arXiv subjects

Wang Chao

Publications and source records attributed to Wang Chao.

7 recordsLinked to original sources

arXiv2025

Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation

Prompt engineering has proven to be a crucial step in leveraging pretrained large language models (LLMs) in solving various real-world tasks. Numerous solutions have been proposed that seek to automate prompt engineering by using the model itself to edit prompts. However, the majority of state-of-the-art approaches are evaluated on tasks that require minimal prompt templates and on very large and highly capable LLMs. In contrast, solving complex tasks that require detailed information to be included in the prompt increases the amount of text that needs to be optimised. Furthermore, smaller models have been shown to be more sensitive to prompt design. To address these challenges, we propose an evolutionary search approach to automated discrete prompt optimisation consisting of two phases. In the first phase, grammar-guided genetic programming is invoked to synthesise prompt-creating programmes by searching the space of programmes populated by function compositions of syntactic, dictionary-based and LLM-based prompt-editing functions. In the second phase, local search is applied to explore the neighbourhoods of best-performing programmes in an attempt to further fine-tune their performance. Our approach outperforms three state-of-the-art prompt optimisation approaches, PromptWizard, OPRO, and RL-Prompt, on three relatively small general-purpose LLMs in four domain-specific challenging tasks. We also illustrate several examples where these benchmark methods suffer relatively severe performance degradation, while our approach improves performance in almost all task-model combinations, only incurring minimal degradation when it does not.

cs.CL↗

arXiv2024

Regularized Multi-output Gaussian Convolution Process with Domain Adaptation

Multi-output Gaussian process (MGP) has been attracting increasing attention as a transfer learning method to model multiple outputs. Despite its high flexibility and generality, MGP still faces two critical challenges when applied to transfer learning. The first one is negative transfer, which occurs when there exists no shared information among the outputs. The second challenge is the input domain inconsistency, which is commonly studied in transfer learning yet not explored in MGP. In this paper, we propose a regularized MGP modeling framework with domain adaptation to overcome these challenges. More specifically, a sparse covariance matrix of MGP is proposed by using convolution process, where penalization terms are added to adaptively select the most informative outputs for knowledge transfer. To deal with the domain inconsistency, a domain adaptation method is proposed by marginalizing inconsistent features and expanding missing features to align the input domains among different outputs. Statistical properties of the proposed method are provided to guarantee the performance practically and asymptotically. The proposed framework outperforms state-of-the-art benchmarks in comprehensive simulation studies and one real case study of a ceramic manufacturing process. The results demonstrate the effectiveness of our method in dealing with both the negative transfer and the domain inconsistency.

stat.ML↗

arXiv2024

Decision algorithms for reversibility of one-dimensional non-linear cellular automata under null boundary conditions

The property of reversibility is quite meaningful for the classic theoretical computer science model, cellular automata. For the reversibility problem for a CA under null boundary conditions, while linear rules have been studied a lot, the non-linear rules remain unexplored at present. The paper investigates the reversibility problem of general one-dimensional CA on a finite field $\mathbb{Z}_p$, and proposes an approach to optimize the Amoroso's infinite CA surjectivity detection algorithm. This paper proposes algorithms for deciding the reversibility of one-dimensional CA under null boundary conditions. We propose a method to decide the strict reversibility of one-dimensional CA under null boundary conditions. We also provide a bucket chain based algorithm for calculating the reversibility function of one-dimensional CA under null boundary conditions. These decision algorithms work for not only linear rules but also non-linear rules. In addition, it has been confirmed that the reversibility function always has a period, and its periodicity is related to the periodicity of the corresponding bucket chain. Some of our experiment results of reversible CA are presented in the paper, complementing and validating the theoretical aspects, and thereby further supporting the research conclusions of this paper.

cs.CC↗

arXiv2023

Automatic detection of aerial survey ground control points based on Yolov5-OBB

The use of ground control points (GCPs) for georeferencing is the most common strategy in unmanned aerial vehicle (UAV) photogrammetry, but at the same time their collection represents the most time-consuming and expensive part of UAV campaigns. Recently, deep learning has been rapidly developed in the field of small object detection. In this letter, to automatically extract coordinates information of ground control points (GCPs) by detecting GCP-markers in UAV images, we propose a solution that uses a deep learning-based architecture, YOLOv5-OBB, combined with a confidence threshold filtering algorithm and an optimal ranking algorithm. We applied our proposed method to a dataset collected by DJI Phantom 4 Pro drone and obtained good detection performance with the mean Average Precision (AP) of 0.832 and the highest AP of 0.982 for the cross-type GCP-markers. The proposed method can be a promising tool for future implementation of the end-to-end aerial triangulation process.

cs.CV↗

arXiv2022

A New Radar Signal Multiparameter-Based Deinterleaving Method

Radar signal deinterleaving has been extensively and thoroughly investigated in the electronic reconnaissance field. In this work, a new radar signal multiparameter-based deinterleaving method is proposed. In this method, semantic information composed of the pulse repetition interval (PRI), pulse width (PW), radio frequency (RF), and pulse amplitude (PA) of a radar signal is used to deinterleave radar signals. A bidirectional gated recurrent unit (BGRU) is employed, and the difference of time of arrival (DTOA)/RF, DTOA/PW, and DTOA/PA of the pulse stream are input into the BGRU. Based on the semantic information contained in different radar signal types, each pulse in the obtained pulse stream is classified according to the semantic information category, and the radar signals are deinterleaved. Compared to the PRI-based deinterleaving methods, the proposed method utilizes the multidimensional information of radar signals. As a result, higher deinterleaving accuracy is achieved. Compared to other existing radar signal multiparameter-based deinterleaving methods, the proposed method can adapt to radar signals with complex parameter features as well as to complex signal environments, and can complete the use of multiparameter in one step.

eess.SP↗

arXiv2022

A Radar Signal Deinterleaving Method Based on Semantic Segmentation with Neural Network

Radar signal deinterleaving is an important part of electronic reconnaissance. This study proposes a new radar signal deinterleaving method based on semantic segmentation, which we call "semantic segmentation deinterleaving" (SSD). We select representative sequence modeling neural network (NN) architectures and input the difference of time of arrival of the pulse stream into them. According to semantics contained in different radar signal types, each pulse in the pulse stream is marked according to the category of semantics contained, and radar signals are deinterleaved. Compared to the traditional deinterleaving method, the SSD method can adapt to complex pulse repetition interval (PRI) modulation environments without searching the PRI or PRI period. Multiple rounds of search and merging operation are not required for radar signals with multiple pulses in a period. Compared to other deinterleaving methods based on NNs, the SSD method does not need to digitize the data and train a network for each target type. The SSD method also does not need to iterate input and output data. The proposed method has high robustness to pulse loss and noise pulses. This research also shows that recurrent NNs still have more advantages than convolutional NNs in this sequence modeling task.

eess.SP↗

arXiv2018

Unpaired Photo-to-Caricature Translation on Faces in the Wild

Recently, image-to-image translation has been made much progress owing to the success of conditional Generative Adversarial Networks (cGANs). And some unpaired methods based on cycle consistency loss such as DualGAN, CycleGAN and DiscoGAN are really popular. However, it's still very challenging for translation tasks with the requirement of high-level visual information conversion, such as photo-to-caricature translation that requires satire, exaggeration, lifelikeness and artistry. We present an approach for learning to translate faces in the wild from the source photo domain to the target caricature domain with different styles, which can also be used for other high-level image-to-image translation tasks. In order to capture global structure with local statistics while translation, we design a dual pathway model with one coarse discriminator and one fine discriminator. For generator, we provide one extra perceptual loss in association with adversarial loss and cycle consistency loss to achieve representation learning for two different domains. Also the style can be learned by the auxiliary noise input. Experiments on photo-to-caricature translation of faces in the wild show considerable performance gain of our proposed method over state-of-the-art translation methods as well as its potential real applications.

cs.CV↗