arXiv subjects

Miao Wang

Publications and source records attributed to Miao Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

COLA: A Scalable Multi-Agent Framework For Windows UI Task Automation

With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated the potential of LLM-based agents on automating Windows GUI operations. However, existing methodologies exhibit two critical challenges: (1) static agent architectures fail to dynamically adapt to the heterogeneous requirements of OS-level tasks, leading to inadequate scenario generalization;(2) the agent workflows lack fault tolerance mechanism, necessitating complete process re-execution for UI agent decision error. To address these limitations, we introduce \textit{COLA}, a collaborative multi-agent framework for automating Windows UI operations. In this framework, a scenario-aware agent Task Scheduler decomposes task requirements into atomic capability units, dynamically selects the optimal agent from a decision agent pool, effectively responds to the capability requirements of diverse scenarios. The decision agent pool supports plug-and-play expansion for enhanced flexibility. In addition, we design a memory unit equipped to all agents for their self-evolution. Furthermore, we develop an interactive backtracking mechanism that enables human to intervene to trigger state rollbacks for non-destructive process repair. Our experimental results on the GAIA benchmark demonstrates that the \textit{COLA} framework achieves state-of-the-art performance with an average score of 31.89\%, significantly outperforming baseline approaches without web API integration. Ablation studies further validate the individual contributions of our dynamic scheduling. The code is available at https://github.com/Alokia/COLA-demo.

cs.MA↗

arXiv2025

YUNet: Improved YOLOv11 Network for Skyline Detection

Skyline detection plays an important role in geolocalizaion, flight control, visual navigation, port security, etc. The appearance of the sky and non-sky areas are variable, because of different weather or illumination environment, which brings challenges to skyline detection. In this research, we proposed the YUNet algorithm, which improved the YOLOv11 architecture to segment the sky region and extract the skyline in complicated and variable circumstances. To improve the ability of multi-scale and large range contextual feature fusion, the YOLOv11 architecture is extended as an UNet-like architecture, consisting of an encoder, neck and decoder submodule. The encoder extracts the multi-scale features from the given images. The neck makes fusion of these multi-scale features. The decoder applies the fused features to complete the prediction rebuilding. To validate the proposed approach, the YUNet was tested on Skyfinder and CH1 datasets for segmentation and skyline detection respectively. Our test shows that the IoU of YUnet segmentation can reach 0.9858, and the average error of YUnet skyline detection is just 1.36 pixels. The implementation is published at https://github.com/kuazhangxiaoai/SkylineDet-YOLOv11Seg.git.

cs.CV↗

arXiv2025

PAT: Pruning-Aware Tuning for Large Language Models

Large language models (LLMs) excel in language tasks, especially with supervised fine-tuning after pre-training. However, their substantial memory and computational requirements hinder practical applications. Structural pruning, which reduces less significant weight dimensions, is one solution. Yet, traditional post-hoc pruning often leads to significant performance loss, with limited recovery from further fine-tuning due to reduced capacity. Since the model fine-tuning refines the general and chaotic knowledge in pre-trained models, we aim to incorporate structural pruning with the fine-tuning, and propose the Pruning-Aware Tuning (PAT) paradigm to eliminate model redundancy while preserving the model performance to the maximum extend. Specifically, we insert the innovative Hybrid Sparsification Modules (HSMs) between the Attention and FFN components to accordingly sparsify the upstream and downstream linear modules. The HSM comprises a lightweight operator and a globally shared trainable mask. The lightweight operator maintains a training overhead comparable to that of LoRA, while the trainable mask unifies the channels to be sparsified, ensuring structural pruning. Additionally, we propose the Identity Loss which decouples the transformation and scaling properties of the HSMs to enhance training robustness. Extensive experiments demonstrate that PAT excels in both performance and efficiency. For example, our Llama2-7b model with a 25\% pruning ratio achieves 1.33$\times$ speedup while outperforming the LoRA-finetuned model by up to 1.26\% in accuracy with a similar training cost. Code: https://github.com/kriskrisliu/PAT_Pruning-Aware-Tuning

cs.LG↗

arXiv2024

AI and Cultural Context: An Empirical Investigation of Large Language Models' Performance on Chinese Social Work Professional Standards

Objective: This study examines how well leading Chinese and Western large language models understand and apply Chinese social work principles, focusing on their foundational knowledge within a non-Western professional setting. We test whether the cultural context in the developing country influences model reasoning and accuracy. Method: Using a published self-study version of the Chinese National Social Work Examination (160 questions) covering jurisprudence and applied knowledge, we administered three testing conditions to eight cloud-based large language models - four Chinese and four Western. We examined their responses following official guidelines and evaluated their explanations' reasoning quality. Results: Seven models exceeded the 60-point passing threshold in both sections. Chinese models performed better in jurisprudence (median = 77.0 vs. 70.3) but slightly lower in applied knowledge (median = 65.5 vs. 67.0). Both groups showed cultural biases, particularly regarding gender equality and family dynamics. Models demonstrated strong professional terminology knowledge but struggled with culturally specific interventions. Valid reasoning in incorrect answers ranged from 16.4% to 45.0%. Conclusions: While both Chinese and Western models show foundational knowledge of Chinese social work principles, technical language proficiency does not ensure cultural competence. Chinese models demonstrate advantages in regulatory content, yet both Chinese and Western models struggle with culturally nuanced practice scenarios. These findings contribute to informing responsible AI integration into cross-cultural social work practice.

cs.CY↗

arXiv2024

Maximizing User Connectivity in AI-Enabled Multi-UAV Networks: A Distributed Strategy Generalized to Arbitrary User Distributions

Deep reinforcement learning (DRL) has been extensively applied to Multi-Unmanned Aerial Vehicle (UAV) network (MUN) to effectively enable real-time adaptation to complex, time-varying environments. Nevertheless, most of the existing works assume a stationary user distribution (UD) or a dynamic one with predicted patterns. Such considerations may make the UD-specific strategies insufficient when a MUN is deployed in unknown environments. To this end, this paper investigates distributed user connectivity maximization problem in a MUN with generalization to arbitrary UDs. Specifically, the problem is first formulated into a time-coupled combinatorial nonlinear non-convex optimization with arbitrary underlying UDs. To make the optimization tractable, a multi-agent CNN-enhanced deep Q learning (MA-CDQL) algorithm is proposed. The algorithm integrates a ResNet-based CNN to the policy network to analyze the input UD in real time and obtain optimal decisions based on the extracted high-level UD features. To improve the learning efficiency and avoid local optimums, a heatmap algorithm is developed to transform the raw UD to a continuous density map. The map will be part of the true input to the policy network. Simulations are conducted to demonstrate the efficacy of UD heatmaps and the proposed algorithm in maximizing user connectivity as compared to K-means methods.

eess.SY↗

arXiv2024

Learning with Dynamics: Autonomous Regulation of UAV Based Communication Networks with Dynamic UAV Crew

Unmanned Aerial Vehicle (UAV) based communication networks (UCNs) are a key component in future mobile networking. To handle the dynamic environments in UCNs, reinforcement learning (RL) has been a promising solution attributed to its strong capability of adaptive decision-making free of the environment models. However, most existing RL-based research focus on control strategy design assuming a fixed set of UAVs. Few works have investigated how UCNs should be adaptively regulated when the serving UAVs change dynamically. This article discusses RL-based strategy design for adaptive UCN regulation given a dynamic UAV set, addressing both reactive strategies in general UCNs and proactive strategies in solar-powered UCNs. An overview of the UCN and the RL framework is first provided. Potential research directions with key challenges and possible solutions are then elaborated. Some of our recent works are presented as case studies to inspire innovative ways to handle dynamic UAV crew with different RL algorithms.

eess.SY↗

arXiv2024

When Learning Meets Dynamics: Distributed User Connectivity Maximization in UAV-Based Communication Networks

Distributed management over Unmanned Aerial Vehicle (UAV) based communication networks (UCNs) has attracted increasing research attention. In this work, we study a distributed user connectivity maximization problem in a UCN. The work features a horizontal study over different levels of information exchange during the distributed iteration and a consideration of dynamics in UAV set and user distribution, which are not well addressed in the existing works. Specifically, the studied problem is first formulated into a time-coupled mixed-integer non-convex optimization problem. A heuristic two-stage UAV-user association policy is proposed to faster determine the user connectivity. To tackle the NP-hard problem in scalable manner, the distributed user connectivity maximization algorithm 1 (DUCM-1) is proposed under the multi-agent deep Q learning (MA-DQL) framework. DUCM-1 emphasizes on designing different information exchange levels and evaluating how they impact the learning convergence with stationary and dynamic user distribution. To comply with the UAV dynamics, DUCM-2 algorithm is developed which is devoted to autonomously handling arbitrary quit's and join-in's of UAVs in a considered time horizon. Extensive simulations are conducted i) to conclude that exchanging state information with a deliberated task-specific reward function design yields the best convergence performance, and ii) to show the efficacy and robustness of DUCM-2 against the dynamics.

cs.NI↗

arXiv2024

Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes

We present Neural 3D Strokes, a novel technique to generate stylized images of a 3D scene at arbitrary novel views from multi-view 2D images. Different from existing methods which apply stylization to trained neural radiance fields at the voxel level, our approach draws inspiration from image-to-painting methods, simulating the progressive painting process of human artwork with vector strokes. We develop a palette of stylized 3D strokes from basic primitives and splines, and consider the 3D scene stylization task as a multi-view reconstruction process based on these 3D stroke primitives. Instead of directly searching for the parameters of these 3D strokes, which would be too costly, we introduce a differentiable renderer that allows optimizing stroke parameters using gradient descent, and propose a training scheme to alleviate the vanishing gradient issue. The extensive evaluation demonstrates that our approach effectively synthesizes 3D scenes with significant geometric and aesthetic stylization while maintaining a consistent appearance across different views. Our method can be further integrated with style loss and image-text contrastive models to extend its applications, including color transfer and text-driven 3D scene drawing. Results and code are available at http://buaavrcg.github.io/Neural3DStrokes.

cs.CV↗

arXiv2023

Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding

Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language-embedded scene representations have made progress by incorporating language features into 3D spaces. However, their efficacy heavily depends on neural networks that are resource-intensive in training and rendering. Although recent 3D Gaussians offer efficient and high-quality novel view synthesis, directly embedding language features in them leads to prohibitive memory usage and decreased performance. In this work, we introduce Language Embedded 3D Gaussians, a novel scene representation for open-vocabulary query tasks. Instead of embedding high-dimensional raw semantic features on 3D Gaussians, we propose a dedicated quantization scheme that drastically alleviates the memory requirement, and a novel embedding procedure that achieves smoother yet high accuracy query, countering the multi-view feature inconsistencies and the high-frequency inductive bias in point-based representations. Our comprehensive experiments show that our representation achieves the best visual quality and language querying accuracy across current language-embedded representations, while maintaining real-time rendering frame rates on a single desktop GPU.

cs.CV↗

arXiv2023

BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesis

Synthesizing photorealistic 4D human head avatars from videos is essential for VR/AR, telepresence, and video game applications. Although existing Neural Radiance Fields (NeRF)-based methods achieve high-fidelity results, the computational expense limits their use in real-time applications. To overcome this limitation, we introduce BakedAvatar, a novel representation for real-time neural head avatar synthesis, deployable in a standard polygon rasterization pipeline. Our approach extracts deformable multi-layer meshes from learned isosurfaces of the head and computes expression-, pose-, and view-dependent appearances that can be baked into static textures for efficient rasterization. We thus propose a three-stage pipeline for neural head avatar synthesis, which includes learning continuous deformation, manifold, and radiance fields, extracting layered meshes and textures, and fine-tuning texture details with differential rasterization. Experimental results demonstrate that our representation generates synthesis results of comparable quality to other state-of-the-art methods while significantly reducing the inference time required. We further showcase various head avatar synthesis results from monocular videos, including view synthesis, face reenactment, expression editing, and pose editing, all at interactive frame rates.

cs.GR↗

arXiv2023

Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception

Vehicle-to-everything (V2X) autonomous driving opens up a promising direction for developing a new generation of intelligent transportation systems. Collaborative perception (CP) as an essential component to achieve V2X can overcome the inherent limitations of individual perception, including occlusion and long-range perception. In this survey, we provide a comprehensive review of CP methods for V2X scenarios, bringing a profound and in-depth understanding to the community. Specifically, we first introduce the architecture and workflow of typical V2X systems, which affords a broader perspective to understand the entire V2X system and the role of CP within it. Then, we thoroughly summarize and analyze existing V2X perception datasets and CP methods. Particularly, we introduce numerous CP methods from various crucial perspectives, including collaboration stages, roadside sensors placement, latency compensation, performance-bandwidth trade-off, attack/defense, pose alignment, etc. Moreover, we conduct extensive experimental analyses to compare and examine current CP methods, revealing some essential and unexplored insights. Specifically, we analyze the performance changes of different methods under different bandwidths, providing a deep insight into the performance-bandwidth trade-off issue. Also, we examine methods under different LiDAR ranges. To study the model robustness, we further investigate the effects of various simulated real-world noises on the performance of different CP methods, covering communication latency, lossy communication, localization errors, and mixed noises. In addition, we look into the sim-to-real generalization ability of existing CP methods. At last, we thoroughly discuss issues and challenges, highlighting promising directions for future efforts. Our codes for experimental analysis will be public at https://github.com/memberRE/Collaborative-Perception.

cs.CV↗

arXiv2023

TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT

Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate. The advancements in large language models (LLMs) have made it possible to interact with tables using natural language input, bringing this capability closer to reality. In this paper, we present TableGPT, a unified fine-tuned framework that enables LLMs to understand and operate on tables using external functional commands. It introduces the capability to seamlessly interact with tables, enabling a wide range of functionalities such as question answering, data manipulation (e.g., insert, delete, query, and modify operations), data visualization, analysis report generation, and automated prediction. TableGPT aims to provide convenience and accessibility to users by empowering them to effortlessly leverage tabular data. At the core of TableGPT lies the novel concept of global tabular representations, which empowers LLMs to gain a comprehensive understanding of the entire table beyond meta-information. By jointly training LLMs on both table and text modalities, TableGPT achieves a deep understanding of tabular data and the ability to perform complex operations on tables through chain-of-command instructions. Importantly, TableGPT offers the advantage of being a self-contained system rather than relying on external API interfaces. Moreover, it supports efficient data process flow, query rejection (when appropriate) and private deployment, enabling faster domain data fine-tuning and ensuring data privacy, which enhances the framework's adaptability to specific use cases.

cs.AI↗

arXiv2023

HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolution

The task of lane detection has garnered considerable attention in the field of autonomous driving due to its complexity. Lanes can present difficulties for detection, as they can be narrow, fragmented, and often obscured by heavy traffic. However, it has been observed that the lanes have a geometrical structure that resembles a straight line, leading to improved lane detection results when utilizing this characteristic. To address this challenge, we propose a hierarchical Deep Hough Transform (DHT) approach that combines all lane features in an image into the Hough parameter space. Additionally, we refine the point selection method and incorporate a Dynamic Convolution Module to effectively differentiate between lanes in the original image. Our network architecture comprises a backbone network, either a ResNet or Pyramid Vision Transformer, a Feature Pyramid Network as the neck to extract multi-scale features, and a hierarchical DHT-based feature aggregation head to accurately segment each lane. By utilizing the lane features in the Hough parameter space, the network learns dynamic convolution kernel parameters corresponding to each lane, allowing the Dynamic Convolution Module to effectively differentiate between lane features. Subsequently, the lane features are fed into the feature decoder, which predicts the final position of the lane. Our proposed network structure demonstrates improved performance in detecting heavily occluded or worn lane images, as evidenced by our extensive experimental results, which show that our method outperforms or is on par with state-of-the-art techniques.

cs.CV↗

arXiv2023

Towards a transportable Ca$^+$ optical clock with a systematic uncertainty of $4.8\times 10^{-18}$

We present a compact, long-term nearly continuous operation of a room-temperature Ca$^+$ optical clock setup towards a transportable clock, achieving an overall systematic uncertainty of $4.8\times 10^{-18}$ and an uptime rate of 97.8% over an 8-day period. The active liquid-cooling scheme is adopted, combined with the precise temperature measurement with 13 temperature sensors both inside and outside the vacuum chamber to ensure the accurate evaluation of the thermal environment for the optical clock. The environmental temperature uncertainty is evaluated as 293.31(0.4) K, corresponding to a blackbody radiation (BBR) frequency shift uncertainty of $4.6\times 10^{-18}$, which is reduced more than two times compared to our previous work. Through the frequency comparison between the room temperature Ca$^+$ optical clock and a cryogenic Ca$^+$ optical clock, the overall uncertainty of the clock comparison is $7.5\times 10^{-18}$, including a statistic uncertainty of $4.9\times 10^{-18}$ and a systematic uncertainty of $5.7\times 10^{-18}$. This work provides a set of feasible implementations for high-precision transportable ion optical clocks.

physics.atom-ph↗

arXiv2023

Optimal Charging Profile Design for Solar-Powered Sustainable UAV Communication Networks

This work studies optimal solar charging for solar-powered self-sustainable UAV communication networks, considering the day-scale time-variability of solar radiation and user service demand. The objective is to optimally trade off between the user coverage performance and the net energy loss of the network by proactively assigning UAVs to serve, charge, or land. Specifically, the studied problem is first formulated into a time-coupled mixed-integer non-convex optimization problem, and further decoupled into two sub-problems for tractability. To solve the challenge caused by time-coupling, deep reinforcement learning (DRL) algorithms are respectively designed for the two sub-problems. Particularly, a relaxation mechanism is put forward to overcome the "dimension curse" incurred by the large discrete action space in the second sub-problem. At last, simulation results demonstrate the efficacy of our designed DRL algorithms in trading off the communication performance against the net energy loss, and the impact of different parameters on the tradeoff performance.

eess.SY↗

arXiv2022

Multi-User Redirected Walking in Separate Physical Spaces for Online VR Scenarios

With the recent rise of Metaverse, online multiplayer VR applications are becoming increasingly prevalent worldwide. Allowing users to move easily in virtual environments is crucial for high-quality experiences in such collaborative VR applications. This paper focuses on redirected walking technology (RDW) to allow users to move beyond the confines of the limited physical environments (PE). The existing RDW methods lack the scheme to coordinate multiple users in different PEs, and thus have the issue of triggering too many resets for all the users. We propose a novel multi-user RDW method that is able to significantly reduce the overall reset number and give users a better immersive experience by providing a more continuous exploration. Our key idea is to first find out the "bottleneck" user that may cause all users to be reset and estimate the time to reset, and then redirect all the users to favorable poses during that maximized bottleneck time to ensure the subsequent resets can be postponed as much as possible. More particularly, we develop methods to estimate the time of possibly encountering obstacles and the reachable area for a specific pose to enable the prediction of the next reset caused by any user. Our experiments and user study found that our method outperforms existing RDW methods in online VR applications.

cs.HC↗

arXiv2022

C3-STISR: Scene Text Image Super-resolution with Triple Clues

Scene text image super-resolution (STISR) has been regarded as an important pre-processing task for text recognition from low-resolution scene text images. Most recent approaches use the recognizer's feedback as clues to guide super-resolution. However, directly using recognition clue has two problems: 1) Compatibility. It is in the form of probability distribution, has an obvious modal gap with STISR - a pixel-level task; 2) Inaccuracy. it usually contains wrong information, thus will mislead the main task and degrade super-resolution performance. In this paper, we present a novel method C3-STISR that jointly exploits the recognizer's feedback, visual and linguistical information as clues to guide super-resolution. Here, visual clue is from the images of texts predicted by the recognizer, which is informative and more compatible with the STISR task; while linguistical clue is generated by a pre-trained character-level language model, which is able to correct the predicted texts. We design effective extraction and fusion mechanisms for the triple cross-modal clues to generate a comprehensive and unified guidance for super-resolution. Extensive experiments on TextZoom show that C3-STISR outperforms the SOTA methods in fidelity and recognition performance. Code is available in https://github.com/zhaominyiz/C3-STISR.

cs.CV↗

arXiv2022

Measurement of infrared magic wavelength for an all-optical trapping of $^{40}$Ca$^{+}$ ion clock

For the first time, we experimentally determine the infrared magic wavelength for the $^{40}$Ca$^{+}$ $4s\, ^{2}\!S_{1/2} \rightarrow 3d\,^{2}\!D_{5/2}$ electric quadrupole transition by observation of the light shift canceling in $^{40}$Ca$^{+}$ optical clock. A "magic" magnetic field direction is chosen to make the magic wavelength insensitive to both the linear polarization purity and the polarization direction of the laser. The determined magic wavelength for this transition is 1056.37(9)~nm, which is not only in good agreement with theoretical predictions but also more precise by a factor of about 300. Using this measured magic wavelength we also derive the differential static polarizability to be $-44.32(32)$~a.u., which will be an important input for the evaluation of the blackbody radiation shift at room temperatures. Our work paves a way for all-optical-trapping of $^{40}$Ca$^{+}$ optical clock.

physics.atom-ph↗