arXiv subjects

Tianrun Gao

Publications and source records attributed to Tianrun Gao.

12 recordsLinked to original sources

arXiv2026

RealPDEBench: A Benchmark for Complex Physical Systems with Real-World Data

Predicting the evolution of complex physical systems remains a central problem in science and engineering. Despite rapid progress in scientific Machine Learning (ML) models, a critical bottleneck is the lack of expensive real-world data, resulting in most current models being trained and validated on simulated data. Beyond limiting the development and evaluation of scientific ML, this gap also hinders research into essential tasks such as sim-to-real transfer. We introduce RealPDEBench, the first benchmark for scientific ML that integrates real-world measurements with paired numerical simulations. RealPDEBench consists of five datasets, three tasks, eight metrics, and ten baselines. We first present five real-world measured datasets with paired simulated datasets across different complex physical systems. We further define three tasks, which allow comparisons between real-world and simulated data, and facilitate the development of methods to bridge the two. Moreover, we design eight evaluation metrics, spanning data-oriented and physics-oriented metrics, and finally benchmark ten representative baselines, including state-of-the-art models, pretrained PDE foundation models, and a traditional method. Experiments reveal significant discrepancies between simulated and real-world data, while showing that pretraining with simulated data consistently improves both accuracy and convergence. In this work, we hope to provide insights from real-world data, advancing scientific ML toward bridging the sim-to-real gap and real-world deployment. Our benchmark, datasets, and instructions are available at https://realpdebench.github.io/.

cs.LG↗

arXiv2026

HybridOM: Hybrid Physics-Based and Data-Driven Global Ocean Modeling with Efficient Spatial Downscaling

Global ocean modeling is vital for climate science but struggles to balance computational efficiency with accuracy. Traditional numerical solvers are accurate but computationally expensive, while pure deep learning approaches, though fast, often lack physical consistency and long-term stability. To address this, we introduce HybridOM, a framework integrating a lightweight, differentiable numerical solver as a skeleton to enforce physical laws, with a neural network as the flesh to correct subgrid-scale dynamics. To enable efficient high-resolution modeling, we further introduce a physics-informed regional downscaling mechanism based on flux gating. This design achieves the inference efficiency of AI-based methods while preserving the accuracy and robustness of physical models. Extensive experiments on the GLORYS12V1 and OceanBench dataset validate HybridOM's performance in two distinct regimes: long-term subseasonal-to-seasonal simulation and short-term operational forecasting coupled with the FuXi-2.0 weather model. Results demonstrate that HybridOM achieves state-of-the-art accuracy while strictly maintaining physical consistency, offering a robust solution for next-generation ocean digital twins. Our source code is available at https://github.com/ChiyodaMomo01/HybridOM.

physics.ao-ph↗

arXiv2026

GenCP: Towards Generative Modeling Paradigm of Coupled Physics

Real-world physical systems are inherently complex, often involving the coupling of multiple physics, making their simulation both highly valuable and challenging. Many mainstream approaches face challenges when dealing with decoupled data. Besides, they also suffer from low efficiency and fidelity in strongly coupled spatio-temporal physical systems. Here we propose GenCP, a novel and elegant generative paradigm for coupled multiphysics simulation. By formulating coupled-physics modeling as a probability modeling problem, our key innovation is to integrate probability density evolution in generative modeling with iterative multiphysics coupling, thereby enabling training on data from decoupled simulation and inferring coupled physics during sampling. We also utilize operator-splitting theory in the space of probability evolution to establish error controllability guarantees for this "conditional-to-joint" sampling scheme. We evaluate our paradigm on a synthetic setting and three challenging multi-physics scenarios to demonstrate both principled insight and superior application performance of GenCP. Code is available at this repo: github.com/AI4Science-WestlakeU/GenCP.

cs.LG↗

arXiv2025

BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction

Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrated reasoning under strict physical constraints. While modern LLMs possess broad knowledge and strong reasoning capabilities that make them promising candidates for this domain, their construction competencies remain largely unevaluated. To address this gap, we introduce BuildArena, the first physics-aligned interactive benchmark designed for language-driven engineering construction. Technically, it contributes to the community in two aspects: (1) an extendable task design strategy spanning static and dynamic mechanics across multiple difficulty tiers; (2) a 3D Spatial Geometric Computation Library for supporting construction based on language instructions. On nine frontier LLMs and three additional open-weight models, BuildArena comprehensively evaluates their capabilities for language-driven and physics-grounded construction automation. We release the code at https://github.com/AI4Science-WestlakeU/BuildArena to benefit construction automation in engineering applications.

cs.AI↗

arXiv2025

Towards Group Fairness with Multiple Sensitive Attributes in Federated Foundation Models

The deep integration of foundation models (FM) with federated learning (FL) enhances personalization and scalability for diverse downstream tasks, making it crucial in sensitive domains like healthcare. Achieving group fairness has become an increasingly prominent issue in the era of federated foundation models (FFMs), since biases in sensitive attributes might lead to inequitable treatment for under-represented demographic groups. Existing studies mostly focus on achieving fairness with respect to a single sensitive attribute. This renders them unable to provide clear interpretability of dependencies among multiple sensitive attributes which is required to achieve group fairness. Our paper takes the first attempt towards a causal analysis of the relationship between group fairness across various sensitive attributes in the FFM. We extend the FFM structure to trade off multiple sensitive attributes simultaneously and quantify the causal effect behind the group fairness through causal discovery and inference. Extensive experiments validate its effectiveness, offering insights into interpretability towards building trustworthy and fair FFM systems.

cs.LG↗

arXiv2025

SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning

Federated Learning (FL) is a collaborative machine learning paradigm for training models on local sensitive data with privacy protection. Pre-trained transformer-based models have emerged as useful foundation models (FMs) to be fine-tuned for a wide range of downstream tasks. However, large-scale pre-trained models make it challenging for traditional FL due to high communication overhead in the resource-constrained IoT. This has inspired the field of parameter-efficient fine-tuning (PEFT) research. Existing PEFT methods attempt to optimize model performance at the given dropout level. Such an approach places the burden on human users to find a dropout rate that provides a satisfactory level of performance through trial-and-error, which is time consuming and resource intensive. To address this limitation, we propose the Step-wise Parameter Dropout for Continual Federated Learning (SPD-CFL) approach. Instead of pre-defining a desired dropout rate, it allows users to specify the target level of performance and then attempts to find the most suitable dropout rate for the given FL model. Specifically, on the server side, SPD-CFL drops trainable parameters in a stepwise manner to improve communication efficiency by reducing the rank of low-rank adaptation (LoRA). The sensitivity-based gradient consistency (SGC) measure is designed to facilitate the adaptive adjustment of parameter dropout. In addition, SPD-CFL introduces continual learning (CL) on the client side to mitigate performance degradation due to the inconsistent optima with distinct parameter dropout rates under heterogeneous FL. Extensive experiments on the public benchmark dataset CIFAR-10 and a real-world medical Face dataset demonstrate significant superiority of SPD-CFL over state-of-the-art methods. Compared to the best-performing baseline, it achieves a 2.07% higher test AUC while reducing communication overhead by 29.53%.

cs.LG↗

arXiv2025

EqCollide: Equivariant and Collision-Aware Deformable Objects Neural Simulator

Simulating collisions of deformable objects is a fundamental yet challenging task due to the complexity of modeling solid mechanics and multi-body interactions. Existing data-driven methods often suffer from lack of equivariance to physical symmetries, inadequate handling of collisions, and limited scalability. Here we introduce EqCollide, the first end-to-end equivariant neural fields simulator for deformable objects and their collisions. We propose an equivariant encoder to map object geometry and velocity into latent control points. A subsequent equivariant Graph Neural Network-based Neural Ordinary Differential Equation models the interactions among control points via collision-aware message passing. To reconstruct velocity fields, we query a neural field conditioned on control point features, enabling continuous and resolution-independent motion predictions. Experimental results on 2D and 3D scenarios show that EqCollide achieves accurate, stable, and scalable simulations across diverse object configurations. It achieves $24.34\%$ to $57.62\%$ lower rollout MSE, even compared with the best-performing baseline model. Furthermore, EqCollide could generalize to more colliding objects and extended temporal horizons, and stay robust to input transformed with group action. Code is available at: https://github.com/AI4Science-WestlakeU/EqCollide

cs.LG↗

arXiv2025

ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation

Recently, LLM agents have made rapid progress in improving their programming capabilities. However, existing benchmarks lack the ability to automatically evaluate from users' perspective, and also lack the explainability of the results of LLM agents' code generation capabilities. Thus, we introduce ProjectEval, a new benchmark for LLM agents project-level code generation's automated evaluation by simulating user interaction. ProjectEval is constructed by LLM with human reviewing. It has three different level inputs of natural languages or code skeletons. ProjectEval can evaluate the generated projects by user interaction simulation for execution, and by code similarity through existing objective indicators. Through ProjectEval, we find that systematic engineering project code, overall understanding of the project and comprehensive analysis capability are the keys for LLM agents to achieve practical projects. Our findings and benchmark provide valuable insights for developing more effective programming agents that can be deployed in future real-world production.

cs.SE↗

arXiv2023

A new smoothed particle hydrodynamics method based on high-order moving-least-square targeted essentially non-oscillatory scheme for compressible flows

In this study, we establish a hybrid high-order smoothed particle hydrodynamics (SPH) framework (MLS-TENO-SPH) for compressible flows with discontinuities, which is able to achieve genuine high-order convergence in smooth regions and also capture discontinuities well in non-smooth regions. The framework can be either fully Lagrangian, Eulerian or realizing arbitary-Lagrangian-Eulerian (ALE) feature enforcing the isotropic particle distribution in specific cases. In the proposed framework, the computational domain is divided into smooth regions and non-smooth regions, and these two regions are determined by a strong scale separation strategy in the targeted essentially non-oscillatory (TENO) scheme. In smooth regions, the moving-least-square (MLS) approximation is used for evaluating high-order derivative operator, which is able to realize genuine high-order construction; in non-smooth regions, the new TENO scheme based on Vila's framework with several new improvements will be deployed to capture discontinuities and high-wavenumber flow scales with low numerical dissipation. The present MLS-TENO-SPH method is validated with a set of challenging cases based on the Eulerian, Lagrangian or ALE framework. Numerical results demonstrate that the MLS-TENO-SPH method features lower numerical dissipation and higher efficiency than the conventional method, and can restore genuine high-order accuracy in smooth regions. Overall, the proposed framework serves as a new exploration in high-order SPH methods, which are potential for compressible flow simulations with shockwaves.

physics.flu-dyn↗

arXiv2022

Self adaptive global-local feature enhancement for radiology report generation

Automated radiology report generation aims at automatically generating a detailed description of medical images, which can greatly alleviate the workload of radiologists and provide better medical services to remote areas. Most existing works pay attention to the holistic impression of medical images, failing to utilize important anatomy information. However, in actual clinical practice, radiologists usually locate important anatomical structures, and then look for signs of abnormalities in certain structures and reason the underlying disease. In this paper, we propose a novel framework AGFNet to dynamically fuse the global and anatomy region feature to generate multi-grained radiology report. Firstly, we extract important anatomy region features and global features of input Chest X-ray (CXR). Then, with the region features and the global features as input, our proposed self-adaptive fusion gate module could dynamically fuse multi-granularity information. Finally, the captioning generator generates the radiology reports through multi-granularity features. Experiment results illustrate that our model achieved the state-of-the-art performance on two benchmark datasets including the IU X-Ray and MIMIC-CXR. Further analyses also prove that our model is able to leverage the multi-grained information from radiology images and texts so as to help generate more accurate reports.

cs.CV↗

arXiv2022

Multi-level adaptive particle refinement method with large refinement scale ratio and new free-surface detection algorithm for complex fluid-structure interaction problems

Fluid-Structure Interaction (FSI) is a crucial problem in ocean engineering. The smoothed particle hydrodynamics (SPH) method has been employed recently for FSI problems in light of its Lagrangian nature and its advantage in handling multi-physics problems. The efficiency of SPH can be greatly improved with the Adaptive Particle Refinement (APR) method, which refines particles in the regions of interest while deploying coarse particles in the left areas. In this study, the APR method is further improved by developing several new algorithms. Firstly, a new particle refinement strategy with the refinement scale ratio of 4 is employed for multi-level resolutions, and this dramatically decreases the computational costs compared to the standard APR method. Secondly, the regularized transition sub-zone is deployed to render an isotropic particle distribution, which makes the solutions between the refinement zone and the non-refinement zone smoother and consequently results in a more accurate prediction. Thirdly, for complex FSI problems with free surface, a new free-surface detection method based on the Voronoi diagram is proposed, and the performance is validated in comparison to the conventional method. The improved APR method is then applied to a set of challenging FSI cases. Numerical simulations demonstrate that the results from the refinement with scale ratio 4 are consistent with other studies and experimental data, and also agree well with those employing the refinement scale ratio 2. A significant reduction in the computational time is observed for all the considered cases. Overall, the improved APR method with a large refinement scale ratio and the new free-surface detection strategy shows great potential in simulating complex FSI problems efficiently and accurately.

physics.flu-dyn↗

arXiv2022

A Block-based Adaptive Particle Refinement SPH Method for Fluid-Structure Interaction Problems

The multi-resolution method, e.g., the Adaptive Particle Refinement (APR) method, has been developed to increase the local particle resolution and therefore the solution quality within a pre-defined refinement zone instead of using a globally uniform resolution for Smoothed Particle Hydrodynamics (SPH). However, sometimes, the targeted zone of interest can be varying, and the corresponding topology is very complex, thus the conventional APR method is not able to track these characteristics adaptively. In this study, a novel Block-based Adaptive Particle Refinement (BAPR) method is developed, which is able to provide the necessary local refinement flexibly for any targeted characteristic, and track it adaptively. In BAPR, the so-called activation status of the block array defines the refinement regions, where the transition and activated zones are determined accordingly. A regularization method for the generated particles in the newly activated blocks is developed to render an isotropic distribution of these new particles. The proposed method has been deployed for simulating Fluid-Structure Interaction (FSI) problems. A set of 2D FSI cases have been simulated with the proposed BAPR method, and the performance of the BAPR method is quantified and validated comprehensively. In a word, the BAPR method is viable and potential for complex multi-resolution FSI simulations by tracking any targeted characteristic of interest.

physics.flu-dyn↗