Author name cluster

Nuo Xu

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.

11 papers

1 author row

EAAI Journal 2026 Journal Article

A smart computational framework for predicting mechanical and sustainability indicators and optimizing mix proportions of recycled rubber aggregate concrete

Lang Lin
Nuo Xu
Di Yang
Guangzhou Li
Yiming Xiao
Yong Yu

Recycled rubber aggregate concrete (RRAC), a sustainable composite in which end-of-life tire rubber replaces natural aggregates, aids waste reduction, conserves resources, lowers structural weight and enhances acoustic and energy-dissipation performance. Yet its wider deployment remains constrained by limited accuracy in predicting mechanical properties and by the inefficiency of conventional mix-design practices. This study thus introduces an integrated framework that unifies property prediction, sustainability assessment and mix-design optimization. A dataset of 1382 experiments was used to train compressive strength (f c) and elastic modulus (E) models using random forest, gradient-boosted regression trees, extreme gradient boosting (XGB), light gradient boosting machine and a Bayesian neural network, from which the top-performing model was identified. Model transparency was achieved through Shapley additive explanations, partial dependence plots and individual conditional expectation analysis. Life-cycle carbon emissions of RRAC were quantified, and particle swarm optimization was employed to balance f c, E and carbon footprint, yielding optimized mixture formulations. Key findings include: (a) Predictive models attained R 2 values of 0. 584–0. 759 for f c and 0. 674–0. 842 for E, with train-test gaps ≤0. 05, demonstrating solid accuracy and generalization, with XGB performing best. (b) Feature-importance analysis showed that f c was governed primarily by recycled fine-aggregate substitution, water-to-cement ratio, recycled coarse aggregate substitution, sand ratio and aggregate-to-cement ratio, with E following a similar hierarchy. (c) Particle swarm optimization produced mix designs that reconcile strength, stiffness and emissions. Relative to unoptimized mixtures, optimized RRAC lowered carbon emissions by 20 %–55 % without sacrificing mechanical performance, offering a robust pathway toward sustainable concrete design.

Details DOI

EAAI Journal 2025 Journal Article

A sampling interval-adaptive transformer for industrial time sequence modeling with heterogeneou s sampling rates in quality prediction

Zijian Xu
Nuo Xu
Kai Wang
Xiaofeng Yuan
Yalin Wang
Chunhua Yang
Weihua Gui
Shuqiao Cheng

The industrial data sequences frequently exhibit irregular sampling frequencies, which pose a number of difficulties for data analysis and modeling. The traditional dynamic models like Recurrent Neural Network (RNN) and Transformer are difficult to model such data sequences. The main reason is that these models assume that data sampling frequency should be constant. To this end, a Sampling Interval-Adaptive Transformer (SIA-Trans) is proposed in this paper to adaptively model the temporal information for heterogeneous sampling sequences in industrial processes. The SIA-Trans uses the sampling interval and position embedding block to address the problem of unequal time intervals and rectify the temporal correlations in time series. Then, the interval-aware self-attention net is designed for dynamic data relationship modeling, taking the processed data through the self-attention mechanism. Finally, the predicted output is obtained after the point-wise feed-forward layer. The proposed SIA-Trans is validated on a real-world hydrocracking process to predict the content of hydrocarbon mixture with five carbon atoms (C5) hydrocarbons in light naphtha, as well as the final boiling point of jet fuel.

Details DOI

AAAI Conference 2025 Conference Paper

Exploring Intrinsic Alignments Within Text Corpus

Zi Liang
Pinghui Wang
Ruofei Zhang
Haibo Hu
Shuo Zhang
Qingqing Ye
Nuo Xu
Yaxin Xiao

Recent years have witnessed rapid advancements in the safety alignments of large language models (LLMs). Methods such as supervised instruction fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) have thus emerged as vital components in constructing LLMs. While these methods achieve robust and fine-grained alignment to human values, their practical application is still hindered by high annotation costs and incomplete human alignments. Besides, the intrinsic human values within training corpora have not been fully exploited. To address these issues, we propose ISAAC (Intrinsically Supervised Alignments by Assessing Corpus), a primary and coarse-grained safety alignment strategy for LLMs. ISAAC only relies on a prior assumption about the text corpus, and does not require preferences in RLHF or human responses selection in SFT. Specifically, it assumes a long-tail distribution of text corpus and employs a specialized sampling strategy to automatically sample high-quality responses. Theoretically, we prove that this strategy can improve the safety of LLMs under our assumptions. Empirically, our evaluations on mainstream LLMs show that ISAAC achieves a safety score comparable to current SFT solutions. Moreover, we conduct experiments on ISAAC for some RLHF-based LLMs, where we find that ISAAC can even improve the safety of these models under specific safety domains. These findings demonstrate that ISAAC can provide preliminary alignment to LLMs, thereby reducing the construction costs of existing human-feedback-based methods.

PDF Details DOI

EAAI Journal 2024 Journal Article

Interval Value Z-probabilistic double hierarchy linguistic multi-criteria group decision making method based on ratio system-peference point-full multiplicative form its application in selection of habitable city

Sidong Xian
Nuo Xu
Shuang Hu
Longjun Yin

Adequate representation of individual opinions, as well as effective multi-criteria group decision-making (MCGDM) models, are critical to the evaluation of livable cities. Problems often encountered in expressing individual opinions include how to characterize ambiguity, credibility, and uncertainty simultaneously. In this study, an interval-value Z-probabilistic double hierarchy linguistic MCGDM model based on the ratio system, the reference point, and the full multiplicative form (IZPDHL-RRF) is proposed, which offers a comprehensive information representation and addresses ambiguity, credibility and uncertainty in livable city assessments. Firstly, the Interval-Value Z-probabilistic double hierarchy linguistic term set (IZPDHLTS) is introduced, which can represent individual opinions more adequately. Then, a score function based on prospect theory is proposed to effectively compare linguistic variables, and the correlation and distance measures of IZPDHLVs are studied. Finally, the IZPDHL-RRF method for evaluating habitable city selection has been established. Comparative and sensitivity analysis are conducted to validate the efficacy and superiority of this method.

Details DOI

AAAI Conference 2024 Conference Paper

Learn How to See: Collaborative Embodied Learning for Object Detection and Camera Adjusting

Lingdong Shen
Chunlei Huo
Nuo Xu
Chaowei Han
Zichen Wang

Passive object detectors, trained on large-scale static datasets, often overlook the feedback from object detection to image acquisition. Embodied vision and active detection mitigate this issue by interacting with the environment. Nevertheless, the materialization of activeness hinges on resource-intensive data collection and annotation. To tackle these challenges, we propose a collaborative student-teacher framework. Technically, a replay buffer is built based on the trajectory data to encapsulate the relationship of state, action, and reward. In addition, the student network diverges from reinforcement learning by redefining sequential decision pathways using a GPT structure enriched with causal self-attention. Moreover, the teacher network establishes a subtle state-reward mapping based on adjacent benefit differences, providing reliable rewards for student adaptively self-tuning with the vast unlabeled replay buffer data. Additionally, an innovative yet straightforward benefit reference value is proposed within the teacher network, adding to its effectiveness and simplicity. Leveraging a flexible replay buffer and embodied collaboration between teacher and student, the framework learns to see before detection with shallower features and shorter inference steps. Experiments highlight significant advantages of our algorithm over state-of-the-art detectors. The code is released at https://github.com/lydonShen/STF.

PDF Details DOI

AAAI Conference 2024 Conference Paper

MERGE: Fast Private Text Generation

Zi Liang
Pinghui Wang
Ruofei Zhang
Nuo Xu
Shuo Zhang
Lifeng Xing
Haitao Bai
Ziyang Zhou

The drastic increase in language models' parameters has led to a new trend of deploying models in cloud servers, raising growing concerns about private inference for Transformer-based models. Existing two-party privacy-preserving techniques, however, only take into account natural language understanding (NLU) scenarios. Private inference in natural language generation (NLG), crucial for applications like translation and code completion, remains underexplored. In addition, previous privacy-preserving techniques suffer from convergence issues during model training and exhibit poor inference speed when used with NLG models due to the neglect of time-consuming operations in auto-regressive generations. To address these issues, we propose a fast private text generation framework for Transformer-based language models, namely MERGE. MERGE reuses the output hidden state as the word embedding to bypass the embedding computation and reorganize the linear operations in the Transformer module to accelerate the forward procedure. Extensive experiments show that MERGE achieves a 26.5x speedup to the vanilla encrypted model under the sequence length 512, and reduces 80% communication cost, with an up to 10x speedup to state-of-the-art approximated models.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference

Ran Ran
Nuo Xu
Tao Liu
Wei Wang
Gang Quan
Wujie Wen

The marriage of Graph Convolutional Network (GCN) and Homomorphic Encryption (HE) enables the inference of graph data on the cloud with significantly enhanced client data privacy. However, the tremendous computation and memory overhead associated with HE operations challenges the practicality of HE-based GCN inference. GCN inference involves a sequence of expensive matrix-matrix multiplications, and we observe that directly applying the state-of-the-art HE-based secure matrix-matrix multiplication solutions to accelerate HE-GCN inference is far less efficient as it does not exploit the unique aggregation mechanism of two-dimension graph node-features in GCN layer computation. As a result, in this paper, we propose a novel HE-based ciphertext packing technique, i. e. , Penguin, that can take advantage of the unique computation pattern during the HE-GCN inference to significantly reduce the computation and memory overhead associated with HE operations. Specifically, Penguin employs (i) an effective two-dimension parallel packing technique for feature ciphertext with optimal graph node partitioning and graph feature interleaving, and (ii) an interleaved assembly technique that can effectively make use of the blank slots to merge ciphertexts after feature reduction and significantly reduce the costly rotation operation. We provide theoretical analysis and experimental validation to demonstrate the speedup achieved by Penguin in accelerating GCN inference using popular GCN models and datasets. Our results show that Penguin can achieve up to $\sim10\times$ speedup and around $\sim79$% reduction in computational memory overhead, significantly outperforming state-of-the-art solutions. To the best of our knowledge, this is the first work that can ensure the protection of both graph structure and features when accelerating HE-GCN inference on encrypted data. Our code is publicly available at https: //github. com/ranran0523/Penguin.

PDF Details

NeurIPS Conference 2022 Conference Paper

CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference

Ran Ran
Wei Wang
Quan Gang
Jieming Yin
Nuo Xu
Wujie Wen

Recently cloud-based graph convolutional network (GCN) has demonstrated great success and potential in many privacy-sensitive applications such as personal healthcare and financial systems. Despite its high inference accuracy and performance on the cloud, maintaining data privacy in GCN inference, which is of paramount importance to these practical applications, remains largely unexplored. In this paper, we take an initial attempt towards this and develop CryptoGCN--a homomorphic encryption (HE) based GCN inference framework. A key to the success of our approach is to reduce the tremendous computational overhead for HE operations, which can be orders of magnitude higher than its counterparts in the plaintext space. To this end, we develop a solution that can effectively take advantage of the sparsity of matrix operations in GCN inference to significantly reduce the encrypted computational overhead. Specifically, we propose a novel Adjacency Matrix-Aware (AMA) data formatting method along with the AMA assisted patterned sparse matrix partitioning, to exploit the complex graph structure and perform efficient matrix-matrix multiplication in HE computation. In this way, the number of HE operations can be significantly reduced. We also develop a co-optimization framework that can explore the trade-offs among the accuracy, security level, and computational overhead by judicious pruning and polynomial approximation of activation modules in GCNs. Based on the NTU-XVIEW skeleton joint dataset, i. e. , the largest dataset evaluated homomorphically by far as we are aware of, our experimental results demonstrate that CryptoGCN outperforms state-of-the-art solutions in terms of the latency and number of homomorphic operations, i. e. , achieving as much as a 3. 10$\times$ speedup on latency and reduces the total Homomorphic Operation Count (HOC) by 77. 4\% with a small accuracy loss of 1-1. 5$\%$. Our code is publicly available at https: //github. com/ranran0523/CryptoGCN.

PDF Details

AAAI Conference 2021 Conference Paper

Learning to Check Contract Inconsistencies

Shuo Zhang
Junzhou Zhao
Pinghui Wang
Nuo Xu
Yang Yang
Yiting Liu
Yi Huang
Junlan Feng

Contract consistency is important in ensuring the legal validity of the contract. In many scenarios, a contract is written by filling the blanks in a precompiled form. Due to carelessness, two blanks that should be filled with the same (or different) content may be incorrectly filled with different (or same) content. This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract. Traditional methods to address this issue mainly rely on manual contract review, which is labor-intensive and costly. In this work, we formulate a novel Contract Inconsistency Checking (CIC) problem, and design an end-to-end framework, called Pair-wise Blank Resolution (PBR), to solve the CIC problem with high accuracy. Our PBR model contains a novel BlankCoder to address the challenge of modeling meaningless blanks. BlankCoder adopts a two-stage attention mechanism that adequately associates a meaningless blank with its relevant descriptions while avoiding the incorporation of irrelevant context words. Experiments conducted on real-world datasets show the promising performance of our method with a balanced accuracy of 94. 05% and an F1 score of 90. 90% in the CIC problem.

PDF Details

IJCAI Conference 2019 Conference Paper

MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

Nuo Xu
Pinghui Wang
Long Chen
Jing Tao
Junzhou Zhao

Predicting interactions between structured entities lies at the core of numerous tasks such as drug regimen and new material design. In recent years, graph neural networks have become attractive. They represent structured entities as graphs, and then extract features from each individual graph using graph convolution operations. However, these methods have some limitations: i) their networks only extract features from a fix-sized subgraph structure (i. e. , a fix-sized receptive field) of each node, and ignore features in substructures of different sizes, and ii) features are extracted by considering each entity independently, which may not effectively reflect the interaction between two entities. To resolve these problems, we present {\em MR-GNN}, an end-to-end graph neural network with the following features: i) it uses a multi-resolution based architecture to extract node features from different neighborhoods of each node, and, ii) it uses dual graph-state long short-term memory networks (LSTMs) to summarize local features of each graph and extracts the interaction features between pairwise graphs. Experiments conducted on real-world datasets show that MR-GNN improves the prediction of state-of-the-art methods.

PDF Details

AAAI Conference 2014 Conference Paper

GP-Localize: Persistent Mobile Robot Localization Using Online Sparse Gaussian Process Observation Model

Nuo Xu
Kian Hsiang Low
Jie Chen
Keng Kiat Lim
Etkin Ozgul

Central to robot exploration and mapping is the task of persistent localization in environmental fields characterized by spatially correlated measurements. This paper presents a Gaussian process localization (GP-Localize) algorithm that, in contrast to existing works, can exploit the spatially correlated field measurements taken during a robot’s exploration (instead of relying on prior training data) for efficiently and scalably learning the GP observation model online through our proposed novel online sparse GP. As a result, GP-Localize is capable of achieving constant time and memory (i. e. , independent of the size of the data) per filtering step, which demonstrates the practical feasibility of using GPs for persistent robot localization and autonomy. Empirical evaluation via simulated experiments with real-world datasets and a real robot experiment shows that GP-Localize outperforms existing GP localization algorithms.

PDF Details