-PFN, two federated learning methods, FedPFN and FedPNU, are proposed, showing the prospects of training-time neuron alignment. FedPFN and FedPNU reach state-of-the-art performances in federated learning under heterogeneous settings and can be compatible with the server-side algorithm.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1659-1670
FedGuCci: Making Local Models More Connected in Landscape for Federated Learning
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1659-1670
Open AccessFedGuCci: Making Local Models More Connected in Landscape for Federated Learning
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-12
Clebsch Gauge Fluid on Particle Flow Maps
We propose a novel gauge fluid solver that evolves Clebsch wave functions on particle flow maps (PFMs). The key insight underlying our work is that particle flow maps exhibit superior performance in transporting point elements—such as Clebsch components—compared to line and surface elements, which were the focus of previous methods relying on impulse and vortex gauge variables for flow maps. Our Clebsch PFM method incorporates three main contributions: a novel gauge transformation enabling accurate transport of wave functions on particle flow maps, an enhanced velocity reconstruction method for coarse grids, and a PFM-based simulation framework designed to better preserve fine-scale flow structures. We validate the Clebsch PFM method through a wide range of benchmark tests and simulation examples, ranging from leapfrogging vortex rings and vortex reconnections to Kelvin-Helmholtz instabilities, demonstrating that our method outperforms its impulse- or vortex-based counterparts on particle flow maps, particularly in preserving and evolving small-scale features.
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-12
Open AccessClebsch Gauge Fluid on Particle Flow Maps
We propose a novel gauge fluid solver that evolves Clebsch wave functions on particle flow maps (PFMs). The key insight underlying our work is that particle flow maps exhibit superior performance in transporting point elements—such as Clebsch components—compared to line and surface elements, which were the focus of previous methods relying on impulse and vortex gauge variables for flow maps. Our Clebsch PFM method incorporates three main contributions: a novel gauge transformation enabling accurate transport of wave functions on particle flow maps, an enhanced velocity reconstruction method for coarse grids, and a PFM-based simulation framework designed to better preserve fine-scale flow structures. We validate the Clebsch PFM method through a wide range of benchmark tests and simulation examples, ranging from leapfrogging vortex rings and vortex reconnections to Kelvin-Helmholtz instabilities, demonstrating that our method outperforms its impulse- or vortex-based counterparts on particle flow maps, particularly in preserving and evolving small-scale features.