arXiv subjects

Jiaxuan Liu

Publications and source records attributed to Jiaxuan Liu.

28 records · Page 2Linked to original sources

arXiv2025

PaddleOCR 3.0 Technical Report

This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR 3.0 presents three major solutions: (1) PP-OCRv5 for multilingual text recognition, (2) PP-StructureV3 for hierarchical document parsing, and (3) PP-ChatOCRv4 for key information extraction. Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs. In addition to offering a high-quality OCR model library, PaddleOCR 3.0 provides efficient tools for training, inference, and deployment, supports heterogeneous hardware acceleration, and enables developers to easily build intelligent document applications.

cs.CV↗

arXiv2025

Materials discovery acceleration by using condition generative methodology

With the rapid advancement of AI technologies, generative models have been increasingly employed in the exploration of novel materials. By integrating traditional computational approaches such as density functional theory (DFT) and molecular dynamics (MD), existing generative models, including diffusion models and autoregressive models, have demonstrated remarkable potential in the discovery of novel materials. However, their efficiency in goal-directed materials design remains suboptimal. In this work we developed a highly transferable, efficient and robust conditional generation framework, PODGen, by integrating a general generative model with multiple property prediction models. Based on PODGen, we designed a workflow for the high-throughput crystals conditional generation which is used to search new topological insulators (TIs). Our results show that the success rate of generating TIs using our framework is 5.3 times higher than that of the unconstrained approach. More importantly, while general methods rarely produce gapped TIs, our framework succeeds consistently, highlighting an effectively $\infty$ improvement. This demonstrates that conditional generation significantly enhances the efficiency of targeted material discovery. Using this method, we generated tens of thousands of new topological materials and conducted further first-principles calculations on those with promising application potential. Furthermore, we identified promising, synthesizable topological (crystalline) insulators such as CsHgSb, NaLaB$_{12}$, Bi$_4$Sb$_2$Se$_3$, Be$_3$Ta$_2$Si and Be$_2$W.

cond-mat.mtrl-sci↗

arXiv2025

DPmoire: A tool for constructing accurate machine learning force fields in moiré systems

In moiré systems, the impact of lattice relaxation on electronic band structures is significant, yet the computational demands of first-principles relaxation are prohibitively high due to the large number of atoms involved. To address this challenge, We introduce a robust methodology for the construction of machine learning potentials specifically tailored for moiré structures and present an open-source software package DPmoire designed to facilitate this process. Utilizing this package, we have developed machine learning force fields (MLFFs) for MX$_2$ (M = Mo, W; X = S, Se, Te) materials. Our approach not only streamlines the computational process but also ensures accurate replication of the detailed electronic and structural properties typically observed in density functional theory (DFT) relaxations. The MLFFs were rigorously validated against standard DFT results, confirming their efficacy in capturing the complex interplay of atomic interactions within these layered materials. This development not only enhances our ability to explore the physical properties of moiré systems with reduced computational overhead but also opens new avenues for the study of relaxation effects and their impact on material properties in two-dimensional layered structures.

cond-mat.mes-hall↗

arXiv2024

DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles

Human speech exhibits rich and flexible prosodic variations. To address the one-to-many mapping problem from text to prosody in a reasonable and flexible manner, we propose DiffStyleTTS, a multi-speaker acoustic model based on a conditional diffusion module and an improved classifier-free guidance, which hierarchically models speech prosodic features, and controls different prosodic styles to guide prosody prediction. Experiments show that our method outperforms all baselines in naturalness and achieves superior synthesis speed compared to three diffusion-based baselines. Additionally, by adjusting the guiding scale, DiffStyleTTS effectively controls the guidance intensity of the synthetic prosody.

cs.SD↗

arXiv2024

Universal Moiré-Model-Building Method without Fitting: Application to Twisted MoTe$_2$ and WSe$_2$

We develop a comprehensive method to construct analytical continuum models for moiré systems directly from first-principle calculations without any parameter fitting. The core idea of this method is to interpret the terms in the continuum model as a basis, allowing us to determine model parameters as coefficients of this basis through Gram-Schmidt orthogonalization. We apply our method to twisted MoTe$_2$ and WSe$_2$ with twist angles ranging from 2.13$^\circ$ to 3.89$^\circ$, producing continuum models that exhibit excellent agreement with both energy bands and wavefunctions obtained from first-principles calculations. We further propose a strategy to integrate out the higher-energy degrees of freedom to reduce the number of the parameters in the model without sacrificing the accuracy for low-energy bands. Our findings reveal that decreasing twist angles typically need an increasing number of harmonics in the moiré potentials to accurately replicate first-principles results. We provide parameter values for all derived continuum models, facilitating further robust many-body calculations. Our approach is general and applicable to any commensurate moiré materials accessible by first-principles calculations.

cond-mat.mes-hall↗

arXiv2024

Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation has attracted increasing attention in computer vision, aiming to leverage unlabeled data through latent supervision. To achieve this goal, prototype-based classification has been introduced and achieved lots of success. However, the current approaches isolate prototype generation from the main training framework, presenting a non-end-to-end workflow. Furthermore, most methods directly perform the K-Means clustering on features to generate prototypes, resulting in their proximity to category semantic centers, while overlooking the clear delineation of class boundaries. To address the above problems, we propose a novel end-to-end boundary-refined prototype generation (BRPG) method. Specifically, we perform online clustering on sampled features to incorporate the prototype generation into the whole training framework. In addition, to enhance the classification boundaries, we sample and cluster high- and low-confidence features separately based on confidence estimation, facilitating the generation of prototypes closer to the class boundaries. Moreover, an adaptive prototype optimization strategy is proposed to increase the number of prototypes for categories with scattered feature distributions, which further refines the class boundaries. Extensive experiments demonstrate the remarkable robustness and scalability of our method across diverse datasets, segmentation networks, and semi-supervised frameworks, outperforming the state-of-the-art approaches on three benchmark datasets: PASCAL VOC 2012, Cityscapes and MS COCO. The code is available at https://github.com/djh-dzxw/BRPG.

cs.CV↗

arXiv2024

DroidBot-GPT: GPT-powered UI Automation for Android

This paper introduces DroidBot-GPT, a tool that utilizes GPT-like large language models (LLMs) to automate the interactions with Android mobile applications. Given a natural language description of a desired task, DroidBot-GPT can automatically generate and execute actions that navigate the app to complete the task. It works by translating the app GUI state information and the available actions on the smartphone screen to natural language prompts and asking the LLM to make a choice of actions. Since the LLM is typically trained on a large amount of data including the how-to manuals of diverse software applications, it has the ability to make reasonable choices of actions based on the provided information. We evaluate DroidBot-GPT with a self-created dataset that contains 33 tasks collected from 17 Android applications spanning 10 categories. It can successfully complete 39.39% of the tasks, and the average partial completion progress is about 66.76%. Given the fact that our method is fully unsupervised (no modification required from both the app and the LLM), we believe there is great potential to enhance automation performance with better app development paradigms and/or custom model training.

cs.SE↗

arXiv2023

Moiré Fractional Chern Insulators II: First-principles Calculations and Continuum Models of Rhombohedral Graphene Superlattices

The experimental discovery of fractional Chern insulators (FCIs) in rhombohedral pentalayer graphene twisted on hexagonal boron nitride (hBN) has preceded theoretical prediction. Supported by large-scale first principles relaxation calculations at the experimental twist angle of $0.77^\circ$, we obtain an accurate continuum model of $n=3,4,5,6,7$ layer rhombohedral graphene-hBN moiré systems. Focusing on the pentalayer case, we analytically explain the robust $|C|=0,5$ Chern numbers seen in the low-energy single-particle bands and their flattening with displacement field, making use of a minimal two-flavor continuum Hamiltonian derived from the full model. We then predict nonzero valley Chern numbers at the $ν= -4,0$ insulators observed in experiment. Our analysis makes clear the importance of displacement field and the moiré potential in producing localized "heavy fermion" charge density in the top valence band, in addition to the nearly free conduction band. Lastly, we study doubly aligned devices as additional platforms for moiré FCIs with higher Chern number bands.

cond-mat.mes-hall↗

arXiv2023

Moiré Fractional Chern Insulators I: First-principles calculations and Continuum Models of Twisted Bilayer MoTe$_2$

Recent experiments observed fractional Chern insulators (FCI) in twisted bilayer MoTe$_2$ at zero magnetic field, yet even the single-particle model of this material is controversial, leading to unreliable predictions of the experimental phase diagram as discussed in [Yu et al., 2023]. In this light, we revisit the single-particle model of twisted bilayer MoTe$_2$. Utilizing large-scale density functional theory, we calculate the band structure of twisted AA-stacked bilayer MoTe$_2$ at various twist angles relevant to experiment. We find that a band inversion occurs near $4.41^\circ$ between the second and third bands. Our ab initio band structure is in qualitative agreement with [Wang et al., 2023], but shows important differences in the remote bands and in the $Γ$ valley. We incorporate two higher harmonic terms into the continuum model to capture the highest 3 valence bands per valley. We confirm that the two highest valence bands per valley have opposite Chern numbers with $|C|=1$ for small angles, and also use our model to predict a variety of Chern states in the remote bands accessible by displacement field. Finally, we perform DFT calculations and build models for the AB stacking configuration. Our work serves as a foundation for accurate determination of the correlated phases in twisted bilayer MoTe$_2$.

cond-mat.mes-hall↗

arXiv2023

The News Delivery Channel Recommendation Based on Granular Neural Network

With the continuous maturation and expansion of neural network technology, deep neural networks have been widely utilized as the fundamental building blocks of deep learning in a variety of applications, including speech recognition, machine translation, image processing, and the creation of recommendation systems. Therefore, many real-world complex problems can be solved by the deep learning techniques. As is known, traditional news recommendation systems mostly employ techniques based on collaborative filtering and deep learning, but the performance of these algorithms is constrained by the sparsity of the data and the scalability of the approaches. In this paper, we propose a recommendation model using granular neural network model to recommend news to appropriate channels by analyzing the properties of news. Specifically, a specified neural network serves as the foundation for the granular neural network that the model is considered to be build. Different information granularities are attributed to various types of news material, and different information granularities are released between networks in various ways. When processing data, granular output is created, which is compared to the interval values pre-set on various platforms and used to quantify the analysis's effectiveness. The analysis results could help the media to match the proper news in depth, maximize the public attention of the news and the utilization of media resources.

cs.IR↗