arXiv subjects

Yue Hu

Publications and source records attributed to Yue Hu.

At least 127 records · Page 7Linked to original sources

arXiv2025

Machine Learning Approach for Estimating Magnetic Field Strength in Galaxy Clusters from Synchrotron Emission

Magnetic fields play a crucial role in various astrophysical processes within the intracluster medium, including heat conduction, cosmic ray acceleration, and the generation of synchrotron radiation. However, measuring magnetic field strength is typically challenging due to the limited availability of Faraday Rotation Measure sources. To address the challenge, we propose a novel method that employs Convolutional Neural Networks (CNNs) alongside synchrotron emission observations to estimate magnetic field strengths in galaxy clusters. Our CNN model is trained on either magnetohydrodynamic (MHD) turbulence simulations or MHD galaxy cluster simulations, which incorporate complex dynamics such as cluster mergers and sloshing motions. The results demonstrate that CNNs can effectively estimate magnetic field strengths with mean squared error of approximately \SI{0.135}{\micro G}$^2$, \SI{0.044}{\micro G}$^2$, and \SI{0.02}{\micro G}$^2$ for $β= 100$, 200, and 500 conditions, respectively. Additionally, we have confirmed that our CNN model remains robust against noise and variations in viewing angles with sufficient training, ensuring reliable performance under a wide range of observational conditions. We compare the CNN approach with the traditional magnetic field strength estimates method that assumes equipartition between cosmic ray electron energy and magnetic field energy. Different from the equipartition method, this CNN approach relies on the morphological feature of synchrotron images, offering a new perspective for complementing traditional estimates and enhancing our understanding of cosmic ray acceleration mechanisms.

astro-ph.GA↗

arXiv2025

Dynamics of Multiphase Carbon in the Turbulent Circumgalactic Medium

The circumgalactic medium (CGM) plays a crucial role in regulating material and energy exchange between galaxies and their environments. The best means of observing this medium is through absorption-line spectroscopy, but we have yet to develop a consistent physical model that fully explains these results. Here we investigate the impact of turbulence and non-equilibrium chemistry on the properties of the CGM, using three-dimensional hydrodynamic simulations that include the impact of an ionizing background. Increasing turbulence enhances small-scale density fluctuations, shifting the kinetic energy spectra from Kolmogorov to Burgers scaling. This is indicative of shock-dominated dissipation, which plays a critical role in driving carbon ionization and shaping the multiphase structure of the medium. At the same time, the presence of background radiation significantly alters the ionization balance, increasing the prevalence of C\textsc{ii} and C\textsc{iv}. Thus, turbulence and the background radiation have complementary roles: turbulence governs the spatial distribution and facilitates the formation of ionized species, whereas the background radiation modifies the overall ionization equilibrium, setting the observed distribution of multiphase carbon.

astro-ph.GA↗

arXiv2025

MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension

Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer visual/linguistic knowledge by full fine-tuning. However, full fine-tuning the entire backbone not only breaks the rich prior knowledge embedded in the pre-training, but also incurs significant computational costs. Motivated by the recent emergence of Parameter-Efficient Transfer Learning (PETL) methods, we aim to solve the REC task in an effective and efficient manner. Directly applying these PETL methods to the REC task is inappropriate, as they lack the specific-domain abilities for precise local visual perception and visual-language alignment. Therefore, we propose a novel framework of Multimodal Prior-guided Parameter Efficient Tuning, namely MaPPER. Specifically, MaPPER comprises Dynamic Prior Adapters guided by an aligned prior, and Local Convolution Adapters to extract precise local semantics for better visual perception. Moreover, the Prior-Guided Text module is proposed to further utilize the prior for facilitating the cross-modal alignment. Experimental results on three widely-used benchmarks demonstrate that MaPPER achieves the best accuracy compared to the full fine-tuning and other PETL methods with only 1.41% tunable backbone parameters. Our code is available at https://github.com/liuting20/MaPPER.

cs.CV↗

arXiv2025

Circum-nuclear eccentric gas flow in the Galactic Center revealed by ALMA CMZ Exploration Survey (ACES)

We analyze the CS (J=2-1) line cube from the internal data release obtained by the large-scale program "ALMA CMZ Exploration Survey (ACES)" to investigate the kinematic structure of the innermost $\sim 10$ pc region of the Galaxy, which contains the high-velocity compact cloud (HVCC) at $(l,b,v_{\rm lsr})\sim(+0^\circ.02,-0^\circ.02, 100 {\rm km~s}^{-1})$ (hereafter G0.02). The longitude-velocity diagram (LVD) of the cloud draws an elliptical structure, which is interpreted as an orbital trajectory in the $(l,V_{\rm lsr})$ space of a noncircular (eccentric) motion of the molecular gas in the gravitational potential of an extended mass distribution in the central 10 pc of the Galaxy. We argue that G0.02 is a kinematic tracer of the inner potential, a rare case of a dense gas following an eccentric orbit in the nuclear gravitational field.

astro-ph.GA↗

arXiv2025

BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation

Zero-shot object navigation (ZSON) allows robots to find target objects in unfamiliar environments using natural language instructions, without relying on pre-built maps or task-specific training. Recent general-purpose models, such as large language models (LLMs) and vision-language models (VLMs), equip agents with semantic reasoning abilities to estimate target object locations in a zero-shot manner. However, these models often greedily select the next goal without maintaining a global understanding of the environment and are fundamentally limited in the spatial reasoning necessary for effective navigation. To overcome these limitations, we propose a novel 3D voxel-based belief map that estimates the target's prior presence distribution within a voxelized 3D space. This approach enables agents to integrate semantic priors from LLMs and visual embeddings with hierarchical spatial structure, alongside real-time observations, to build a comprehensive 3D global posterior belief of the target's location. Building on this 3D voxel map, we introduce BeliefMapNav, an efficient navigation system with two key advantages: i) grounding LLM semantic reasoning within the 3D hierarchical semantics voxel space for precise target position estimation, and ii) integrating sequential path planning to enable efficient global navigation decisions. Experiments on HM3D, MP3D, and HSSD benchmarks show that BeliefMapNav achieves state-of-the-art (SOTA) Success Rate (SR) and Success weighted by Path Length (SPL), with a notable 46.4% SPL improvement over the previous best SR method, validating its effectiveness and efficiency.

cs.RO↗

arXiv2025

What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation

Open vocabulary image segmentation tackles the challenge of recognizing dynamically adjustable, predefined novel categories at inference time by leveraging vision-language alignment. However, existing paradigms typically perform class-agnostic region segmentation followed by category matching, which deviates from the human visual system's process of recognizing objects based on semantic concepts, leading to poor alignment between region segmentation and target concepts. To bridge this gap, we propose a novel Cognition-Inspired Framework for open vocabulary image segmentation that emulates the human visual recognition process: first forming a conceptual understanding of an object, then perceiving its spatial extent. The framework consists of three core components: (1) A Generative Vision-Language Model (G-VLM) that mimics human cognition by generating object concepts to provide semantic guidance for region segmentation. (2) A Concept-Aware Visual Enhancer Module that fuses textual concept features with global visual representations, enabling adaptive visual perception based on target concepts. (3) A Cognition-Inspired Decoder that integrates local instance features with G-VLM-provided semantic cues, allowing selective classification over a subset of relevant categories. Extensive experiments demonstrate that our framework achieves significant improvements, reaching $27.2$ PQ, $17.0$ mAP, and $35.3$ mIoU on A-150. It further attains $56.2$, $28.2$, $15.4$, $59.2$, $18.7$, and $95.8$ mIoU on Cityscapes, Mapillary Vistas, A-847, PC-59, PC-459, and PAS-20, respectively. In addition, our framework supports vocabulary-free segmentation, offering enhanced flexibility in recognizing unseen categories. Code will be public.

cs.CV↗

arXiv2025

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space

Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings-spanning environment, action, and perception-largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces. To support this task, we present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks across six categories, grounded in a realistic 3D urban simulator. Moreover, we propose Planner-Manager-Actor (PMA), a novel agent tailored for CityEQA. PMA enables long-horizon planning and hierarchical task execution: the Planner breaks down the question answering into sub-tasks, the Manager maintains an object-centric cognitive map for spatial reasoning during the process control, and the specialized Actors handle navigation, exploration, and collection sub-tasks. Experiments demonstrate that PMA achieves 60.7% of human-level answering accuracy, significantly outperforming competitive baselines. While promising, the performance gap compared to humans highlights the need for enhanced visual reasoning in CityEQA. This work paves the way for future advancements in urban spatial intelligence. Dataset and code are available at https://github.com/BiluYong/CityEQA.git.

cs.AI↗

arXiv2025

Tuning Topological States by Dissipation

The bulk-boundary correspondence plays a crucial role in topological quantum systems, however,this principle is broken in non-Hermitian systems. The breakdown of the bulk-boundary correspondence indicates that the global phase diagrams under open boundary conditions are significantly different from those under periodic boundary conditions. In this paper, we investigate how the bulk-boundary correspondence breaks down by gradually tearing the system. We find that by tuning the strength of gain and loss domain wall, in the thermodynamic limit, the global phase diagrams of the topological system become the hybrids of those under periodic and open boundary conditions. Moreover, during the breakdown of the bulk-boundary correspondence, several phase transitions occur. This situation is quite different from earlier work, where the breakdown of the bulk-boundary correspondence in the thermodynamic limit occurred suddenly due to infinitesimal boundary hopping amplitudes. To support our conclusions, we provide both analytical and numerical calculations. These results help researchers better understand non-Hermitian topological systems.

quant-ph↗

arXiv2025

Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology

Aerial Visual Object Search (AVOS) tasks in urban environments require Unmanned Aerial Vehicles (UAVs) to autonomously search for and identify target objects using visual and textual cues without external guidance. Existing approaches struggle in complex urban environments due to redundant semantic processing, similar object distinction, and the exploration-exploitation dilemma. To bridge this gap and support the AVOS task, we introduce CityAVOS, the first benchmark dataset for autonomous search of common urban objects. This dataset comprises 2,420 tasks across six object categories with varying difficulty levels, enabling comprehensive evaluation of UAV agents' search capabilities. To solve the AVOS tasks, we also propose PRPSearcher (Perception-Reasoning-Planning Searcher), a novel agentic method powered by multi-modal large language models (MLLMs) that mimics human three-tier cognition. Specifically, PRPSearcher constructs three specialized maps: an object-centric dynamic semantic map enhancing spatial perception, a 3D cognitive map based on semantic attraction values for target reasoning, and a 3D uncertainty map for balanced exploration-exploitation search. Also, our approach incorporates a denoising mechanism to mitigate interference from similar objects and utilizes an Inspiration Promote Thought (IPT) prompting mechanism for adaptive action planning. Experimental results on CityAVOS demonstrate that PRPSearcher surpasses existing baselines in both success rate and search efficiency (on average: +37.69% SR, +28.96% SPL, -30.69% MSS, and -46.40% NE). While promising, the performance gap compared to humans highlights the need for better semantic reasoning and spatial exploration capabilities in AVOS tasks. This work establishes a foundation for future advances in embodied target search. Dataset and source code are available at https://anonymous.4open.science/r/CityAVOS-3DF8.

cs.CV↗

arXiv2025

Origin of the Multi-Phase Interstellar Medium: the Effects of Turbulence and Magnetic Field

The interstellar medium (ISM) consists of a multiphase gas, including the warm neutral medium (WNM), the unstable neutral medium (UNM), and the cold neutral medium (CNM). While significant attention has been devoted to understanding the WNM and CNM, the formation of a substantial fraction of the UNM, with temperatures ranging from a few hundred to a few thousand Kelvin, remains less well understood. In this study, we present three-dimensional hydrodynamical and magnetohydrodynamical simulations of turbulent multiphase ISM to investigate the roles of turbulence and magnetic fields in regulating the multiphase ISM. Our results confirm that turbulence is crucial in redistributing energy and producing the UNM. The turbulent mixing effect smooths the phase diagram, flattens the pressure-density relationship, and increases the fraction of gas in the UNM. We find that magnetic fields not only contribute to sustaining the UNM but also influence the dynamics and distribution of gas across all phases. Magnetic fields introduce anisotropy to the turbulent cascade, reducing the efficiency of turbulent mixing in the direction perpendicular to the magnetic field. We find the anisotropy results in a less flat phase diagram compared to hydrodynamical cases. Furthermore, the inclusion of magnetic fields shallowens the second-order velocity structure functions across multiple ISM phases, suggesting that more small-scale fluctuations are driven. These fluctuations contribute to the formation of the UNM by altering the energy cascade and thermodynamic properties of the gas. Our findings suggest that the combined effects of turbulence and magnetic fields are important in regulating the multiphase ISM.

astro-ph.GA↗

arXiv2025

Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking

Grokking, referring to the abrupt improvement in test accuracy after extended overfitting, offers valuable insights into the mechanisms of model generalization. Existing researches based on progress measures imply that grokking relies on understanding the optimization dynamics when the loss function is dominated solely by the weight decay term. However, we find that this optimization merely leads to token uniformity, which is not a sufficient condition for grokking. In this work, we investigate the grokking mechanism underlying the Transformer in the task of prime number operations. Based on theoretical analysis and experimental validation, we present the following insights: (i) The weight decay term encourages uniformity across all tokens in the embedding space when it is minimized. (ii) The occurrence of grokking is jointly determined by the uniformity of the embedding space and the distribution of the training dataset. Building on these insights, we provide a unified perspective for understanding various previously proposed progress measures and introduce a novel, concise, and effective progress measure that could trace the changes in test loss more accurately. Finally, to demonstrate the versatility of our theoretical framework, we design a dedicated dataset to validate our theory on ResNet-18, successfully showcasing the occurrence of grokking. The code is released at https://github.com/Qihuai27/Grokking-Insight.

cs.LG↗

arXiv2025

SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting

Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene details. While differentiable rendering techniques such as Neural Radiance Fields (NeRF) address some of these challenges, their high computational costs make them unsuitable for real-time applications. Additionally, existing 3D Gaussian Splatting (3DGS) methods often focus on photometric consistency, neglecting geometric accuracy and failing to exploit SLAM's dynamic depth and pose updates for scene refinement. We propose a framework integrating dense SLAM with 3DGS for real-time, high-fidelity dense reconstruction. Our approach introduces SLAM-Informed Adaptive Densification, which dynamically updates and densifies the Gaussian model by leveraging dense point clouds from SLAM. Additionally, we incorporate Geometry-Guided Optimization, which combines edge-aware geometric constraints and photometric consistency to jointly optimize the appearance and geometry of the 3DGS scene representation, enabling detailed and accurate SLAM mapping reconstruction. Experiments on the Replica and TUM-RGBD datasets demonstrate the effectiveness of our approach, achieving state-of-the-art results among monocular systems. Specifically, our method achieves a PSNR of 36.864, SSIM of 0.985, and LPIPS of 0.040 on Replica, representing improvements of 10.7%, 6.4%, and 49.4%, respectively, over the previous SOTA. On TUM-RGBD, our method outperforms the closest baseline by 10.2%, 6.6%, and 34.7% in the same metrics. These results highlight the potential of our framework in bridging the gap between photometric and geometric dense 3D scene representations, paving the way for practical and efficient monocular dense reconstruction.

cs.CV↗

arXiv2025

Towards Collaborative Autonomous Driving: Simulation Platform and End-to-End System

Vehicle-to-everything-aided autonomous driving (V2X-AD) has a huge potential to provide a safer driving solution. Despite extensive researches in transportation and communication to support V2X-AD, the actual utilization of these infrastructures and communication resources in enhancing driving performances remains largely unexplored. This highlights the necessity of collaborative autonomous driving: a machine learning approach that optimizes the information sharing strategy to improve the driving performance of each vehicle. This effort necessitates two key foundations: a platform capable of generating data to facilitate the training and testing of V2X-AD, and a comprehensive system that integrates full driving-related functionalities with mechanisms for information sharing. From the platform perspective, we present V2Xverse, a comprehensive simulation platform for collaborative autonomous driving. This platform provides a complete pipeline for collaborative driving. From the system perspective, we introduce CoDriving, a novel end-to-end collaborative driving system that properly integrates V2X communication over the entire autonomous pipeline, promoting driving with shared perceptual information. The core idea is a novel driving-oriented communication strategy. Leveraging this strategy, CoDriving improves driving performance while optimizing communication efficiency. We make comprehensive benchmarks with V2Xverse, analyzing both modular performance and closed-loop driving performance. Experimental results show that CoDriving: i) significantly improves the driving score by 62.49% and drastically reduces the pedestrian collision rate by 53.50% compared to the SOTA end-to-end driving method, and ii) achieves sustaining driving performance superiority over dynamic constraint communication conditions.

cs.CV↗

arXiv2025

Leveraging GCN-based Action Recognition for Teleoperation in Daily Activity Assistance

Caregiving of older adults is an urgent global challenge, with many older adults preferring to age in place rather than enter residential care. However, providing adequate home-based assistance remains difficult, particularly in geographically vast regions. Teleoperated robots offer a promising solution, but conventional motion-mapping teleoperation imposes unnatural movement constraints on operators, leading to muscle fatigue and reduced usability. This paper presents a novel teleoperation framework that leverages action recognition to enable intuitive remote robot control. Using our simplified Spatio-Temporal Graph Convolutional Network (S-ST-GCN), the system recognizes human actions and executes corresponding preset robot trajectories, eliminating the need for direct motion synchronization. A finite-state machine (FSM) is integrated to enhance reliability by filtering out misclassified actions. Our experiments demonstrate that the proposed framework enables effortless operator movement while ensuring accurate robot execution. This proof-of-concept study highlights the potential of teleoperation with action recognition for enabling caregivers to remotely assist older adults during activities of daily living (ADLs). Future work will focus on improving the S-ST-GCN's recognition accuracy and generalization, integrating advanced motion planning techniques to further enhance robotic autonomy in older adult care, and conducting a user study to evaluate the system's telepresence and ease of control.

cs.RO↗

arXiv2025

Robot Character Generation and Adaptive Human-Robot Interaction with Personality Shaping

We present a novel framework for designing emotionally agile robots with dynamic personalities and memory-based learning, with the aim of performing adaptive and non-deterministic interactions with humans while conforming to shared social understanding. While existing work has largely focused on emotion recognition and static response systems, many approaches rely on sentiment analysis and action mapping frameworks that are pre-defined with limited dimensionality and fixed configurations, lacking the flexibility of dynamic personality traits and memory-enabled adaptation. Other systems are often restricted to limited modes of expression and fail to develop a causal relationship between human behavior and the robot's proactive physical actions, resulting in constrained adaptability and reduced responsiveness in complex, dynamic interactions. Our methodology integrates the Big Five Personality Traits, Appraisal Theory, and abstracted memory layers through Large Language Models (LLMs). The LLM generates a parameterized robot personality based on the Big Five, processes human language and sentiments, evaluates human behavior using Appraisal Theory, and generates emotions and selects appropriate actions adapted by historical context over time. We validated the framework by testing three robots with distinct personalities in identical background contexts and found that personality, appraisal, and memory influence the adaptability of human-robot interactions. The impact of the individual components was further validated through ablation tests. We conclude that this system enables robots to engage in meaningful and personalized interactions with users, and holds significant potential for applications in domains such as pet robots, assistive robots, educational robots, and collaborative functional robots, where cultivating tailored relationships and enriching user experiences are essential.

cs.HC↗

arXiv2025

A Novel Channel Boosted Residual CNN-Transformer with Regional-Boundary Learning for Breast Cancer Detection

Recent advancements in detecting tumors using deep learning on breast ultrasound images (BUSI) have demonstrated significant success. Deep CNNs and vision-transformers (ViTs) have demonstrated individually promising initial performance. However, challenges related to model complexity and contrast, texture, and tumor morphology variations introduce uncertainties that hinder the effectiveness of current methods. This study introduces a novel hybrid framework, CB-Res-RBCMT, combining customized residual CNNs and new ViT components for detailed BUSI cancer analysis. The proposed RBCMT uses stem convolution blocks with CNN Meet Transformer (CMT) blocks, followed by new Regional and boundary (RB) feature extraction operations for capturing contrast and morphological variations. Moreover, the CMT block incorporates global contextual interactions through multi-head attention, enhancing computational efficiency with a lightweight design. Additionally, the customized inverse residual and stem CNNs within the CMT effectively extract local texture information and handle vanishing gradients. Finally, the new channel-boosted (CB) strategy enriches the feature diversity of the limited dataset by combining the original RBCMT channels with transfer learning-based residual CNN-generated maps. These diverse channels are processed through a spatial attention block for optimal pixel selection, reducing redundancy and improving the discrimination of minor contrast and texture variations. The proposed CB-Res-RBCMT achieves an F1-score of 95.57%, accuracy of 95.63%, sensitivity of 96.42%, and precision of 94.79% on the standard harmonized stringent BUSI dataset, outperforming existing ViT and CNN methods. These results demonstrate the versatility of our integrated CNN-Transformer framework in capturing diverse features and delivering superior performance in BUSI cancer diagnosis.

eess.IV↗

arXiv2025

M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension

Referring expression comprehension (REC) is a vision-language task to locate a target object in an image based on a language expression. Fully fine-tuning general-purpose pre-trained vision-language foundation models for REC yields impressive performance but becomes increasingly costly. Parameter-efficient transfer learning (PETL) methods have shown strong performance with fewer tunable parameters. However, directly applying PETL to REC faces two challenges: (1) insufficient multi-modal interaction between pre-trained vision-language foundation models, and (2) high GPU memory usage due to gradients passing through the heavy vision-language foundation models. To this end, we present M2IST: Multi-Modal Interactive Side-Tuning with M3ISAs: Mixture of Multi-Modal Interactive Side-Adapters. During fine-tuning, we fix the pre-trained uni-modal encoders and update M3ISAs to enable efficient vision-language alignment for REC. Empirical results reveal that M2IST achieves better performance-efficiency trade-off than full fine-tuning and other PETL methods, requiring only 2.11\% tunable parameters, 39.61\% GPU memory, and 63.46\% training time while maintaining competitive performance. Our code is released at https://github.com/xuyang-liu16/M2IST.

cs.CV↗

arXiv2025

On the Feasibility of Fingerprinting Collaborative Robot Network Traffic

This study examines privacy risks in collaborative robotics, focusing on the potential for traffic analysis in encrypted robot communications. While previous research has explored low-level command recovery in teleoperation setups, our work investigates high-level motion recovery from script-based control interfaces. We evaluate the efficacy of prominent website fingerprinting techniques (e.g., Tik-Tok, RF) and their limitations in accurately identifying robotic actions due to their inability to capture detailed temporal relationships. To address this, we introduce a traffic classification approach using signal processing techniques, demonstrating high accuracy in action identification and highlighting the vulnerability of encrypted communications to privacy breaches. Additionally, we explore defenses such as packet padding and timing manipulation, revealing the challenges in balancing traffic analysis resistance with network efficiency. Our findings emphasize the need for continued development of practical defenses in robotic privacy and security.

cs.CR↗