Author name cluster

Zhuo Wang

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.

16 papers

2 author rows

EAAI Journal 2026 Journal Article

Integrated modeling and modal layered control strategy for flatness regulation in variable crown temper rolling

Ji Zhang
Zhixuan Wang
Zhuo Wang
Haibo Yuan
Renhao Wu
Hyoung Seop Kim
Zhenhua Bai

Strip flatness is a critical indicator of product quality, strongly influencing downstream processing and the final performance of rolled products. Temper mills equipped with variable-crown (VC) rolls offer superior flatness control by combining hydraulic bulging with inner and outer roll bending. This study presents a novel framework characterized by the unique integration of a comprehensive VC roll physical model with a hierarchical multi-objective optimization strategy. The proposed model integrates metal plastic deformation theory, roll elastic deformation behavior, and the complex mechanical interactions within the roll-stack system. A Particle Swarm Optimization algorithm is employed to identify and optimize the key input parameters of the prediction model. Furthermore, an intelligent layered flatness control strategy is designed using the Non-dominated Sorting Genetic Algorithm III for multi-objective optimization. The strategy operates in two stages: first, inner and outer bending forces are prioritized for rapid coarse adjustment; subsequently, as flatness deviation approaches a defined threshold, hydraulic crown control is activated to work in coordination with the bending forces, enabling fine and precise regulation. The proposed methodology was validated through industrial application on 2503 actual production coils, encompassing a wide range of steel grades. Industrial results confirm that this strategy reduces the average flatness deviation by 61. 4 % and narrows the standard deviation by 56. 3 %, while achieving an exceptional quality compliance rate of 99. 4 %. This framework establishes a robust theoretical foundation and provides highly effective practical guidance for high-precision flatness regulation in modern manufacturing.

Details DOI

AAAI Conference 2026 Conference Paper

MetaEval: Measuring the Discrimination of Benchmarks for Efficient LLM Evaluation

Zhuo Wang
Wen Wu
Guoqing Wang
Guangze Ye
Zhenxiao Cheng

Benchmarks serve as standardized test systems to distinguish capabilities among large language models (LLMs). Discriminative items enable high-ability LLMs to favor correct answers, while causing low-ability models to assign lower plausibility to these answers and tend toward incorrect answers. Current methods for assessing benchmark quality primarily focus on coverage of difficulty levels and task diversity, yet lack direct quantification of discrimination—the core metric. Furthermore, large-scale benchmarks incur high evaluation costs. Although heuristic methods can reduce item counts to some extent, they cannot guarantee preservation of the benchmark’s original discriminative properties. To address these limitations, we propose MetaEval, a meta-evaluation framework designed to precisely quantify per-item discrimination and enable efficient assessment. Central to MetaEval is our novel Signal Detection and Item Response (SD-IR) model, which simulates LLMs’ detection of correct answers (signals) by representing each model’s perception through two latent ability states: “known” and “unknown”. For any item, discrimination is quantified as the difference in signal plausibility between these states. Leveraging these discrimination metrics, MetaEval introduces two strategies to replicate full-benchmark results using minimal subsets for efficient evaluation: (1) Distilling metaBench: a compact subset that retains discriminative power by removing redundant items; (2) Predicting performance on full-benchmark based on metaBench’s discrimination. Experiments across five benchmarks confirm that high-discrimination items capture greater performance variation among LLMs, align more closely with full-benchmark rankings, and exhibit superior predictive ability. Notably, in the best case, MetaEval achieves accurate full-benchmark estimation using only 2.5% of items, substantially reducing evaluation costs while preserving reliability.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Cognitive Predictive Processing: A Human-inspired Framework for Adaptive Exploration in Open-World Reinforcement Learning

boheng liu
Ziyu Li
Chenghua Duan
Yutian Liu
Zhuo Wang
Xiuxing Li
Qing Li
Xia Wu

Open-world reinforcement learning challenges agents to develop intelligent behavior in vast exploration spaces. Recent approaches like LS-Imagine have advanced the field by extending imagination horizons through jumpy state transitions, yet remain limited by fixed exploration mechanisms and static jump thresholds that cannot adapt across changing task phases, resulting in inefficient exploration and lower completion rates. Humans demonstrate remarkable capabilities in open-world decision-making through a chain-like process of task decomposition, selective memory utilization, and adaptive uncertainty regulation. Inspired by human decision-making processes, we present Cognitive Predictive Processing (CPP), a novel framework that integrates three neurologically-inspired systems: a phase-adaptive cognitive controller that dynamically decomposes tasks into exploration, approach, and completion phases with adaptive parameters; a dual-memory integration system implementing dual-modal memory that balances immediate context with selective long-term storage; and an uncertainty-modulated prediction regulator that continuously updates environmental predictions to modulate exploration behavior. Comprehensive experiments in MineDojo demonstrate that these human-inspired decision-making strategies enhance performance over recent techniques, with success rates improving by an average of 4. 6\% across resource collection tasks while reducing task completion steps by an average of 7. 1\%. Our approach bridges cognitive neuroscience and reinforcement learning, excelling in complex scenarios that require sustained exploration and strategic adaptation while demonstrating how neural-inspired models can solve key challenges in open-world AI systems.

PDF Details

JBHI Journal 2025 Journal Article

Dual Transformer Network for Predicting Joint Angles and Torques From Multi-Channel EMG Signals in the Lower Limbs

Zhuo Wang
Chunjie Chen
Hui Chen
Yizhe Zhou
Xiangyang Wang
Xinyu Wu

Accurate estimation of lower limb joint kinematics and kinetics using wearable sensors enables biomechanical analysis beyond laboratory settings and facilitates real-time adaptation of exoskeleton assistance profiles. This study introduces a Dual Transformer Network (DTN) designed to concurrently estimate multiple joint angles and moments from multi-channel surface electromyography (sEMG) signals in the lower limbs. The performance evaluation of the predicted joint angles for the hip, knee, and ankle showed average root mean square error ( RMSE ) values of 1. 1827 $^{\circ }$, 1. 4312 $^{\circ }$, and 0. 8113 $^{\circ }$, Pearson correlation coefficients ( $\boldsymbol{\rho }$ ) of 0. 9992, 0. 9993, and 0. 9991, and coefficients of determination ( $\mathbf {{\mathit{R}}}^{2}$ ) of 0. 9847, 0. 9858, and 0. 9838, respectively. For the predicted joint moments, the corresponding values were RMSE of 0. 0458, 0. 0341, and 0. 0522 Nm/kg, $\boldsymbol{\rho }$ of 0. 9978, 0. 9972, and 0. 9990, and $\mathbf {{\mathit{R}}}^{2}$ of 0. 9825, 0. 9801, and 0. 9902. Angular velocities, derived by differentiating the estimated joint angles, achieved an RMSE below 0. 6530 rd/s, $\boldsymbol{\rho }$ exceeding 0. 9534, and $\mathbf {{\mathit{R}}}^{2}$ above 0. 9552. Additionally, joint power, computed as the dot product of predicted joint moments and angular velocities, resulted in RMSE below 0. 3823W/kg, $\boldsymbol{\rho }$ above 0. 9771, and $\mathbf {{\mathit{R}}}^{2}$ above 0. 8925. These results demonstrate the effectiveness of the proposed network in continuously estimating lower limb kinematics and kinetics, contributing to advancements in assist-as-needed exoskeleton control strategies.

Details DOI

EAAI Journal 2025 Journal Article

Research on optimization strategy for steel strip temper rolling elongation based on model predictive control

Zhixuan Wang
Ji Zhang
Zhuo Wang
Hao Wang
Zhenhua Bai

This study addresses the limitations of traditional Proportional-Integral-Derivative (PID) control in strip steel temper rolling elongation rate regulation, such as weak anti-interference capability and insufficient dynamic response, by proposing an intelligent elongation rate optimization strategy based on a hybrid Model Predictive Control (MPC) and Long Short-Term Memory (LSTM)-Transformer model. A data-driven closed-loop control framework is constructed by integrating the temporal modeling capability of deep learning with the dynamic optimization characteristics of MPC. First, an innovative LSTM-Transformer hybrid prediction model is applied, combining LSTM's local temporal feature extraction capability with Transformer's global dependency capturing mechanism, achieving high-precision prediction of real elongation rate (test set Mean Absolute Error <0. 02, R2 > 0. 97). Second, a dynamic weighted sampling method is proposed to address the insufficient model generalization caused by imbalanced industrial data distribution by enhancing learning of key dynamic conditions such as weld seam transitions and rolling mill speed changes. On this basis, a Cross-Entropy Method (CEM)-based MPC controller is developed, integrating the prediction model with multi-objective optimization to dynamically adjust rolling force, tension, and other parameters while minimizing elongation rate fluctuations under equipment constraints. Finally, experiments on an offline simulation platform demonstrate that elongation rate fluctuations are substantially reduced, achieving precise control and robust disturbance rejection under complex conditions like acceleration/deceleration and weld seams. This study provides theoretical support and a technical paradigm for the intelligent transformation of the steel industry, demonstrating significant engineering application value.

Details DOI

ICRA Conference 2024 Conference Paper

Enhancing Visual Place Recognition with Multi-modal Features and Time-constrained Graph Attention Aggregation

Zhuo Wang
Yunzhou Zhang
Xinge Zhao
Jian Ning
Dehao Zou
Meiqi Pei

Visual place recognition(VPR) is a crucial technology for autonomous driving and robotic navigation. However, severe appearance and perspective changes often lead to degradation of algorithm performance. Current methods mainly utilize single-modality RGB images, which are sensitive to environmental changes. To address this challenge, we propose a novel multi-modal visual place recognition method by incorporating depth information as auxiliary data to enhance the robustness of the VPR algorithm. The pipeline involves dual-branch feature extraction and shared multi-modal feature fusion based on transformer(SFFM) to enable full interaction between semantic and structural information. Furthermore, we introduces a time-constrained graph attention aggregation(TC-GAT) that propagates node information across time and space to deal with perceptual aliasing. Extensive experiments on the Oxford Robotcar and MSLS datasets demonstrate that the proposed algorithm is not only effective in appearance changes but also competitive in opposing viewpoints.

Details

IROS Conference 2024 Conference Paper

Pos 2 VPR: Fast Position Consistency Validation with Positive Sample Mining for Hierarchical Place Recognition

Dehao Zou
Xiaolong Qian
Yunzhou Zhang
Xinge Zhao
Zhuo Wang

Visual place recognition (VPR) is a challenging issue for robotics and autonomous systems, focusing on utilizing visual information for robot localization. Currently, hierarchical architecture is being employed by growing works, which embraces RANSAC-based geometric verification for re-ranking. However, RANSAC is time-consuming and only employs geometric information while neglecting other potential information that could be useful for re-ranking. Here we propose a fast position consistency via local patch (PCLP) algorithm to take the position of task-relevant patch-descriptor into account. Without training, it only costs little time but performs better than other re-ranking methods that rely on geometric consistency verification. In this paper, we present a unified place recognition framework that incorporates an aggregation module to extract global features for retrieval and a PCLP validation module to filter local patch for reranking. Meanwhile, we propose a RANSAC-based tightly coupled learning (R-TCL) strategy to discover the best positive sample for training robust models. Unlike common sample mining methods, we introduce RANSAC into the sample mining process, achieving trade-off between efficiency and accuracy. Due to improved positive sample mining strategy and novel position validation module, our model is named as Pos 2 VPR. Remarkably, Pos 2 VPR outperforms state-of-the-art methods on four major datasets with extremely short running time.

Details

NeurIPS Conference 2024 Conference Paper

Validating Climate Models with Spherical Convolutional Wasserstein Distance

Robert C. Garrett
Trevor Harris
Zhuo Wang
Bo Li

The validation of global climate models is crucial to ensure the accuracy and efficacy of model output. We introduce the spherical convolutional Wasserstein distance to more comprehensively measure differences between climate models and reanalysis data. This new similarity measure accounts for spatial variability using convolutional projections and quantifies local differences in the distribution of climate variables. We apply this method to evaluate the historical model outputs of the Coupled Model Intercomparison Project (CMIP) members by comparing them to observational and reanalysis data products. Additionally, we investigate the progression from CMIP phase 5 to phase 6 and find modest improvements in the phase 6 models regarding their ability to produce realistic climatologies.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Learning to Binarize Continuous Features for Neuro-Rule Networks

Wei Zhang
Yongxiang Liu
Zhuo Wang
Jianyong Wang

Neuro-Rule Networks (NRNs) emerge as a promising neuro-symbolic method, enjoyed by the ability to equate fully-connected neural networks with logic rules. To support learning logic rules consisting of boolean variables, converting input features into binary representations is required. Different from discrete features that could be directly transformed by one-hot encodings, continuous features need to be binarized based on some numerical intervals. Existing studies usually select the bound values of intervals based on empirical strategies (e. g. , equal-width interval). However, it is not optimal since the bounds are fixed and cannot be optimized to accommodate the ultimate training target. In this paper, we propose AutoInt, an approach that automatically binarizes continuous features and enables the intervals to be optimized with NRNs in an end-to-end fashion. Specifically, AutoInt automatically selects an interval for a given continuous feature in a soft manner to enable a differentiable learning procedure of interval-related parameters. Moreover, it introduces an additional soft K-means clustering loss to make the interval centres approach the original feature value distribution, thus reducing the risk of overfitting intervals. We conduct comprehensive experiments on public datasets and demonstrate the effectiveness of AutoInt in boosting the performance of NRNs.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

Scalable Rule-Based Representation Learning for Interpretable Classification

Zhuo Wang
Wei Zhang
Ning Liu
Jianyong Wang

Rule-based models, e. g. , decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity. However, rule-based models are hard to optimize, especially on large data sets, due to their discrete parameters and structures. Ensemble methods and fuzzy/soft rules are commonly used to improve performance, but they sacrifice the model interpretability. To obtain both good scalability and interpretability, we propose a new classifier, named Rule-based Representation Learner (RRL), that automatically learns interpretable non-fuzzy rules for data representation and classification. To train the non-differentiable RRL effectively, we project it to a continuous space and propose a novel training method, called Gradient Grafting, that can directly optimize the discrete model using gradient descent. An improved design of logical activation functions is also devised to increase the scalability of RRL and enable it to discretize the continuous features end-to-end. Exhaustive experiments on nine small and four large data sets show that RRL outperforms the competitive interpretable approaches and can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios. Our code is available at: https: //github. com/12wang3/rrl.

PDF Details

AAAI Conference 2020 Conference Paper

Transparent Classification with Multilayer Logical Perceptrons and Random Binarization

Zhuo Wang
Wei Zhang
Ning Liu
Jianyong Wang

Models with transparent inner structure and high classiﬁcation performance are required to reduce potential risk and provide trust for users in domains like health care, ﬁnance, security, etc. However, existing models are hard to simultaneously satisfy the above two properties. In this paper, we propose a new hierarchical rule-based model for classi- ﬁcation tasks, named Concept Rule Sets (CRS), which has both a strong expressive ability and a transparent inner structure. To address the challenge of efﬁciently learning the nondifferentiable CRS model, we propose a novel neural network architecture, Multilayer Logical Perceptron (MLLP), which is a continuous version of CRS. Using MLLP and the Random Binarization (RB) method we proposed, we can search the discrete solution of CRS in continuous space using gradient descent and ensure the discrete CRS acts almost the same as the corresponding continuous MLLP. Experiments on 12 public data sets show that CRS outperforms the state-of-theart approaches and the complexity of the learned CRS is close to the simple decision tree.

PDF Details

AAAI Conference 2019 Conference Paper

Community Focusing: Yet Another Query-Dependent Community Detection

Zhuo Wang
Weiping Wang
Chaokun Wang
Xiaoyan Gu
Bo Li
Dan Meng

As a major kind of query-dependent community detection, community search finds a densely connected subgraph containing a set of query nodes. As density is the major consideration of community search, most methods of community search often find a dense subgraph with many vertices far from the query nodes, which are not very related to the query nodes. Motivated by this, a new problem called community focusing (CF) is studied. It finds a community where the members are close and densely connected to the query nodes. A distance-sensitive dense subgraph structure called β-attention-core is proposed to remove the vertices loosely connected to or far from the query nodes, and a combinational density is designed to guarantee the density of a subgraph. Then CF is formalized as finding a subgraph with the largest combinational density among the β-attention-core subgraphs containing the query nodes with the largest β. Thereafter, effective methods are devised for CF. Furthermore, a speed-up strategy is developed to make the methods scalable to large networks. Extensive experimental results on real and synthetic networks demonstrate the performance of our methods.

PDF Details

NeurIPS Conference 2016 Conference Paper

Efficient Neural Codes under Metabolic Constraints

Zhuo Wang
Xue-Xin Wei
Alan Stocker
Daniel Lee

Neural codes are inevitably shaped by various kinds of biological constraints, \emph{e. g. } noise and metabolic cost. Here we formulate a coding framework which explicitly deals with noise and the metabolic costs associated with the neural representation of information, and analytically derive the optimal neural code for monotonic response functions and arbitrary stimulus distributions. For a single neuron, the theory predicts a family of optimal response functions depending on the metabolic budget and noise characteristics. Interestingly, the well-known histogram equalization solution can be viewed as a special case when metabolic resources are unlimited. For a pair of neurons, our theory suggests that under more severe metabolic constraints, ON-OFF coding is an increasingly more efficient coding scheme compared to ON-ON or OFF-OFF. The advantage could be as large as one-fold, substantially larger than the previous estimation. Some of these predictions could be generalized to the case of large neural populations. In particular, these analytical results may provide a theoretical basis for the predominant segregation into ON- and OFF-cells in early visual processing areas. Overall, we provide a unified framework for optimal neural codes with monotonic tuning curves in the brain, and makes predictions that can be directly tested with physiology experiments.

PDF Details

NeurIPS Conference 2013 Conference Paper

Optimal Neural Population Codes for High-dimensional Stimulus Variables

Zhuo Wang
Alan Stocker
Daniel Lee

How does neural population process sensory information? Optimal coding theories assume that neural tuning curves are adapted to the prior distribution of the stimulus variable. Most of the previous work has discussed optimal solutions for only one-dimensional stimulus variables. Here, we expand some of these ideas and present new solutions that define optimal tuning curves for high-dimensional stimulus variables. We consider solutions for a minimal case where the number of neurons in the population is equal to the number of stimulus dimensions (diffeomorphic). In the case of two-dimensional stimulus variables, we analytically derive optimal solutions for different optimal criteria such as minimal L2 reconstruction error or maximal mutual information. For higher dimensional case, the learning rule to improve the population code is provided.

PDF Details

YNIMG Journal 2012 Journal Article

Anxiolytic-like effect of pregabalin on unconditioned fear in the rat: An autoradiographic brain perfusion mapping and functional connectivity study

Zhuo Wang
Raina D. Pang
Martha Hernandez
Marco A. Ocampo
Daniel P. Holschneider

Clinical and preclinical evidence suggests anxiolytic-like efficacy of pregabalin (PGB, Lyrica). However, its mechanism of action remains under investigation. The current study applied [14C]-iodoantipyrine cerebral blood flow (CBF) mapping to examine the effect of PGB on neural substrates underlying unconditioned fear in a rat model of footshock-induced fear. Regional CBF (rCBF) was analyzed by statistical parametric mapping. Functional connectivity and graph theoretical analysis were used to investigate how footshock and PGB affect brain activation at the network level. Pregabalin significantly attenuated footshock-induced ultrasonic vocalization, but showed no significant effect on freezing behavior. Footshock compared to no-shock controls elicited significant increases in rCBF in limbic/paralimbic regions implicated in the processing of unconditioned fear and ultrasonic vocalization, including the amygdala, hypothalamus, lateral septum, dorsal periaqueductal gray, the anterior insular (aINS) and medial prefrontal cortex (mPFC). The activation pattern was similar in vehicle- and PGB-treated subjects, with PGB significantly attenuating activation in the amygdala, hypothalamus, and aINS. The vehicle/no-shock group showed strong, positive intra-structural correlations within the cortex, hypothalamus, amygdala, thalamus, and brainstem. The cortex was negatively correlated with the hypothalamus and brainstem. Footshock reduced the total number of significant correlations, but induced greater intra-cortical connectivity of the aINS and mPFC, and new positive correlations between the hypothalamus and amygdala. In no-shock controls, PGB significantly reduced the positive intra-structural correlations within the cortex and amygdala, as well as the negative cortico-subcortical correlations. Following footshocks, PGB disrupted both the network recruitment of aINS and mPFC, and the positive hypothalamic-amygdaloid correlations. Our findings suggest that PGB may exert anxiolytic effect by attenuating cortico-cortical and cortico-subcortical communication and inhibiting network recruitment of the aINS, mPFC, amygdala, and hypothalamus following a fear-inducing stimulus. Functional brain mapping in rodents may provide new endpoints for preclinical evaluation of anxiolytic drug candidates with potentially improved translational power compared to behavioral measurements alone.

Details DOI

NeurIPS Conference 2012 Conference Paper

Optimal Neural Tuning Curves for Arbitrary Stimulus Distributions: Discrimax, Infomax and Minimum $L_p$ Loss

Zhuo Wang
Alan Stocker
Daniel Lee

In this work we study how the stimulus distribution influences the optimal coding of an individual neuron. Closed-form solutions to the optimal sigmoidal tuning curve are provided for a neuron obeying Poisson statistics under a given stimulus distribution. We consider a variety of optimality criteria, including maximizing discriminability, maximizing mutual information and minimizing estimation error under a general $L_p$ norm. We generalize the Cramer-Rao lower bound and show how the $L_p$ loss can be written as a functional of the Fisher Information in the asymptotic limit, by proving the moment convergence of certain functions of Poisson random variables. In this manner, we show how the optimal tuning curve depends upon the loss function, and the equivalence of maximizing mutual information with minimizing $L_p$ loss in the limit as $p$ goes to zero.

PDF Details