arXiv subjects

Zhe Liu

Publications and source records attributed to Zhe Liu.

At least 127 records · Page 7Linked to original sources

arXiv2025

A quantum-coherent photon--emitter interface in the original telecom band

Quantum dots stand out as the most advanced and versatile light-matter interface available today. Their ability to deliver high-quality, high-rate, and pure photons has set benchmarks that far surpass other emitters. Yet, a critical frontier has remained elusive: achieving these exceptional capabilities at telecom wavelengths, bridging the gap to fiber-optic infrastructure and scalable silicon photonics. Overcoming this challenge demands high quality quantum materials and devices which, despite extensive efforts, have not been realized yet. Here, we demonstrate waveguide-integrated quantum dots and realize a fully quantum-coherent photon-emitter interface operating in the original telecommunication band. The quality is assessed by recording transform-limited linewidths only 8 % broader than the inverse lifetime and bright 41.7 MHz emission rate under 80 MHz $π$-pulse excitation, unlocking the full potential of quantum dots for scalable quantum networks.

physics.optics↗

arXiv2025

Consistent Estimation of Numerical Distributions under Local Differential Privacy by Wavelet Expansion

Distribution estimation under local differential privacy (LDP) is a fundamental and challenging task. Significant progresses have been made on categorical data. However, due to different evaluation metrics, these methods do not work well when transferred to numerical data. In particular, we need to prevent the probability mass from being misplaced far away. In this paper, we propose a new approach that express the sample distribution using wavelet expansions. The coefficients of wavelet series are estimated under LDP. Our method prioritizes the estimation of low-order coefficients, in order to ensure accurate estimation at macroscopic level. Therefore, the probability mass is prevented from being misplaced too far away from its ground truth. We establish theoretical guarantees for our methods. Experiments show that our wavelet expansion method significantly outperforms existing solutions under Wasserstein and KS distances.

cs.LG↗

arXiv2025

Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions

Generating diverse follow-up questions that uncover missing information remains challenging for conversational agents, particularly when they run on small, locally hosted models. To address this, we develop an information-gap-driven knowledge distillation pipeline in which a teacher LLM generates a comprehensive answer, contrasts it with the initial answer to identify information gaps, and formulates gap-bridging follow-up questions. Using this pipeline, we augment the existing FollowupQG dataset tenfold. We then fine-tune smaller student models on the augmented dataset to distill the teacher's knowledge. Experiments with selected teacher-student model pairs show that fine-tuned students achieve significantly higher informativeness and diversity than variations trained on the original dataset. These findings indicate that our pipeline, which mirrors the human cognitive process of information seeking, provides an efficient distillation channel from state-of-the-art LLMs to smaller models, enabling resource-constrained conversational systems to generate more diverse and informative follow-up questions.

cs.CL↗

arXiv2025

Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents

Mobile agents powered by vision-language models (VLMs) are increasingly adopted for tasks such as UI automation and camera-based assistance. These agents are typically fine-tuned using small-scale, user-collected data, making them susceptible to stealthy training-time threats. This work introduces VIBMA, the first clean-text backdoor attack targeting VLM-based mobile agents. The attack injects malicious behaviors into the model by modifying only the visual input while preserving textual prompts and instructions, achieving stealth through the complete absence of textual anomalies. Once the agent is fine-tuned on this poisoned data, adding a predefined visual pattern (trigger) at inference time activates the attacker-specified behavior (backdoor). Our attack aligns the training gradients of poisoned samples with those of an attacker-specified target instance, effectively embedding backdoor-specific features into the poisoned data. To ensure the robustness and stealthiness of the attack, we design three trigger variants that better resemble real-world scenarios: static patches, dynamic motion patterns, and low-opacity blended content. Extensive experiments on six Android applications and three mobile-compatible VLMs demonstrate that our attack achieves high success rates (ASR up to 94.67%) while preserving clean-task behavior (FSR up to 95.85%). We further conduct ablation studies to understand how key design factors impact attack reliability and stealth. These findings is the first to reveal the security vulnerabilities of mobile agents and their susceptibility to backdoor injection, underscoring the need for robust defenses in mobile agent adaptation pipelines.

cs.CR↗

arXiv2025

LKA: Large Kernel Adapter for Enhanced Medical Image Classification

Despite the notable success of current Parameter-Efficient Fine-Tuning (PEFT) methods across various domains, their effectiveness on medical datasets falls short of expectations. This limitation arises from two key factors: (1) medical images exhibit extensive anatomical variation and low contrast, necessitating a large receptive field to capture critical features, and (2) existing PEFT methods do not explicitly address the enhancement of receptive fields. To overcome these challenges, we propose the Large Kernel Adapter (LKA), designed to expand the receptive field while maintaining parameter efficiency. The proposed LKA consists of three key components: down-projection, channel-wise large kernel convolution, and up-projection. Through extensive experiments on various datasets and pre-trained models, we demonstrate that the incorporation of a larger kernel size is pivotal in enhancing the adaptation of pre-trained models for medical image analysis. Our proposed LKA outperforms 11 commonly used PEFT methods, surpassing the state-of-the-art by 3.5% in top-1 accuracy across five medical datasets.

cs.CE↗

arXiv2025

Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance

Low-Light Enhancement (LLE) is aimed at improving the quality of photos/videos captured under low-light conditions. It is worth noting that most existing LLE methods do not take advantage of geometric modeling. We believe that incorporating geometric information can enhance LLE performance, as it provides insights into the physical structure of the scene that influences illumination conditions. To address this, we propose a Geometry-Guided Low-Light Enhancement Refine Framework (GG-LLERF) designed to assist low-light enhancement models in learning improved features for LLE by integrating geometric priors into the feature representation space. In this paper, we employ depth priors as the geometric representation. Our approach focuses on the integration of depth priors into various LLE frameworks using a unified methodology. This methodology comprises two key novel modules. First, a depth-aware feature extraction module is designed to inject depth priors into the image representation. Then, Hierarchical Depth-Guided Feature Fusion Module (HDGFFM) is formulated with a cross-domain attention mechanism, which combines depth-aware features with the original image features within the LLE model. We conducted extensive experiments on public low-light image and video enhancement benchmarks. The results illustrate that our designed framework significantly enhances existing LLE methods.

cs.CV↗

arXiv2025

$D^{()}\bar{B}^{()}$ dynamics in chiral effective field theory

In this work, we systematically study the interactions of the $S$-wave $D^{(*)}\bar{B}^{(*)}$ systems within the framework of chiral effective field theory in heavy hadron formalism. We calculate the $D^{(*)}\bar{B}^{(*)}$ effective potentials up to next-to-leading order, explore the bound state formations, and investigate the $D^{(*)}\bar{B}^{(*)}$ scattering properties such as scattering rate, scattering length, and effective range. Our results show that all $I=1$ $D^{(*)}\bar{B}^{(*)}$ potentials are repulsive, preventing the formation of bound states, while the $I=0$ potentials are generally attractive. Specifically, we get two important observations: first, the shallow bound state is more likely to exist in the $D\bar{B}[I(J^{P})=0(0^{+})]$ system than in the $D\bar{B}^{*}[I(J^{P})=0(1^{+})]$ system; second, $D^{*}\bar{B}^{*}[I(J^{P})=0(0^{+})]$ and $D^{*}\bar{B}^{*}[I(J^{P})=0(1^{+})]$ systems possess relatively large binding energies and positive scattering lengths, which suggests strong bound state formations in these channels. So the attractions in the $D^{*}\bar{B}^{*}[I=0]$ systems are deeper than those in the $D\bar{B}^{(*)}[I=0]$ systems, thus we strongly recommend the future experiment to search for the $D^{*}\bar{B}^{*}[I=0]$ tetraquark systems. We also investigate the coupled-channel effects on the $J=0, 1$ systems and conclude that the inclusion of the coupled channels introduces small but visible influences. In addition, we also investigate the dependencies of the $D\bar{B}^{(*)}$ binding energies on the contact low-energy coupling constants.

hep-ph↗

arXiv2025

Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT

This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on Recurrent Neural Network Transducers (RNN-T) can perform real-time transcription, achieving streaming translation in real-time remains a significant challenge. To address this issue, we propose a simultaneous translation approach that effectively balances translation quality and latency. We also investigate efficient integration of ASR and MT, leveraging linguistic cues generated by the ASR system to manage context and utilizing efficient beam-search pruning techniques such as time-out and forced finalization to maintain system's real-time factor. We apply our approach to an on-device bilingual conversational speech translation and demonstrate that our techniques outperform baselines in terms of latency and quality. Notably, our technique narrows the quality gap with non-streaming translation systems, paving the way for more accurate and efficient real-time speech translation.

cs.CL↗

arXiv2025

CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis

Clinicians usually combine information from multiple sources to achieve the most accurate diagnosis, and this has sparked increasing interest in leveraging multimodal deep learning for diagnosis. However, in real clinical scenarios, due to differences in incidence rates, multimodal medical data commonly face the issue of class imbalance, which makes it difficult to adequately learn the features of minority classes. Most existing methods tackle this issue with resampling or loss reweighting, but they are prone to overfitting or underfitting and fail to capture cross-modal interactions. Therefore, we propose a Curriculum Learning framework for Imbalanced Multimodal Diagnosis (CLIMD). Specifically, we first design multimodal curriculum measurer that combines two indicators, intra-modal confidence and inter-modal complementarity, to enable the model to focus on key samples and gradually adapt to complex category distributions. Additionally, a class distribution-guided training scheduler is introduced, which enables the model to progressively adapt to the imbalanced class distribution during training. Extensive experiments on multiple multimodal medical datasets demonstrate that the proposed method outperforms state-of-the-art approaches across various metrics and excels in handling imbalanced multimodal medical data. Furthermore, as a plug-and-play CL framework, CLIMD can be easily integrated into other models, offering a promising path for improving multimodal disease diagnosis accuracy. Code is publicly available at https://github.com/KHan-UJS/CLIMD.

cs.CV↗

arXiv2025

Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval

Open-set 3D object retrieval (3DOR) is an emerging task aiming to retrieve 3D objects of unseen categories beyond the training set. Existing methods typically utilize all modalities (i.e., voxels, point clouds, multi-view images) and train specific backbones before fusion. However, they still struggle to produce generalized representations due to insufficient 3D training data. Being contrastively pre-trained on web-scale image-text pairs, CLIP inherently produces generalized representations for a wide range of downstream tasks. Building upon it, we present a simple yet effective framework named Describe, Adapt and Combine (DAC) by taking only multi-view images for open-set 3DOR. DAC innovatively synergizes a CLIP model with a multi-modal large language model (MLLM) to learn generalized 3D representations, where the MLLM is used for dual purposes. First, it describes the seen category information to align with CLIP's training objective for adaptation during training. Second, it provides external hints about unknown objects complementary to visual cues during inference. To improve the synergy, we introduce an Additive-Bias Low-Rank adaptation (AB-LoRA), which alleviates overfitting and further enhances the generalization to unseen categories. With only multi-view images, DAC significantly surpasses prior arts by an average of +10.01\% mAP on four open-set 3DOR datasets. Moreover, its generalization is also validated on image-based and cross-dataset setups. Code is available at https://github.com/wangzhichuan123/DAC.

cs.CV↗

arXiv2025

UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block

Depth estimation plays a crucial role in 3D scene understanding and is extensively used in a wide range of vision tasks. Image-based methods struggle in challenging scenarios, while event cameras offer high dynamic range and temporal resolution but face difficulties with sparse data. Combining event and image data provides significant advantages, yet effective integration remains challenging. Existing CNN-based fusion methods struggle with occlusions and depth disparities due to limited receptive fields, while Transformer-based fusion methods often lack deep modality interaction. To address these issues, we propose UniCT Depth, an event-image fusion method that unifies CNNs and Transformers to model local and global features. We propose the Convolution-compensated ViT Dual SA (CcViT-DA) Block, designed for the encoder, which integrates Context Modeling Self-Attention (CMSA) to capture spatial dependencies and Modal Fusion Self-Attention (MFSA) for effective cross-modal fusion. Furthermore, we design the tailored Detail Compensation Convolution (DCC) Block to improve texture details and enhances edge representations. Experiments show that UniCT Depth outperforms existing image, event, and fusion-based monocular depth estimation methods across key metrics.

cs.CV↗

arXiv2025

LONG3R: Long Sequence Streaming 3D Reconstruction

Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either rely on time-consuming offline optimization or are restricted to shorter sequences, hindering their applicability in real-time scenarios. In this work, we propose LONG3R (LOng sequence streaming 3D Reconstruction), a novel model designed for streaming multi-view 3D scene reconstruction over longer sequences. Our model achieves real-time processing by operating recurrently, maintaining and updating memory with each new observation. We first employ a memory gating mechanism to filter relevant memory, which, together with a new observation, is fed into a dual-source refined decoder for coarse-to-fine interaction. To effectively capture long-sequence memory, we propose a 3D spatio-temporal memory that dynamically prunes redundant spatial information while adaptively adjusting resolution along the scene. To enhance our model's performance on long sequences while maintaining training efficiency, we employ a two-stage curriculum training strategy, each stage targeting specific capabilities. Experiments demonstrate that LONG3R outperforms state-of-the-art streaming methods, particularly for longer sequences, while maintaining real-time inference speed. Project page: https://zgchen33.github.io/LONG3R/.

cs.CV↗

arXiv2025

HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point clouds. While recent Mamba-based approaches offer efficient processing with linear complexity, they struggle with feature representation when extracting 3D features. However, effectively combining these complementary strengths remains an open challenge in this field. In this paper, we propose HybridTM, the first hybrid architecture that integrates Transformer and Mamba for 3D semantic segmentation. In addition, we propose the Inner Layer Hybrid Strategy, which combines attention and Mamba at a finer granularity, enabling simultaneous capture of long-range dependencies and fine-grained local features. Extensive experiments demonstrate the effectiveness and generalization of our HybridTM on diverse indoor and outdoor datasets. Furthermore, our HybridTM achieves state-of-the-art performance on ScanNet, ScanNet200, and nuScenes benchmarks. The code will be made available at https://github.com/deepinact/HybridTM.

cs.CV↗

arXiv2025

QuantEIT: Ultra-Lightweight Quantum-Assisted Inference for Chest Electrical Impedance Tomography

Electrical Impedance Tomography (EIT) is a non-invasive, low-cost bedside imaging modality with high temporal resolution, making it suitable for bedside monitoring. However, its inherently ill-posed inverse problem poses significant challenges for accurate image reconstruction. Deep learning (DL)-based approaches have shown promise but often rely on complex network architectures with a large number of parameters, limiting efficiency and scalability. Here, we propose an Ultra-Lightweight Quantum-Assisted Inference (QuantEIT) framework for EIT image reconstruction. QuantEIT leverages a Quantum-Assisted Network (QA-Net), combining parallel 2-qubit quantum circuits to generate expressive latent representations that serve as implicit nonlinear priors, followed by a single linear layer for conductivity reconstruction. This design drastically reduces model complexity and parameter number. Uniquely, QuantEIT operates in an unsupervised, training-data-free manner and represents the first integration of quantum circuits into EIT image reconstruction. Extensive experiments on simulated and real-world 2D and 3D EIT lung imaging data demonstrate that QuantEIT outperforms conventional methods, achieving comparable or superior reconstruction accuracy using only 0.2% of the parameters, with enhanced robustness to noise.

cs.CV↗

arXiv2025

D2IP: Deep Dynamic Image Prior for 3D Time-sequence Pulmonary Impedance Imaging

Unsupervised learning methods, such as Deep Image Prior (DIP), have shown great potential in tomographic imaging due to their training-data-free nature and high generalization capability. However, their reliance on numerous network parameter iterations results in high computational costs, limiting their practical application, particularly in complex 3D or time-sequence tomographic imaging tasks. To overcome these challenges, we propose Deep Dynamic Image Prior (D2IP), a novel framework for 3D time-sequence imaging. D2IP introduces three key strategies - Unsupervised Parameter Warm-Start (UPWS), Temporal Parameter Propagation (TPP), and a customized lightweight reconstruction backbone, 3D-FastResUNet - to accelerate convergence, enforce temporal coherence, and improve computational efficiency. Experimental results on both simulated and clinical pulmonary datasets demonstrate that D2IP enables fast and accurate 3D time-sequence Electrical Impedance Tomography (tsEIT) reconstruction. Compared to state-of-the-art baselines, D2IP delivers superior image quality, with a 24.8% increase in average MSSIM and an 8.1% reduction in ERR, alongside significantly reduced computational time (7.1x faster), highlighting its promise for clinical dynamic pulmonary imaging.

eess.IV↗

arXiv2025

End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localization

Robot localization using a built map is essential for a variety of tasks including accurate navigation and mobile manipulation. A popular approach to robot localization is based on image-to-point cloud registration, which combines illumination-invariant LiDAR-based mapping with economical image-based localization. However, the recent works for image-to-point cloud registration either divide the registration into separate modules or project the point cloud to the depth image to register the RGB and depth images. In this paper, we present I2PNet, a novel end-to-end 2D-3D registration network, which directly registers the raw 3D point cloud with the 2D RGB image using differential modules with a united target. The 2D-3D cost volume module for differential 2D-3D association is proposed to bridge feature extraction and pose regression. The soft point-to-pixel correspondence is implicitly constructed on the intrinsic-independent normalized plane in the 2D-3D cost volume module. Moreover, we introduce an outlier mask prediction module to filter the outliers in the 2D-3D association before pose regression. Furthermore, we propose the coarse-to-fine 2D-3D registration architecture to increase localization accuracy. Extensive localization experiments are conducted on the KITTI, nuScenes, M2DGR, Argoverse, Waymo, and Lyft5 datasets. The results demonstrate that I2PNet outperforms the state-of-the-art by a large margin and has a higher efficiency than the previous works. Moreover, we extend the application of I2PNet to the camera-LiDAR online calibration and demonstrate that I2PNet outperforms recent approaches on the online calibration task. Source codes are released at https://github.com/IRMVLab/I2PNet.

cs.RO↗

arXiv2025

MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices

Recent advancements in deep neural networks have driven significant progress in image enhancement (IE). However, deploying deep learning models on resource-constrained platforms, such as mobile devices, remains challenging due to high computation and memory demands. To address these challenges and facilitate real-time IE on mobile, we introduce an extremely lightweight Convolutional Neural Network (CNN) framework with around 4K parameters. Our approach integrates reparameterization with an Incremental Weight Optimization strategy to ensure efficiency. Additionally, we enhance performance with a Feature Self-Transform module and a Hierarchical Dual-Path Attention mechanism, optimized with a Local Variance-Weighted loss. With this efficient framework, we are the first to achieve real-time IE inference at up to 1,100 frames per second (FPS) while delivering competitive image quality, achieving the best trade-off between speed and performance across multiple IE tasks. The code will be available at https://github.com/AVC2-UESTC/MobileIE.git.

cs.CV↗

arXiv2025

SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents

With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large model-driven agents. However, the related systems are also increasingly exposed to potential jailbreak risks. Attackers may induce the agents to bypass the original behavioral constraints through specific inputs, and then trigger certain risky and sensitive operations, such as modifying settings, executing unauthorized commands, or impersonating user identities, which brings new challenges to system security. Existing security measures for intelligent agents still have limitations when facing complex interactions, especially in detecting potentially risky behaviors across multiple rounds of conversations or sequences of tasks. In addition, an efficient and consistent automated methodology to assist in assessing and determining the impact of such risks is currently lacking. This work explores the security issues surrounding mobile multimodal agents, attempts to construct a risk discrimination mechanism by incorporating behavioral sequence information, and designs an automated assisted assessment scheme based on a large language model. Through preliminary validation in several representative high-risk tasks, the results show that the method can improve the recognition of risky behaviors to some extent and assist in reducing the probability of agents being jailbroken. We hope that this study can provide some valuable references for the security risk modeling and protection of multimodal intelligent agent systems.

cs.AI↗