arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 559 records · Page 31Linked to original sources

arXiv2024

Three-dimensional Coupled PT-symmetric Electronic Resonators

In this article, the non-Hermitian characteristics of three-dimensional PT-symmetric coupled electronic resonators are theoretically analyzed. First, the concept of non-Hermitian PT symmetry is illustrated in the context of electronics using a pair of coupled electronic resonators. Two typical configurations of parallel-coupled PT-symmetric electronic trimers are then analyzed. The results indicate that, for the planar configuration, the system can exhibit two phase transitions as the coupling coefficient or gain-loss parameter changes, different from the linear configuration. By comparing system equations based on coupled-mode theory and circuit theory, it is shown that high dimensionality alone is not a sufficient condition for the existence of a higher-order exceptional point; an approximation condition is also required. A modified exceptional point is proposed, and the approximation conditions for the mean deviation $D$ for the real part of the three eigenfrequencies, satisfying $D \leq 1\%$ and $D \leq 0.1\%$, are discussed, respectively. The theoretical results presented in this paper not only reveal the unique non-Hermitian characteristics of high-dimensional PT-symmetric electronic systems but also offer theoretical support for wireless power transmission and wireless sensing technologies.

physics.app-ph↗

arXiv2024

Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To address this limitation, we propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix. We utilize Householder transformations to construct orthogonal matrices that efficiently mimic the unitary matrices, requiring only a vector. The diagonal values are learned in a layer-wise manner, allowing them to flexibly capture the unique properties of each layer. This approach enables the generation of adaptation matrices with varying ranks across different layers, providing greater flexibility in adapting pre-trained models. Experiments on standard downstream vision tasks demonstrate that our method achieves promising fine-tuning performance.

cs.CV↗

arXiv2024

AutoGLM: Autonomous Foundation Agents for GUIs

We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models. Focusing on Web Browser and Phone as representative GUI scenarios, we have developed AutoGLM as a practical foundation agent system for real-world GUI interactions. Our approach integrates a comprehensive suite of techniques and infrastructures to create deployable agent systems suitable for user delivery. Through this development, we have derived two key insights: First, the design of an appropriate "intermediate interface" for GUI control is crucial, enabling the separation of planning and grounding behaviors, which require distinct optimization for flexibility and accuracy respectively. Second, we have developed a novel progressive training framework that enables self-evolving online curriculum reinforcement learning for AutoGLM. Our evaluations demonstrate AutoGLM's effectiveness across multiple domains. For web browsing, AutoGLM achieves a 55.2% success rate on VAB-WebArena-Lite (improving to 59.1% with a second attempt) and 96.2% on OpenTable evaluation tasks. In Android device control, AutoGLM attains a 36.2% success rate on AndroidLab (VAB-Mobile) and 89.7% on common tasks in popular Chinese APPs.

cs.HC↗

arXiv2024

COSMIC: A Galaxy Cluster Finding Algorithm Using Machine Learning

Building a comprehensive catalog of galaxy clusters is a fundamental task for the studies on the structure formation and galaxy evolution. In this paper, we present COSMIC (Cluster Optical Search using Machine Intelligence in Catalogs), an algorithm utilizing machine learning techniques to efficiently detect galaxy clusters. COSMIC involves two steps, including the identification of the brightest cluster galaxies and the estimation of the cluster richness. We train our models on the galaxy data from the Sloan Digital Sky Survey and WHL galaxy cluster catalog. Validated to a test data in the region of northern Galactic cap, COSMIC algorithm demonstrates a high completeness when cross-matching with previous cluster catalogs. Richness comparison with previous optical and X-ray measurements also demonstrated a tight correlation. Our methodology showcases robust performance in galaxy cluster detection and holds promising prospects for applications in upcoming large-scale surveys.

astro-ph.CO↗

arXiv2024

Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era

Generative AI has made significant progress in recent years, with text-guided content generation being the most practical as it facilitates interaction between human instructions and AI-generated content (AIGC). Thanks to advancements in text-to-image and 3D modeling technologies, like neural radiance field (NeRF), text-to-3D has emerged as a nascent yet highly active research field. Our work conducts a comprehensive survey on this topic and follows up on subsequent research progress in the overall field, aiming to help readers interested in this direction quickly catch up with its rapid development. First, we introduce 3D data representations, including both Structured and non-Structured data. Building on this pre-requisite, we introduce various core technologies to achieve satisfactory text-to-3D results. Additionally, we present mainstream baselines and research directions in recent text-to-3D technology, including fidelity, efficiency, consistency, controllability, diversity, and applicability. Furthermore, we summarize the usage of text-to-3D technology in various applications, including avatar generation, texture generation, scene generation and 3D editing. Finally, we discuss the agenda for the future development of text-to-3D.

cs.CV↗

arXiv2024

Forecasting Australian fertility by age, region, and birthplace

Fertility differentials by urban-rural residence and nativity of women in Australia significantly impact population composition at sub-national levels. We aim to provide consistent fertility forecasts for Australian women characterized by age, region, and birthplace. Age-specific fertility rates at the national and sub-national levels obtained from census data between 1981-2011 are jointly modeled and forecast by the grouped functional time series method. Forecasts for women of each region and birthplace are reconciled following the chosen hierarchies to ensure that results at various disaggregation levels consistently sum up to the respective national total. Coupling the region of residence disaggregation structure with the trace minimization reconciliation method produces the most accurate point and interval forecasts. In addition, age-specific fertility rates disaggregated by the birthplace of women show significant heterogeneity that supports the application of the grouped forecasting method.

stat.AP↗

arXiv2024

Revisiting the Velocity Dispersion-Size Relation in Molecular Cloud Structures

Structures in molecular ISM are observed to follow a power-law relation between the velocity dispersion and spatial size, known as Larson's first relation, which is often attributed to the turbulent nature of molecular ISM and imprints the dynamics of molecular cloud structures. Using the ${}^{13}\mathrm{CO}~(J=1-0)$ data from the Milky Way Imaging Scroll Painting survey, we built a sample with 360 structures having relatively accurate distances obtained from either the reddened background stars with Gaia parallaxes or associated maser parallaxes, spanning from $0.4$ to $\sim 15~\mathrm{kpc}$. Using this sample and about 0.3 million pixels, we analyzed the correlations between velocity dispersion, surface/column density, and spatial scales. Our structure-wise results show power-law indices smaller than 0.5 in both the $σ_v$-$R_{\mathrm{eff}}$ and $σ_v$-$R_{\mathrm{eff}} \cdot Σ$ relations. In the pixel-wise results, the $σ_v^{\mathrm{pix}}$ is statistically scaling with the beam physical size ($R_{\mathrm{s}} \equiv ΘD/2$) in form of $σ_v^{\mathrm{pix}} \propto R_{\mathrm{s}}^{0.43 \pm 0.03}$. Meanwhile, $σ_v^{\mathrm{pix}}$ in the inner Galaxy is statistically larger than the outer side. We also analyzed correlations between $σ_v^{\mathrm{pix}}$ and the $\mathrm{H_2}$ column density $N(\mathrm{H_2})$, finding that $σ_v^{\mathrm{pix}}$ stops increasing with $N(\mathrm{H_2})$ after $\gtrsim 10^{22}~{\mathrm{cm^{-2}}}$. The structures with and without high-column-density ($> 10^{22}~\mathrm{cm^{-2}}$) pixels show different $σ_v^{\mathrm{pix}} \propto N(\mathrm{H_2})^ξ$ relations, where the mean (std) $ξ$ values are $0.38~(0.14)$ and $0.62~(0.27)$, respectively.

astro-ph.GA↗

arXiv2024

The Solution for Single Object Tracking Task of Perception Test Challenge 2024

This report presents our method for Single Object Tracking (SOT), which aims to track a specified object throughout a video sequence. We employ the LoRAT method. The essence of the work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. We train our model using the extensive LaSOT and GOT-10k datasets, which provide a solid foundation for robust performance. Additionally, we implement the alpha-refine technique for post-processing the bounding box outputs. Although the alpha-refine method does not yield the anticipated results, our overall approach achieves a score of 0.813, securing first place in the competition.

cs.CV↗

arXiv2024

FAMSeC: A Few-shot-sample-based General AI-generated Image Detection Method

The explosive growth of generative AI has saturated the internet with AI-generated images, raising security concerns and increasing the need for reliable detection methods. The primary requirement for such detection is generalizability, typically achieved by training on numerous fake images from various models. However, practical limitations, such as closed-source models and restricted access, often result in limited training samples. Therefore, training a general detector with few-shot samples is essential for modern detection mechanisms. To address this challenge, we propose FAMSeC, a general AI-generated image detection method based on LoRA-based Forgery Awareness Module and Semantic feature-guided Contrastive learning strategy. To effectively learn from limited samples and prevent overfitting, we developed a Forgery Awareness Module (FAM) based on LoRA, maintaining the generalization of pre-trained features. Additionally, to cooperate with FAM, we designed a Semantic feature-guided Contrastive learning strategy (SeC), making the FAM focus more on the differences between real/fake image than on the features of the samples themselves. Experiments show that FAMSeC outperforms state-of-the-art method, enhancing classification accuracy by 14.55% with just 0.56% of the training samples.

cs.CV↗

arXiv2024

LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning

The rapid growth of model scale has necessitated substantial computational resources for fine-tuning. Existing approach such as Low-Rank Adaptation (LoRA) has sought to address the problem of handling the large updated parameters in full fine-tuning. However, LoRA utilize random initialization and optimization of low-rank matrices to approximate updated weights, which can result in suboptimal convergence and an accuracy gap compared to full fine-tuning. To address these issues, we propose LoLDU, a Parameter-Efficient Fine-Tuning (PEFT) approach that significantly reduces trainable parameters by 2600 times compared to regular PEFT methods while maintaining comparable performance. LoLDU leverages Lower-Diag-Upper Decomposition (LDU) to initialize low-rank matrices for faster convergence and orthogonality. We focus on optimizing the diagonal matrix for scaling transformations. To the best of our knowledge, LoLDU has the fewest parameters among all PEFT approaches. We conducted extensive experiments across 4 instruction-following datasets, 6 natural language understanding (NLU) datasets, 8 image classification datasets, and image generation datasets with multiple model types (LLaMA2, RoBERTa, ViT, and Stable Diffusion), providing a comprehensive and detailed analysis. Our open-source code can be accessed at \href{https://github.com/SKDDJ/LoLDU}{https://github.com/SKDDJ/LoLDU}.

cs.CV↗

arXiv2024

Is the age pension in Australia sustainable and fair? Evidence from forecasting the old-age dependency ratio using the Hamilton-Perry model

The age pension aims to assist eligible elderly Australians meet specific age and residency criteria in maintaining basic living standards. In designing efficient pension systems, government policymakers seek to satisfy the expectations of the overall aging population in Australia. However, the population's unique demographic characteristics at the state and territory level are often overlooked due to the lack of available data. We use the Hamilton-Perry model, which requires minimum input, to model and forecast the evolution of age-specific populations at the state level. We also integrate the obtained sub-national demographic information to determine sustainable pension ages up to 2051. We also investigate pension welfare distribution in all states and territories to identify disadvantaged residents under the current pension system. Using the sub-national mortality data for Australia from 1971 to 2021 obtained from AHMD (2023), we implement the Hamilton-Perry model with the help of functional time series forecasting techniques. With forecasts of age-specific population sizes for each state and territory, we compute the old age dependency ratio to determine the nationwide sustainable pension age.

stat.AP↗

arXiv2024

A Survey on Indoor Visible Light Positioning Systems: Fundamentals, Applications, and Challenges

The growing demand for location-based services in areas like virtual reality, robot control, and navigation has intensified the focus on indoor localization. Visible light positioning (VLP), leveraging visible light communications (VLC), becomes a promising indoor positioning technology due to its high accuracy and low cost. This paper provides a comprehensive survey of VLP systems. In particular, since VLC lays the foundation for VLP, we first present a detailed overview of the principles of VLC. Then, we provide an in-depth overview of VLP algorithms. The performance of each positioning algorithm is also compared in terms of various metrics such as accuracy, coverage, and orientation limitation. Beyond the physical layer studies, the network design for a VLP system is also investigated, including multi-access technologies, resource allocation, and light-emitting diode (LED) placements. Next, the applications of the VLP systems are overviewed. Finally, this paper outlines open issues, challenges, and opportunities for the research field. In a nutshell, this paper constitutes the first holistic survey on VLP from state-of-the-art studies to practical uses.

eess.SP↗

arXiv2024

Multi-modal Data based Semi-Supervised Learning for Vehicle Positioning

In this paper, a multi-modal data based semi-supervised learning (SSL) framework that jointly use channel state information (CSI) data and RGB images for vehicle positioning is designed. In particular, an outdoor positioning system where the vehicle locations are determined by a base station (BS) is considered. The BS equipped with several cameras can collect a large amount of unlabeled CSI data and a small number of labeled CSI data of vehicles, and the images taken by cameras. Although the collected images contain partial information of vehicles (i.e. azimuth angles of vehicles), the relationship between the unlabeled CSI data and its azimuth angle, and the distances between the BS and the vehicles captured by images are both unknown. Therefore, the images cannot be directly used as the labels of unlabeled CSI data to train a positioning model. To exploit unlabeled CSI data and images, a SSL framework that consists of a pretraining stage and a downstream training stage is proposed. In the pretraining stage, the azimuth angles obtained from the images are considered as the labels of unlabeled CSI data to pretrain the positioning model. In the downstream training stage, a small sized labeled dataset in which the accurate vehicle positions are considered as labels is used to retrain the model. Simulation results show that the proposed method can reduce the positioning error by up to 30% compared to a baseline where the model is not pretrained.

eess.SP↗

arXiv2024

Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views

Recently, federated multi-view clustering (FedMVC) has emerged to explore cluster structures in multi-view data distributed on multiple clients. Existing approaches often assume that clients are isomorphic and all of them belong to either single-view clients or multi-view clients. Despite their success, these methods also present limitations when dealing with practical FedMVC scenarios involving heterogeneous hybrid views, where a mixture of both single-view and multi-view clients exhibit varying degrees of heterogeneity. In this paper, we propose a novel FedMVC framework, which concurrently addresses two challenges associated with heterogeneous hybrid views, i.e., client gap and view gap. To address the client gap, we design a local-synergistic contrastive learning approach that helps single-view clients and multi-view clients achieve consistency for mitigating heterogeneity among all clients. To address the view gap, we develop a global-specific weighting aggregation method, which encourages global models to learn complementary features from hybrid views. The interplay between local-synergistic contrastive learning and global-specific weighting aggregation mutually enhances the exploration of the data cluster structures distributed on multiple clients. Theoretical analysis and extensive experiments demonstrate that our method can handle the heterogeneous hybrid views in FedMVC and outperforms state-of-the-art methods. The code is available at \url{https://github.com/5Martina5/FMCSC}.

cs.LG↗

arXiv2024

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

Large language models (LLMs) have demonstrated impressive reasoning capabilities, particularly in textual mathematical problem-solving. However, existing open-source image instruction fine-tuning datasets, containing limited question-answer pairs per image, do not fully exploit visual information to enhance the multimodal mathematical reasoning capabilities of Multimodal LLMs (MLLMs). To bridge this gap, we address the lack of high-quality, diverse multimodal mathematical datasets by collecting 40K high-quality images with question-answer pairs from 24 existing datasets and synthesizing 320K new pairs, creating the MathV360K dataset, which enhances both the breadth and depth of multimodal mathematical questions. We introduce Math-LLaVA, a LLaVA-1.5-based model fine-tuned with MathV360K. This novel approach significantly improves the multimodal mathematical reasoning capabilities of LLaVA-1.5, achieving a 19-point increase and comparable performance to GPT-4V on MathVista's minitest split, and yielding leading performance on Math-V and MathVerse. Furthermore, Math-LLaVA demonstrates enhanced generalizability, showing substantial improvements on the MMMU benchmark. Our research highlights the importance of dataset diversity and synthesis in advancing MLLMs' mathematical reasoning abilities. The code and data are available at: \url{https://github.com/HZQ950419/Math-LLaVA}.

cs.CL↗

arXiv2024

The Solution for Temporal Action Localisation Task of Perception Test Challenge 2024

This report presents our method for Temporal Action Localisation (TAL), which focuses on identifying and classifying actions within specific time intervals throughout a video sequence. We employ a data augmentation technique by expanding the training dataset using overlapping labels from the Something-SomethingV2 dataset, enhancing the model's ability to generalize across various action classes. For feature extraction, we utilize state-of-the-art models, including UMT, VideoMAEv2 for video features, and BEATs and CAV-MAE for audio features. Our approach involves training both multimodal (video and audio) and unimodal (video only) models, followed by combining their predictions using the Weighted Box Fusion (WBF) method. This fusion strategy ensures robust action localisation. our overall approach achieves a score of 0.5498, securing first place in the competition.

cs.CV↗

arXiv2024

Solution for Point Tracking Task of ECCV 2nd Perception Test Challenge 2024

This report introduces an improved method for the Tracking Any Point~(TAP), focusing on monitoring physical surfaces in video footage. Despite their success with short-sequence scenarios, TAP methods still face performance degradation and resource overhead in long-sequence situations. To address these issues, we propose a simple yet effective approach called Fine-grained Point Discrimination~(\textbf{FPD}), which focuses on perceiving and rectifying point tracking at multiple granularities in zero-shot manner, especially for static points in the videos shot by a static camera. The proposed FPD contains two key components: $(1)$ Multi-granularity point perception, which can detect static sequences in video and points. $(2)$ Dynamic trajectory correction, which replaces point trajectories based on the type of tracked point. Our approach achieved the second highest score in the final test with a score of $0.4720$.

cs.CV↗

arXiv2024

Solution for OOD-CV UNICORN Challenge 2024 Object Detection Assistance LLM Counting Ability Improvement

This report provide a detailed description of the method that we explored and proposed in the ECCV OOD-CV UNICORN Challenge 2024, which focusing on the robustness of responses from large language models. The dataset of this competition are OODCA-VQA and SketchyQA. In order to test the robustness of the model. The organizer extended two variants of the dataset OODCV-Counterfactual and Sketchy-Challenging. There are several difficulties with these datasets. Firstly, the Sketchy-Challenging dataset uses some rarer item categories to test the model's generalization ability. Secondly, in the OODCV-Counterfactual dataset, the given problems often have inflection points and computational steps, requiring the model to recognize them during the inference process. In order to address this issue, we propose a simple yet effective approach called Object Detection Assistance Large Language Model(LLM) Counting Ability Improvement(ODAC), which focuses on using the object detection model to assist the LLM. To clarify, our approach contains two main blocks: (1)Object Detection Assistance. (2) Counterfactual Specific prompt. Our approach ranked second in the final test with a score of 0.86.

cs.CV↗