arXiv subjects

Jianqiang Li

Publications and source records attributed to Jianqiang Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

A Dataset of Low-Rated Applications from the Amazon Appstore for User Feedback Analysis

In todays digital landscape, end-user feedback plays a crucial role in the evolution of software applications, particularly in addressing issues that hinder user experience. While much research has focused on high-rated applications, low-rated applications often remain unexplored, despite their potential to reveal valuable insights. This study introduces a novel dataset curated from 64 low-rated applications sourced from the Amazon Software Appstore (ASA), containing 79,821 user reviews. The dataset is designed to capture the most frequent issues identified by users, which are critical for improving software quality. To further enhance the dataset utility, a subset of 6000 reviews was manually annotated to classify them into six district issue categories: user interface (UI) and user experience (UX), functionality and features, compatibility and device specificity, performance and stability, customer support and responsiveness, and security and privacy issues. This annotated dataset is a valuable resource for developing machine learning-based approaches aiming to automate the classification of user feedback into various issue types. Making both the annotated and raw datasets publicly available provides researchers and developers with a crucial tool to understand common issues in low-rated apps and inform software improvements. The comprehensive analysis and availability of this dataset lay the groundwork for data-derived solutions to improve software quality based on user feedback. Additionally, the dataset can provide opportunities for software vendors and researchers to explore various software evolution-related activities, including frequently missing features, sarcasm, and associated emotions, which will help better understand the reasons for comparatively low app ratings.

cs.SE↗

arXiv2025

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification

Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficiently addressed by techniques developed for dense models. In this work, the MoE-specific safety risk of positional vulnerability-that safety-aligned behaviors rely on specific expert modules-is formalized and systematically analyzed. An analytical framework, SAFEx, is presented to robustly identify, characterize, and validate safety-critical experts via a stability-based expert selection procedure, and to decompose them into two functional groups: the Harmful Content Detection Group (HCDG), which specializes in identifying and recognizing harmful content within user inputs, and the Harmful Response Control Group (HRCG), which specializes in controlling and enforcing model behaviors to generate appropriate safety responses. Expert-level interventions are conducted to probe causality and to test mitigation. Targeted masking of SAFEx-selected experts reveals that safety behavior is highly concentrated. On Qwen3-30B-A3B, configured with 48 MoE-FFN layers and 128 experts per layer under top-8 routing (48x128=6,144 experts in total), disabling 12 selected experts reduces the refusal rate by 22%. In addition, lightweight adaptation is performed using LoRA under three configurations-the HRCG, the union of HCDG and HRCG, and all experts-and the resulting updates are composed through negative weight merging targeted at the HRCG, leading to improved refusal under adversarial prompts without full-model retraining. These results establish positional vulnerability as a distinct MoE-specific safety challenge and provide a practical, compute-efficient pathway for expert-level safety interventions within routed architectures.

cs.LG↗

arXiv2025

AuditAgent: Expert-Guided Multi-Agent Reasoning for Cross-Document Fraudulent Evidence Discovery

Financial fraud detection in real-world scenarios presents significant challenges due to the subtlety and dispersion of evidence across complex, multi-year financial disclosures. In this work, we introduce a novel multi-agent reasoning framework AuditAgent, enhanced with auditing domain expertise, for fine-grained evidence chain localization in financial fraud cases. Leveraging an expert-annotated dataset constructed from enforcement documents and financial reports released by the China Securities Regulatory Commission, our approach integrates subject-level risk priors, a hybrid retrieval strategy, and specialized agent modules to efficiently identify and aggregate cross-report evidence. Extensive experiments demonstrate that our method substantially outperforms General-Purpose Agent paradigm in both recall and interpretability, establishing a new benchmark for automated, transparent financial forensics. Our results highlight the value of domain-specific reasoning and dataset construction for advancing robust financial fraud detection in practical, real-world regulatory applications.

cs.AI↗

arXiv2025

Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus

Quantum machine learning (QML) holds the promise to solve classically intractable problems, but, as critical data can be fragmented across private clients, there is a need for distributed QML in a quantum federated learning (QFL) format. However, the quantum computers that different clients have access to can be error-prone and have heterogeneous error properties, requiring them to run circuits of different depths. We propose a novel solution to this QFL problem, Quorus, that utilizes a layerwise loss function for effective training of varying-depth quantum models, which allows clients to choose models for high-fidelity output based on their individual capacity. Quorus also presents various model designs based on client needs that optimize for shot budget, qubit count, midcircuit measurement, and optimization space. Our simulation and real-hardware results show the promise of Quorus: it increases the magnitude of gradients of higher depth clients and improves testing accuracy by 12.4% on average over the state-of-the-art.

quant-ph↗

arXiv2025

Automating Conflict-Aware ACL Configurations with Natural Language Intents

ACL configuration is essential for managing network flow reachability, yet its complexity grows significantly with topologies and pre-existing rules. To carry out ACL configuration, the operator needs to (1) understand the new configuration policies or intents and translate them into concrete ACL rules, (2) check and resolve any conflicts between the new and existing rules, and (3) deploy them across the network. Existing systems rely heavily on manual efforts for these tasks, especially for the first two, which are tedious, error-prone, and impractical to scale. We propose Xumi to tackle this problem. Leveraging LLMs with domain knowledge of the target network, Xumi automatically and accurately translates the natural language intents into complete ACL rules to reduce operators' manual efforts. Xumi then detects all potential conflicts between new and existing rules and generates resolved intents for deployment with operators' guidance, and finally identifies the best deployment plan that minimizes the rule additions while satisfying all intents. Evaluation shows that Xumi accelerates the entire configuration pipeline by over 10x compared to current practices, addresses O(100) conflicting ACLs and reduces rule additions by ~40% in modern cloud network.

cs.NI↗

arXiv2025

BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models

Large vision models (LVM) based gait recognition has achieved impressive performance. However, existing LVM-based approaches may overemphasize gait priors while neglecting the intrinsic value of LVM itself, particularly the rich, distinct representations across its multi-layers. To adequately unlock LVM's potential, this work investigates the impact of layer-wise representations on downstream recognition tasks. Our analysis reveals that LVM's intermediate layers offer complementary properties across tasks, integrating them yields an impressive improvement even without rich well-designed gait priors. Building on this insight, we propose a simple and universal baseline for LVM-based gait recognition, termed BiggerGait. Comprehensive evaluations on CCPG, CAISA-B*, SUSTech1K, and CCGR\_MINI validate the superiority of BiggerGait across both within- and cross-domain tasks, establishing it as a simple yet practical baseline for gait representation learning. All the models and code will be publicly available.

cs.CV↗

arXiv2025

Multidimensional Electrical Networks and their Application to Exponential Speedups for Graph Problems

Recently, Apers and Piddock [TQC '23] strengthened the connection between quantum walks and electrical networks via Kirchhoff's Law and Ohm's Law. In this work, we develop a new multidimensional electrical network by defining Alternative Kirchhoff's Law and Alternative Ohm's Law based on the multidimensional quantum walk framework by Jeffery and Zur [STOC '23]. In analogy to the connection between the incidence matrix of a graph and Kirchhoff's Law and Ohm's Law in an electrical network, we rebuild the connection between the alternative incidence matrix and Alternative Kirchhoff's Law and Alternative Ohm's Law. This new framework enables generating an alternative electrical flow over the edges on graphs, which has the potential to be applied to a broader range of graph problems, benefiting both quantum and classical algorithm design. We first use this framework to generate quantum alternative electrical flow states and use it to find a marked vertex in one-dimensional random hierarchical graphs as defined by Balasubramanian, Li, and Harrow [arXiv '23]. In this work, they generalised the exponential quantum-classical separation of the welded tree graph by Childs, Cleve, Deotto, Farhi, Gutmann, and Spielman [STOC '03] to random hierarchical graphs. Our result partially recovers their results with an arguably simpler analysis. Furthermore, this framework also allows us to demonstrate an exponential quantum speedup for the pathfinding problem in a type of regular graph, which we name the welded tree circuit graph. The exponential quantum advantage is obtained by efficiently generating quantum alternative electrical flow states and then sampling from them to find an s-t path in the welded tree circuit graph. By comparison, Li [arXiv '23] constructed a non-regular graph based on welded trees and used the degree information to achieve a similar speedup.

quant-ph↗

arXiv2025

ADNP-15: An Open-Source Histopathological Dataset for Neuritic Plaque Segmentation in Human Brain Whole Slide Images with Frequency Domain Image Enhancement for Stain Normalization

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by amyloid-beta plaques and tau neurofibrillary tangles, which serve as key histopathological features. The identification and segmentation of these lesions are crucial for understanding AD progression but remain challenging due to the lack of large-scale annotated datasets and the impact of staining variations on automated image analysis. Deep learning has emerged as a powerful tool for pathology image segmentation; however, model performance is significantly influenced by variations in staining characteristics, necessitating effective stain normalization and enhancement techniques. In this study, we address these challenges by introducing an open-source dataset (ADNP-15) of neuritic plaques (i.e., amyloid deposits combined with a crown of dystrophic tau-positive neurites) in human brain whole slide images. We establish a comprehensive benchmark by evaluating five widely adopted deep learning models across four stain normalization techniques, providing deeper insights into their influence on neuritic plaque segmentation. Additionally, we propose a novel image enhancement method that improves segmentation accuracy, particularly in complex tissue structures, by enhancing structural details and mitigating staining inconsistencies. Our experimental results demonstrate that this enhancement strategy significantly boosts model generalization and segmentation accuracy. All datasets and code are open-source, ensuring transparency and reproducibility while enabling further advancements in the field.

eess.IV↗

arXiv2025

Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning

Enabling a high-degree-of-freedom robot to learn specific skills is a challenging task due to the complexity of robotic dynamics. Reinforcement learning (RL) has emerged as a promising solution; however, addressing such problems requires the design of multiple reward functions to account for various constraints in robotic motion. Existing approaches typically sum all reward components indiscriminately to optimize the RL value function and policy. We argue that this uniform inclusion of all reward components in policy optimization is inefficient and limits the robot's learning performance. To address this, we propose an Automated Hybrid Reward Scheduling (AHRS) framework based on Large Language Models (LLMs). This paradigm dynamically adjusts the learning intensity of each reward component throughout the policy optimization process, enabling robots to acquire skills in a gradual and structured manner. Specifically, we design a multi-branch value network, where each branch corresponds to a distinct reward component. During policy optimization, each branch is assigned a weight that reflects its importance, and these weights are automatically computed based on rules designed by LLMs. The LLM generates a rule set in advance, derived from the task description, and during training, it selects a weight calculation rule from the library based on language prompts that evaluate the performance of each branch. Experimental results demonstrate that the AHRS method achieves an average 6.48% performance improvement across multiple high-degree-of-freedom robotic tasks.

cs.RO↗

arXiv2025

Exponential Quantum Advantage for Pathfinding in Regular Sunflower Graphs

Finding problems that allow for superpolynomial quantum speedup is one of the most important tasks in quantum computation. A key challenge is identifying problem structures that can only be exploited by quantum mechanics. In this paper, we find a class of graphs that allows for exponential quantum-classical separation for the pathfinding problem with the adjacency list oracle, and this class of graphs is named regular sunflower graphs. We prove that, with high probability, a regular sunflower graph of degree at least $7$ is a mild expander graph, that is, the spectral gap of the graph Laplacian is at least inverse polylogarithmic in the graph size. We provide an efficient quantum algorithm to find an $s$-$t$ path in the regular sunflower graph while any classical algorithm takes exponential time. This quantum advantage is achieved by efficiently preparing a $0$-eigenstate of the adjacency matrix of the regular sunflower graph as a quantum superposition state over the vertices, and this quantum state contains enough information to help us efficiently find an $s$-$t$ path in the regular sunflower graph. Because the security of an isogeny-based cryptosystem depends on the hardness of finding an $s$-$t$ path in an expander graph \cite{Charles2009}, a quantum speedup of the pathfinding problem on an expander graph is of significance. Our result represents a step towards this goal as the first provable exponential speedup for pathfinding in a mild expander graph.

quant-ph↗

arXiv2025

Performance Estimation for Supervised Medical Image Segmentation Models on Unlabeled Data Using UniverSeg

The performance of medical image segmentation models is usually evaluated using metrics like the Dice score and Hausdorff distance, which compare predicted masks to ground truth annotations. However, when applying the model to unseen data, such as in clinical settings, it is often impractical to annotate all the data, making the model's performance uncertain. To address this challenge, we propose the Segmentation Performance Evaluator (SPE), a framework for estimating segmentation models' performance on unlabeled data. This framework is adaptable to various evaluation metrics and model architectures. Experiments on six publicly available datasets across six evaluation metrics including pixel-based metrics such as Dice score and distance-based metrics like HD95, demonstrated the versatility and effectiveness of our approach, achieving a high correlation (0.956$\pm$0.046) and low MAE (0.025$\pm$0.019) compare with real Dice score on the independent test set. These results highlight its ability to reliably estimate model performance without requiring annotations. The SPE framework integrates seamlessly into any model training process without adding training overhead, enabling performance estimation and facilitating the real-world application of medical image segmentation algorithms. The source code is publicly available

eess.IV↗

arXiv2025

$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect

Large kernels make standard convolutional neural networks (CNNs) great again over transformer architectures in various vision tasks. Nonetheless, recent studies meticulously designed around increasing kernel size have shown diminishing returns or stagnation in performance. Thus, the hidden factors of large kernel convolution that affect model performance remain unexplored. In this paper, we reveal that the key hidden factors of large kernels can be summarized as two separate components: extracting features at a certain granularity and fusing features by multiple pathways. To this end, we leverage the multi-path long-distance sparse dependency relationship to enhance feature utilization via the proposed Shiftwise (SW) convolution operator with a pure CNN architecture. In a wide range of vision tasks such as classification, segmentation, and detection, SW surpasses state-of-the-art transformers and CNN architectures, including SLaK and UniRepLKNet. More importantly, our experiments demonstrate that $3 \times 3$ convolutions can replace large convolutions in existing large kernel CNNs to achieve comparable effects, which may inspire follow-up works. Code and all the models at https://github.com/lidc54/shift-wiseConv.

cs.CV↗

arXiv2025

A Robust and Distribution-Fitting-Free Estimation Approach of Travel Time Percentile Function based on L-moments

Travel time is one of the key indicators monitored by intelligent transportation systems, helping the systems to gain real-time insights into traffic situations, predict congestion, and identify network bottlenecks. Travel time exhibits variability, and thus suitable probability distributions are necessary to accurately capture full information of travel time variability. Considering the potential issues of insufficient sample size and the disturbance of outliers in actual observations, as well as the heterogeneity of travel time distributions, we propose a robust and distribution-fitting-free estimation approach of travel time percentile function using L-moments based Normal-Polynomial Transformation. We examine the proposed approach from perspectives of validity, robustness, and stability based on both theoretical probability distributions and real data. The results indicate that the proposed approach exhibits high estimation validity, accuracy and low volatility in dealing with outliers, even in scenarios with small sample sizes.

stat.AP↗

arXiv2025

Comparative Analysis of Pre-trained Deep Learning Models and DINOv2 for Cushing's Syndrome Diagnosis in Facial Analysis

Cushing's syndrome is a condition caused by excessive glucocorticoid secretion from the adrenal cortex, often manifesting with moon facies and plethora, making facial data crucial for diagnosis. Previous studies have used pre-trained convolutional neural networks (CNNs) for diagnosing Cushing's syndrome using frontal facial images. However, CNNs are better at capturing local features, while Cushing's syndrome often presents with global facial features. Transformer-based models like ViT and SWIN, which utilize self-attention mechanisms, can better capture long-range dependencies and global features. Recently, DINOv2, a foundation model based on visual Transformers, has gained interest. This study compares the performance of various pre-trained models, including CNNs, Transformer-based models, and DINOv2, in diagnosing Cushing's syndrome. We also analyze gender bias and the impact of freezing mechanisms on DINOv2. Our results show that Transformer-based models and DINOv2 outperformed CNNs, with ViT achieving the highest F1 score of 85.74%. Both the pre-trained model and DINOv2 had higher accuracy for female samples. DINOv2 also showed improved performance when freezing parameters. In conclusion, Transformer-based models and DINOv2 are effective for Cushing's syndrome classification.

cs.LG↗

arXiv2025

Deep Learning-Based Feature Fusion for Emotion Analysis and Suicide Risk Differentiation in Chinese Psychological Support Hotlines

Mental health is a critical global public health issue, and psychological support hotlines play a pivotal role in providing mental health assistance and identifying suicide risks at an early stage. However, the emotional expressions conveyed during these calls remain underexplored in current research. This study introduces a method that combines pitch acoustic features with deep learning-based features to analyze and understand emotions expressed during hotline interactions. Using data from China's largest psychological support hotline, our method achieved an F1-score of 79.13% for negative binary emotion classification.Additionally, the proposed approach was validated on an open dataset for multi-class emotion classification,where it demonstrated better performance compared to the state-of-the-art methods. To explore its clinical relevance, we applied the model to analysis the frequency of negative emotions and the rate of emotional change in the conversation, comparing 46 subjects with suicidal behavior to those without. While the suicidal group exhibited more frequent emotional changes than the non-suicidal group, the difference was not statistically significant.Importantly, our findings suggest that emotional fluctuation intensity and frequency could serve as novel features for psychological assessment scales and suicide risk prediction.The proposed method provides valuable insights into emotional dynamics and has the potential to advance early intervention and improve suicide prevention strategies through integration with clinical tools and assessments The source code is publicly available at https://github.com/Sco-field/Speechemotionrecognition/tree/main.

cs.CL↗

arXiv2024

Exponential speedup of quantum algorithms for the pathfinding problem

Given $x, y$ on an unweighted undirected graph $G$, the goal of the pathfinding problem is to find an $x$-$y$ path. In this work, we first construct a graph $G$ based on welded trees and define a pathfinding problem in the adjacency list oracle $O$. Then we provide an efficient quantum algorithm to find an $x$-$y$ path in the graph $G$. Finally, we prove that no classical algorithm can find an $x$-$y$ path in subexponential time with high probability. The pathfinding problem is one of the fundamental graph-related problems. Our findings suggest that quantum algorithms could potentially offer advantages in more types of graphs to solve the pathfinding problem.

quant-ph↗

arXiv2024

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to design reward functions for real-world tasks, especially for high-dimensional robotic control, due to complex relationships among joints and tasks. Recent advancements large language models (LLMs) enable automatic reward function design. However, approaches evaluate reward functions by re-training policies from scratch placing an undue burden on the reward function, expecting it to be effective throughout the whole policy improvement process. We argue for a more practical strategy in robotic autonomy, focusing on refining existing policies with policy-dependent reward functions rather than a universal one. To this end, we propose a novel reward-policy co-evolution framework where the reward function and the learned policy benefit from each other's progressive on-the-fly improvements, resulting in more efficient and higher-performing skill acquisition. Specifically, the reward evolution process translates the robot's previous best reward function, descriptions of tasks and environment into text inputs. These inputs are used to query LLMs to generate a dynamic amount of reward function candidates, ensuring continuous improvement at each round of evolution. For policy evolution, our method generates new policy populations by hybridizing historically optimal and random policies. Through an improved Bayesian optimization, our approach efficiently and robustly identifies the most capable and plastic reward-policy combination, which then proceeds to the next round of co-evolution. Despite using less data, our approach demonstrates an average normalized improvement of 95.3% across various high-dimensional robotic skill learning tasks.

cs.RO↗

arXiv2024

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running.

cs.RO↗