arXiv subjects

Hui Liu

Publications and source records attributed to Hui Liu.

At least 325 records · Page 18Linked to original sources

arXiv2024

Deep Diversity-Enhanced Feature Representation of Hyperspectral Images

In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature diversity. Specifically, based on the theoretical formulation that feature diversity is correlated with the rank of the unfolded kernel matrix, we rectify 3D convolution by modifying its topology to enhance the rank upper-bound. This modification yields a rank-enhanced spatial-spectral symmetrical convolution set (ReS$^3$-ConvSet), which not only learns diverse and powerful feature representations but also saves network parameters. Additionally, we also propose a novel diversity-aware regularization (DA-Reg) term that directly acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed ReS$^3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks, including denoising, spatial super-resolution, and classification. Extensive experiments show that the proposed approaches outperform state-of-the-art methods both quantitatively and qualitatively to a significant extent. The code is publicly available at https://github.com/jinnh/ReSSS-ConvSet.

cs.CV↗

arXiv2024

G$ \mathbf{^2} $VD Planner: Efficient Motion Planning With Grid-based Generalized Voronoi Diagrams

In this paper, an efficient motion planning approach with grid-based generalized Voronoi diagrams (G$ \mathbf{^2} $VD) is newly proposed for mobile robots. Different from existing approaches, the novelty of this work is twofold: 1) a new state lattice-based path searching approach is proposed, in which the search space is reduced to a novel Voronoi corridor to further improve the search efficiency; 2) an efficient quadratic programming-based path smoothing approach is presented, wherein the clearance to obstacles is considered to improve the path clearance of hard-constrained path smoothing approaches. We validate the efficiency and smoothness of our approach in various challenging simulation scenarios and outdoor environments. It is shown that the computational efficiency is improved by 17.1% in the path searching stage, and path smoothing with the proposed approach is 6.6 times faster than an advanced sparse-banded structure-based path smoothing approach and 53.3 times faster than the popular timed-elastic-band planner. A video showing outdoor navigation on our campus is available at https://youtu.be/iMXGthgvp58.

cs.RO↗

arXiv2024

Modulating trap properties by Cr3+-doping in Zn2SiO4: Mn2+ nano phosphor for optical information storage

Photo stimulated luminescent materials are one of the most attractive alternatives for next generation optical information storage technologies. However, there are still some challenges in regulating appropriate energy levels in luminescent materials for optical information storage. Herein, a green emission nanophosphor Zn2SiO4: Cr3+, Mn2+ with the trap depth of 1.05 eV, fulfilling the requirements for optical information storage, was fabricated for the first time through the solution combustion method and subsequent heat treatment at 1000 degree centigrade for 2h. The crystal structure, micromorphology, photoluminescence (PL), photoluminescence excitation (PLE), and afterglow properties of Zn2SiO4: xCr3+, yMn2+ were studied systematically. By applying the strategy of trap depth engineering, high trap density with proper trap depth was observed when Cr3+ ions were introduced into Zn2SiO4: Mn2+. Thermoluminescence (TL) glow curve analysis through the initial rise (IR) method was conducted to gain some insight into the information of traps. As proof of application, information storage was experimentally achieved by choosing 275 nm illumination for information writing and 980 nm NIR excitation for information reading. The results indicate that Zn2SiO4: Cr3+, Mn2+ phosphor holds promise for potential applications in the field of optical information storage.

cond-mat.mtrl-sci↗

arXiv2024

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models

Text-to-image generative models, especially those based on latent diffusion models (LDMs), have demonstrated outstanding ability in generating high-quality and high-resolution images from textual prompts. With this advancement, various fine-tuning methods have been developed to personalize text-to-image models for specific applications such as artistic style adaptation and human face transfer. However, such advancements have raised copyright concerns, especially when the data are used for personalization without authorization. For example, a malicious user can employ fine-tuning techniques to replicate the style of an artist without consent. In light of this concern, we propose FT-Shield, a watermarking solution tailored for the fine-tuning of text-to-image diffusion models. FT-Shield addresses copyright protection challenges by designing new watermark generation and detection strategies. In particular, it introduces an innovative algorithm for watermark generation. It ensures the seamless transfer of watermarks from training images to generated outputs, facilitating the identification of copyrighted material use. To tackle the variability in fine-tuning methods and their impact on watermark detection, FT-Shield integrates a Mixture of Experts (MoE) approach for watermark detection. Comprehensive experiments validate the effectiveness of our proposed FT-Shield.

cs.CV↗

arXiv2024

A Survey of Deep Learning Based Software Refactoring

Refactoring is one of the most important activities in software engineering which is used to improve the quality of a software system. With the advancement of deep learning techniques, researchers are attempting to apply deep learning techniques to software refactoring. Consequently, dozens of deep learning-based refactoring approaches have been proposed. However, there is a lack of comprehensive reviews on such works as well as a taxonomy for deep learning-based refactoring. To this end, in this paper, we present a survey on deep learning-based software refactoring. We classify related works into five categories according to the major tasks they cover. Among these categories, we further present key aspects (i.e., code smell types, refactoring types, training strategies, and evaluation) to give insight into the details of the technologies that have supported refactoring through deep learning. The classification indicates that there is an imbalance in the adoption of deep learning techniques for the process of refactoring. Most of the deep learning techniques have been used for the detection of code smells and the recommendation of refactoring solutions as found in 56.25\% and 33.33\% of the literature respectively. In contrast, only 6.25\% and 4.17\% were towards the end-to-end code transformation as refactoring and the mining of refactorings, respectively. Notably, we found no literature representation for the quality assurance for refactoring. We also observe that most of the deep learning techniques have been used to support refactoring processes occurring at the method level whereas classes and variables attracted minimal attention. Finally, we discuss the challenges and limitations associated with the employment of deep learning-based refactorings and present some potential research opportunities for future work.

cs.SE↗

arXiv2024

Modeling Selective Feature Attention for Representation-based Siamese Text Matching

Representation-based Siamese networks have risen to popularity in lightweight text matching due to their low deployment and inference costs. While word-level attention mechanisms have been implemented within Siamese networks to improve performance, we propose Feature Attention (FA), a novel downstream block designed to enrich the modeling of dependencies among embedding features. Employing "squeeze-and-excitation" techniques, the FA block dynamically adjusts the emphasis on individual features, enabling the network to concentrate more on features that significantly contribute to the final classification. Building upon FA, we introduce a dynamic "selection" mechanism called Selective Feature Attention (SFA), which leverages a stacked BiGRU Inception structure. The SFA block facilitates multi-scale semantic extraction by traversing different stacked BiGRU layers, encouraging the network to selectively concentrate on semantic information and embedding features across varying levels of abstraction. Both the FA and SFA blocks offer a seamless integration capability with various Siamese networks, showcasing a plug-and-play characteristic. Experimental evaluations conducted across diverse text matching baselines and benchmarks underscore the indispensability of modeling feature attention and the superiority of the "selection" mechanism.

cs.CL↗

arXiv2024

Symmetric periodic Reeb orbits on the sphere

A long standing conjecture in Hamiltonian Dynamics states that every contact form on the standard contact sphere $S^{2n+1}$ has at least $n+1$ simple periodic Reeb orbits. In this work, we consider a refinement of this problem when the contact form has a suitable symmetry and we ask if there are at least $n+1$ simple symmetric periodic orbits. We show that there is at least one symmetric periodic orbit for any contact form and at least two symmetric closed orbits whenever the contact form is dynamically convex.

math.SG↗

arXiv2024

Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective

Molecule discovery plays a crucial role in various scientific fields, advancing the design of tailored materials and drugs. However, most of the existing methods heavily rely on domain experts, require excessive computational cost, or suffer from sub-optimal performance. On the other hand, Large Language Models (LLMs), like ChatGPT, have shown remarkable performance in various cross-modal tasks due to their powerful capabilities in natural language understanding, generalization, and in-context learning (ICL), which provides unprecedented opportunities to advance molecule discovery. Despite several previous works trying to apply LLMs in this task, the lack of domain-specific corpus and difficulties in training specialized LLMs still remain challenges. In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning. MolReGPT leverages the principle of molecular similarity to retrieve similar molecules and their text descriptions from a local database to enable LLMs to learn the task knowledge from context examples. We evaluate the effectiveness of MolReGPT on molecule-caption translation, including molecule understanding and text-based molecule generation. Experimental results show that compared to fine-tuned models, MolReGPT outperforms MolT5-base and is comparable to MolT5-large without additional training. To the best of our knowledge, MolReGPT is the first work to leverage LLMs via in-context learning in molecule-caption translation for advancing molecule discovery. Our work expands the scope of LLM applications, as well as providing a new paradigm for molecule discovery and design.

cs.CL↗

arXiv2024

Explanation based Bias Decoupling Regularization for Natural Language Inference

The robustness of Transformer-based Natural Language Inference encoders is frequently compromised as they tend to rely more on dataset biases than on the intended task-relevant features. Recent studies have attempted to mitigate this by reducing the weight of biased samples during the training process. However, these debiasing methods primarily focus on identifying which samples are biased without explicitly determining the biased components within each case. This limitation restricts those methods' capability in out-of-distribution inference. To address this issue, we aim to train models to adopt the logic humans use in explaining causality. We propose a simple, comprehensive, and interpretable method: Explanation based Bias Decoupling Regularization (EBD-Reg). EBD-Reg employs human explanations as criteria, guiding the encoder to establish a tripartite parallel supervision of Distinguishing, Decoupling and Aligning. This method enables encoders to identify and focus on keywords that represent the task-relevant features during inference, while discarding the residual elements acting as biases. Empirical evidence underscores that EBD-Reg effectively guides various Transformer-based encoders to decouple biases through a human-centric lens, significantly surpassing other methods in terms of out-of-distribution inference capabilities.

cs.CL↗

arXiv2024

Sparse Variable Selection on High Dimensional Heterogeneous Data with Tree Structured Responses

We consider the problem of sparse variable selection on high dimension heterogeneous data sets, which has been taking on renewed interest recently due to the growth of biological and medical data sets with complex, non-i.i.d. structures and huge quantities of response variables. The heterogeneity is likely to confound the association between explanatory variables and responses, resulting in enormous false discoveries when Lasso or its variants are naïvely applied. Therefore, developing effective confounder correction methods is a growing heat point among researchers. However, ordinarily employing recent confounder correction methods will result in undesirable performance due to the ignorance of the convoluted interdependency among response variables. To fully improve current variable selection methods, we introduce a model, the tree-guided sparse linear mixed model, that can utilize the dependency information from multiple responses to explore how specifically clusters are and select the active variables from heterogeneous data. Through extensive experiments on synthetic and real data sets, we show that our proposed model outperforms the existing methods and achieves the highest ROC area.

stat.ME↗

arXiv2024

RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering

We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. RainyScape consists of two main modules: a neural rendering module and a rain-prediction module that incorporates a predictor network and a learnable latent embedding that captures the rain characteristics of the scene. Specifically, based on the spectral bias property of neural networks, we first optimize the neural rendering pipeline to obtain a low-frequency scene representation. Subsequently, we jointly optimize the two modules, driven by the proposed adaptive direction-sensitive gradient-based reconstruction loss, which encourages the network to distinguish between scene details and rain streaks, facilitating the propagation of gradients to the relevant components. Extensive experiments on both the classic neural radiance field and the recently proposed 3D Gaussian splatting demonstrate the superiority of our method in effectively eliminating rain streaks and rendering clean images, achieving state-of-the-art performance. The constructed high-quality dataset and source code will be publicly available.

cs.CV↗

arXiv2024

Dual-comb mode-locked Yb:CALGO laser based on cavity-shared configuration with separated end mirrors

Dual-comb spectroscopy typically requires the utilization of two independent and phase-locked femtosecond lasers, resulting in a complex and expensive system that hinders its industrial applications. Single-cavity dual-comb lasers are considered as one of the primary solution to simplify the system. However, controlling the crucial parameter of difference in repetition rates remains challenging. In this study, we present a dual-comb mode-locked Yb:CALGO laser based on a cavity-shared configuration with separated end mirrors. We employ two pairs of end mirrors and two thin-film polarizers angled at 45 degrees to the cavity axis, leading to separating the cross-polarized laser modes. We achieve simultaneous operation of two combs at approximately 1040 nm with pulse durations of around 400 fs and an average power exceeding 1 W. The repetition rates are approximately 59 MHz and their difference can be easily tuned from zero up to the MHz range. By effectively canceling out common mode noises, we observe minimal fluctuation in the repetition rate difference with a standard deviation of about 1.9 Hz over ten minutes, while experiencing fluctuations in repetition rates as large as 90 Hz. We demonstrate the capabilities of this system by utilizing the free-running dual-comb setup for asynchronous optical sampling on a saturable absorber and measuring etalon transmission spectrum. This system allows for simple and independent control of the repetition rates and their difference during operation, facilitating the selection of optimal repetition rate difference and implementation of phase-locking loops. This advancement paves the way for the development of simple yet high-performance dual-comb laser sources.

physics.optics↗

arXiv2024

Resolution enhancement of SOHO/MDI Magnetograms

Research on the solar magnetic field and its effects on solar dynamo mechanisms and space weather events has benefited from the continual improvements in instrument resolution and measurement frequency. The augmentation and assimilation of historical observational data timelines also play a significant role in understanding the patterns of solar magnetic field variation. Within the realm of astronomical data processing, superresolution reconstruction refers to the process of using a substantial corpus of training data to learn the nonlinear mapping between low-resolution and high-resolution images,thereby achieving higher-resolution astronomical images. This paper is an application study in highdimensional non-linear regression. Deep learning models were employed to perform SR modeling on SOHO/MDI magnetograms and SDO/HMI magnetograms, thus reliably achieving resolution enhancement of full-disk SOHO/MDI magnetograms and enhancing the image resolution to obtain more detailed information. For this study, a dataset comprising 9717 pairs of data from April 2010 to February 2011 was used as the training set,1332 pairs from March 2011 were used as the validation set, and 1,034 pairs from April 2011 were used as the test set. After data preprocessing, we randomly cropped 128x128 sub-images as the LR from the full-disk MDI magnetograms, and the corresponding 512x512 sub-images as HR from the HMI full-disk magnetograms for model training. The tests conducted have shown that the study successfully produced reliable 4x super-resolution reconstruction of full-disk MDI magnetograms.The MESR model'sresults (0.911) were highly correlated with the target HMI magnetographs as indicated by the correlation coefficient values. Furthermore, the method achieved the best PSNR, SSIM, MAE and RMSE values, indicating that the MESR model can effectively reconstruct magnetog.

astro-ph.SR↗

arXiv2024

Content Knowledge Identification with Multi-Agent Large Language Models (LLMs)

Teachers' mathematical content knowledge (CK) is of vital importance and need in teacher professional development (PD) programs. Computer-aided asynchronous PD systems are the most recent proposed PD techniques, which aim to help teachers improve their PD equally with fewer concerns about costs and limitations of time or location. However, current automatic CK identification methods, which serve as one of the core techniques of asynchronous PD systems, face challenges such as diversity of user responses, scarcity of high-quality annotated data, and low interpretability of the predictions. To tackle these challenges, we propose a Multi-Agent LLMs-based framework, LLMAgent-CK, to assess the user responses' coverage of identified CK learning goals without human annotations. By taking advantage of multi-agent LLMs in strong generalization ability and human-like discussions, our proposed LLMAgent-CK presents promising CK identifying performance on a real-world mathematical CK dataset MaCKT. Moreover, our case studies further demonstrate the working of the multi-agent framework.

cs.AI↗

arXiv2024

Proof of Hofer-Wysocki-Zehnder's two or infinity conjecture

We prove that every Reeb flow on a closed connected three-manifold has either two or infinitely many simple periodic orbits, assuming that the associated contact structure has torsion first Chern class. As a special case, we prove a conjecture of Hofer-Wysocki-Zehnder published in 2003 asserting that a smooth and autonomous Hamiltonian flow on $\mathbb{R}^4$ has either two or infinitely many simple periodic orbits on any regular compact connected energy level that is transverse to the radial vector field. Other corollaries settle some old problems about Finsler metrics: we show that every Finsler metric on $S^2$ has either two or infinitely many prime closed geodesics; and we show that a Finsler metric on $S^2$ with at least one closed geodesic that is not irrationally elliptic must have infinitely many prime closed geodesics. The novelty of our work is that we do not make any nondegeneracy hypotheses.

math.SG↗

arXiv2024

Gap and magnetic engineering via doping and pressure in tuning the colossal magnetoresistance in (Mn$_{1-x}$Mg$_x$)$_3$Si$_2$Te$_6$

Ferrimagnetic nodal-line semiconductor Mn$_3$Si$_2$Te$_6$ keeps the records of colossal magnetoresistance (CMR) and angular magnetoresistance (AMR). Here we report tuning the electronic transport properties via doping and pressure in (Mn$_{1-x}$Mg$_x$)$_3$Si$_2$Te$_6$. As the substitution of nonmagnetic Mg$^{2+}$ for magnetic Mn$^{2+}$, ferrimagnetic transition temperature $T_C$ gradually decreases, while the resistivity increases significantly. At the same time, the CMR and AMR are both enhanced for the low-doping compositions (e.g., $x = 0.1$ and 0.2), which can be attributed to doping-induced broadening of the band gap and a larger variation range of the resistivity when undergoing a metal-insulator transition by applying a magnetic field along the $c$ axis. On the contrary, $T_C$ rises with increasing pressure due to the enhancement of the magnetic exchange interactions until a structural transition occurs at $\sim$13 GPa. Meanwhile, the activation gap is lowered under pressure and the magnetoresistance is decreased dramatically above 6 GPa where the gap is closed. At 20 and 26 GPa, evidences for a superconducting transition at $\sim$5 K are observed. The results reveal that doping and pressure are effective methods to tune the activation gap, and correspondingly, the CMR and AMR in nodal-line semiconductors, providing an approach to investigate the magnetoresistance materials for novel spintronic devices.

cond-mat.mtrl-sci↗

arXiv2024

Global smooth solution for the 3D generalized tropical climate model with partial viscosity and damping

The three-dimensional generalized tropical climate model with partial viscosity and damping is considered in this paper. Global well-posedness of solutions of the three-dimensional generalized tropical climate model with partial viscosity and damping is proved for $α\geq\frac{3}{2}$ and $β\geq4$. Global smooth solution of the three-dimensional generalized tropical climate model with partial viscosity and damping is proved in $H^s(\mathbb R^3)$ $(s>2)$ for $α\geq\frac{3}{2}$ and $4\leqβ\leq5$.

math.AP↗

arXiv2024

SIFiD: Reassess Summary Factual Inconsistency Detection with LLM

Ensuring factual consistency between the summary and the original document is paramount in summarization tasks. Consequently, considerable effort has been dedicated to detecting inconsistencies. With the advent of Large Language Models (LLMs), recent studies have begun to leverage their advanced language understanding capabilities for inconsistency detection. However, early attempts have shown that LLMs underperform traditional models due to their limited ability to follow instructions and the absence of an effective detection methodology. In this study, we reassess summary inconsistency detection with LLMs, comparing the performances of GPT-3.5 and GPT-4. To advance research in LLM-based inconsistency detection, we propose SIFiD (Summary Inconsistency Detection with Filtered Document) that identify key sentences within documents by either employing natural language inference or measuring semantic similarity between summaries and documents.

cs.CL↗