Author name cluster

Xiaobin Li

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.

4 papers

1 author row

EAAI Journal 2026 Journal Article

Welding heat source parameter optimization using a dynamic hybrid surrogate model

Xiaobin Li
Wenming Huang
Pei Jiang
Bahmaninezhad Fatemeh
Xi Vincent Wang
Huajun Cao

Accurate calibration of welding heat source parameters is essential for reliable simulation-based prediction of weld quality and residual stresses in critical engineering structures such as pipelines and pressure vessels. However, traditional calibration methods are time-consuming and computationally expensive, limiting their industrial practicality. To address this issue, this paper proposes an intelligent optimization framework for welding heat source calibration, integrating a hybrid surrogate model based on a dynamic feature fusion mechanism with the Newton–Raphson-based optimizer (NRBO). The framework first achieves automated high-precision extraction of molten pool geometric features through isoparametric transformation and computer graphics techniques. Subsequently, a stacking ensemble strategy integrates heterogeneous surrogate models, while incorporating a self-attention-enhanced multilayer perceptron (Self-Attention-MLP) to dynamically fuse outputs from sub-models, which enhances capability of the hybrid surrogate model to capture the complex nonlinear mapping relationships between heat source parameters and molten pool features. Finally, an efficient parameter optimization workflow is established by combining the NRBO algorithm with the objective of minimizing geometric errors in the molten pool. Experimental results demonstrate that the hybrid surrogate model achieves coefficients of determination ( R 2 ) of 0. 955 and 0. 983 for predicting molten pool width and depth, respectively, significantly outperforming individual baseline models. The optimized double-ellipsoidal heat source parameters(front axial length a f = 5. 2, rear axial length a r = 6. 1, transverse expansion coefficient b = 0. 7, and depth coefficient c = 9. 35) were validated via simulation, yielding predicted molten pool width and depth of 12. 90 mm and 9. 03 mm, respectively. These results exhibit relative errors of 3. 3% and 3. 4% compared to experimental measurements ( 13. 34 mm and 9. 35 mm ), confirming the effectiveness and reliability of the proposed method. This study provides industry practitioners with a practical tool for improving simulation fidelity and accelerating process design in demanding industrial applications such as pressure vessel manufacturing and pipeline construction.

Details DOI

AAAI Conference 2025 Conference Paper

B2Opt: Learning to Optimize Black-box Optimization with Little Budget

Xiaobin Li
Kai Wu
Xiaoyu Zhang
Handing Wang

The core challenge of high-dimensional and expensive black-box optimization (BBO) is how to obtain better performance faster with little function evaluation cost. The essence of the problem is how to design an efficient optimization strategy tailored to the target task. This paper designs a powerful optimization framework to automatically learn the optimization strategies from the target or cheap surrogate task without human intervention. However, current methods are weak for this due to poor representation of optimization strategy. To achieve this, 1) drawing on the mechanism of genetic algorithm, we propose a deep neural network framework called B2Opt, which has a stronger representation of optimization strategies based on survival of the fittest; 2) B2Opt can utilize the cheap surrogate functions of the target task to guide the design of the efficient optimization strategies. Compared to the state-of-the-art BBO baselines, B2Opt can achieve multiple orders of magnitude performance improvement with less function evaluation cost.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation

Muqi Han
Xiaobin Li
Kai Wu
Xiaoyu Zhang
Handing Wang

Zero-shot optimization aims to achieve both generalization and performance gains on solving previously unseen black-box optimization problems over SOTA methods without task-specific tuning. Pre-trained optimization models (POMs) address this challenge by learning a general mapping from task features to optimization strategies, enabling direct deployment on new tasks. In this paper, we identify three essential components that determine the effectiveness of POMs: (1) task feature modeling, which captures structural properties of optimization problems; (2) optimization strategy representation, which defines how new candidate solutions are generated; and (3) the feature-to-strategy mapping mechanism learned during pre-training. However, existing POMs often suffer from weak feature representations, rigid strategy modeling, and unstable training. To address these limitations, we propose EPOM, an enhanced framework for pre-trained optimization. EPOM enriches task representations using a cross-attention-based tokenizer, improves strategy diversity through deformable attention, and stabilizes training by replacing non-differentiable operations with a differentiable crossover mechanism. Together, these enhancements yield better generalization, faster convergence, and more reliable performance in zero-shot black-box optimization.

PDF Details

NeurIPS Conference 2024 Conference Paper

Pretrained Optimization Model for Zero-Shot Black Box Optimization

Xiaobin Li
Kai Wu
Yujian B. Li
Xiaoyu Zhang
Handing Wang
Jing Liu

Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or with minimal adjustments to the optimizer. It is crucial to ensure reliable and robust performance in various applications. Current optimizers often struggle with zero-shot optimization and require intricate hyperparameter tuning to adapt to new tasks. To address this, we propose a Pretrained Optimization Model (POM) that leverages knowledge gained from optimizing diverse tasks, offering efficient solutions to zero-shot optimization through direct application or fine-tuning with few-shot samples. Evaluation on the BBOB benchmark and two robot control tasks demonstrates that POM outperforms state-of-the-art black-box optimization methods, especially for high-dimensional tasks. Fine-tuning POM with a small number of samples and budget yields significant performance improvements. Moreover, POM demonstrates robust generalization across diverse task distributions, dimensions, population sizes, and optimization horizons. For code implementation, see https: //github. com/ninja-wm/POM/.

PDF Details DOI