Author name cluster

Hao Gao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2026 Short Paper

Fine-tuning Zero-shot Large Language Models for Patient-reported Outcomes (Student Abstract)

Yang Yan
Matthew W. Chen
Jiayi Lyu
Chen Zhao
Hao Gao
Zhong Chen

Radiotherapy (RT) is a cornerstone of cancer treatment. Following RT, patient-reported outcomes (PROs) collected via standardized questionnaires are crucial for monitoring patients' quality of life and side effects. However, traditional statistical and machine learning methods, which rely on structured numerical data, often fail to capture semantic meaning within patients' health status. To address this, we developed a novel framework using zero- and few-shot large language models (LLMs) to identify patients experiencing mild to severe depression. Furthermore, classification performance is enhanced through parameter-efficient fine-tuning. Experiments on a prostate cancer PRO dataset for depression have demonstrated that our fine-tuned LLMs consistently outperformed other baseline methods across key evaluation metrics.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Point Cloud Quality Assessment via Multi-View Structure-Aware Feature Fusion

Jian Xiong
Lingxia Jiang
Xianzhong Long
Miaohui Wang
Hao Gao

Point cloud quality assessment (PCQA) is essential for reliable 3D visual applications. While point-based methods face challenges in characterizing distortions due to point cloud disorder, projection-based approaches offer better efficiency but suffer from geometric distortion insensitivity and texture representation blind spots. This study proposes SAF-Net, a multi-view structure-aware feature fusion network for PCQA. We first identify two key limitations in projection-based methods: insufficient geometric distortion perception and representation blind spots (RBS) in texture images. To address these issues, SAF-Net innovatively integrates object mask maps and local binary pattern (LBP) maps. The mask maps enhance geometric distortion perception by extracting edge sharpness and curvature variations, while LBP maps capture essential structural information to overcome RBS and align with human visual system (HVS) sensitivity. SAF-Net employs a hybrid CNN-ViT architecture to balance local feature extraction and global context modeling, along with a progressive fusion strategy to optimize cross-modal feature interaction. Extensive experiments demonstrate the superior performance of SAF-Net on multiple benchmarks, establishing new state-of-the-art results in PCQA.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Hao Gao
Shaoyu Chen
Bo Jiang
Bencheng Liao
Yiang Shi
Xiaoyang Guo
Yuechuan Pu
haoran yin

Existing end-to-end autonomous driving (AD) algorithms typically follow the Imitation Learning (IL) paradigm, which faces challenges such as causal confusion and an open-loop gap. In this work, we propose RAD, a 3DGS-based closed-loop Reinforcement Learning (RL) framework for end-to-end Autonomous Driving. By leveraging 3DGS techniques, we construct a photorealistic digital replica of the real physical world, enabling the AD policy to extensively explore the state space and learn to handle out-of-distribution scenarios through large-scale trial and error. To enhance safety, we design specialized rewards to guide the policy in effectively responding to safety-critical events and understanding real-world causal relationships. To better align with human driving behavior, we incorporate IL into RL training as a regularization term. We introduce a closed-loop evaluation benchmark consisting of diverse, previously unseen 3DGS environments. Compared to IL-based methods, RAD achieves stronger performance in most closed-loop metrics, particularly exhibiting a 3× lower collision rate. Abundant closed-loop results are presented in the supplementary material. Code is available at https: //github. com/hustvl/RAD for facilitating future research.

PDF Details

EAAI Journal 2024 Journal Article

Alpha evolution: An efficient evolutionary algorithm with evolution path adaptation and matrix generation

Hao Gao
Qingke Zhang

Metaheuristics involve information extraction and utilization processes to generate more promising solutions. However, the background of excessive metaphor has led to ambiguity in the computational process. To solve this problem, this paper proposes a novel evolutionary algorithm called alpha evolution (AE). It updates the solution using the alpha operator with the adaptive base vector and the random and adaptive step sizes. First, sample candidate solutions to construct the evolution matrix. Estimate the population state through diagonal or weighted operations of the evolution matrix. To enhance the correlation of estimates for each generation, two evolution paths accumulate the estimate results and achieve the base vector adaptation. Second, the composite differential operation constructs the adaptive step size to estimate the problem gradient, which is used to accelerate the convergence of AE. Finally, the attenuation factor alpha adaptively adjusts the random step size generated based on search space to balance exploration and exploitation. AE was comprehensively verified regarding its search bias, invariance, scalability, parameter sensitivity, search behavior, qualitative indicators, exploration and exploitation, convergence, statistics, and complexity. In numerical simulation, AE was compared with 106 algorithms on the CEC’17 benchmark announced at the 2017 congress on evolutionary computation (CEC). Furthermore, AE was applied to solve multiple sequence alignment and engineering design problems. The evidence shows that AE is competitive in exploration and exploitation, convergence speed and accuracy, avoiding local optima, applicability, and reliability. The source code of AE is publicly available at https: //github. com/tsingke/AlphaEvolution.

Details DOI

JMLR Journal 2024 Journal Article

Boundary constrained Gaussian processes for robust physics-informed machine learning of linear partial differential equations

David Dalton
Alan Lazarus
Hao Gao
Dirk Husmeier

We introduce a framework for designing boundary constrained Gaussian process (BCGP) priors for exact enforcement of linear boundary conditions, and apply it to the machine learning of (initial) boundary value problems involving linear partial differential equations (PDEs).In contrast to existing work, we illustrate how to design boundary constrained mean and kernel functions for all classes of boundary conditions typically used in PDE modelling, namely Dirichlet, Neumann, Robin and mixed conditions. Importantly, this is done in a manner which allows for both forward and inverse problems to be naturally accommodated. We prove that the BCGP kernel has a universal representational capacity under Dirichlet conditions, and establish a formal equivalence between BCGPs and boundary-constrained neural networks (BCNNs) of infinite width.Finally, extensive numerical experiments are performed involving several linear PDEs, the results of which demonstrate the effectiveness and robustness of BCGP inference in the presence of sparse, noisy data. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2024. ( edit, beta )

PDF Details

AIIM Journal 2021 Journal Article

Neural network-based left ventricle geometry prediction from CMR images with application in biomechanics

Lukasz Romaszko
Agnieszka Borowska
Alan Lazarus
David Dalton
Colin Berry
Xiaoyu Luo
Dirk Husmeier
Hao Gao

Combining biomechanical modelling of left ventricular (LV) function and dysfunction with cardiac magnetic resonance (CMR) imaging has the potential to improve the prognosis of patient-specific cardiovascular disease risks. Biomechanical studies of LV function in three dimensions usually rely on a computerized representation of the LV geometry based on finite element discretization, which is essential for numerically simulating in vivo cardiac dynamics. Detailed knowledge of the LV geometry is also relevant for various other clinical applications, such as assessing the LV cavity volume and wall thickness. Accurately and automatically reconstructing personalized LV geometries from conventional CMR images with minimal manual intervention is still a challenging task, which is a pre-requisite for any subsequent automated biomechanical analysis. We propose a deep learning-based automatic pipeline for predicting the three-dimensional LV geometry directly from routinely-available CMR cine images, without the need to manually annotate the ventricular wall. Our framework takes advantage of a low-dimensional representation of the high-dimensional LV geometry based on principal component analysis. We analyze how the inference of myocardial passive stiffness is affected by using our automatically generated LV geometries instead of manually generated ones. These insights will inform the development of statistical emulators of LV dynamics to avoid computationally expensive biomechanical simulations. Our proposed framework enables accurate LV geometry reconstruction, outperforming previous approaches by delivering a reconstruction error 50% lower than reported in the literature. We further demonstrate that for a nonlinear cardiac mechanics model, using our reconstructed LV geometries instead of manually extracted ones only moderately affects the inference of passive myocardial stiffness described by an anisotropic hyperelastic constitutive law. The developed methodological framework has the potential to make an important step towards personalized medicine by eliminating the need for time consuming and costly manual operations. In addition, our method automatically maps the CMR scan into a low-dimensional representation of the LV geometry, which constitutes an important stepping stone towards the development of an LV geometry-heterogeneous emulator.

Details DOI

IROS Conference 2017 Conference Paper

Tactile motion recognition with convolutional neural networks

Haoying Wu
Daimin Jiang
Hao Gao

To satisfy the diversity of tactile patterns during Physical Human Robot Interaction(PHRI), this paper proposes a method to recognize human tactile motion using a spherical handle equipped with tactile sensors. The method first exploits convolutional neural networks as universal feature extractors, and then support vector machines are implemented for classifying the 16 kinds of motion in 4D space. Experimental results show the superiority of our approach against other methods, leading to classification rates over 91. 19%.

Details

IROS Conference 2013 Conference Paper

Fast 3-D shape measurement using blink-dot projection

Jun Chen
Qingyi Gu
Hao Gao
Tadayoshi Aoyama
Takeshi Takaki
Idaku Ishii

We propose a novel dot-pattern-projection three-dimensional (3-D) shape measurement method that can measure 3-D displacements of blink dots projected onto a measured object accurately even when it moves rapidly or is observed from a camera as moving rapidly. In our method, blinking dot patterns, in which each dot changes its size at different timings corresponding to its identification (ID) number, are projected from a projector at a high frame rate. 3-D shapes can be obtained without any miscorrespondence of the projected dots between frames by simultaneous tracking and identification of multiple dots projected onto a measured 3-D object in a camera view. Our method is implemented on a field-programmable gate array (FPGA)-based high-frame-rate (HFR) vision platform that can track and recognize as much as 15×15 blink-dot pattern in a 512×512 image in real time at 1000 fps, synchronized with an HFR projector. We demonstrate the performance of our system by showing real-time 3-D measurement results when our system is mounted on a parallel link manipulator as a sensing head.

Details