arXiv subjects

Qi Hu

Publications and source records attributed to Qi Hu.

At least 19 recordsLinked to original sources

arXiv2026

Control-Anchored Residual Flow Matching Conditioned on Gene Geometry for Virtual Cell Perturbation Modeling

A central task in virtual cell modeling is predicting single-cell transcriptional responses to unseen genetic perturbations and drug combinations, and biological networks provide valuable priors on gene relationships. Existing graph-based models commonly use the same network to structure gene representations and mediate intergene interactions, thereby implicitly treating stable associations as perturbation-response pathways. Gene Ontology and control-derived coexpression networks encode relatively stable relationships rather than intervention-specific response directions or magnitudes. We therefore propose GeneGeoFlow, which conditions a control-anchored residual flow on gene-wise geometry derived from biological networks to learn intervention-specific transcriptional responses. GeneGeoFlow derives multi-scale spectral coordinates from Gene Ontology and control-derived coexpression networks. A perturbation-conditioned, gene-wise gating module selects relevant structural scales and network sources, yielding intervention-specific gene geometry. The resulting geometry conditions a control-anchored residual flow without explicitly propagating target-derived signals along the graph. Condition-wise optimal transport couples unpaired control and perturbed populations for training, while a Delta-correlation objective aligns the predicted and observed condition-level expression-shift directions. GeneGeoFlow achieves Pearson Delta scores of 0.8979 on the Norman additive benchmark and 0.9088 on five held-out drug combinations in the fixed ComboSciPlex test split. These results support perturbation-conditioned gene geometry as an effective structural prior for intervention-specific response prediction, without conflating stable gene relationships with response propagation.

q-bio.MN↗

arXiv2026

The origin of ferroelectricity, polarization and high resistivity in Aurivillius CaBi2B2O9 (B = Ta, Nb)

Aurivillius layered oxides are important candidates for high-temperature ferroelectric and piezoelectric application. In this work, we combine group theoretic analysis with first-principles calculations to systematically investigate the origin of ferroelectric phase transition, polarization, piezoelectric response, and intrinsic electrical insulation of the two-layer Aurivillius ferroelectrics CaBi$_{2}$B$_{2}$O$_{9}$ (B = Ta, Nb). The results show that the \textit{A2$_1$am} ferroelectric phase arises from the cooperative condensation of a polar mode and nonpolar oxygen octahedral rotation/tilting modes, whose the $\Gamma_5^-$X$_2^+$X$_3^-$ trilinear coupling substantially lowers the total energy and deepens the ferroelectric potential well. The spontaneous polarization and anisotropic piezoelectric response are governed primarily by the cooperative displacements of the Bi$_{2}$O$_{2}$ layers and Ta/NbO$_{6}$ octahedra, with Bi ions providing an indispensable contribution to both responses. More importantly, the polar distortion can be traced to the relative in-plane displacement between adjacent the Bi$_{2}$O$_{2}$ layer and the perovskite-like block. Because this displacement is intrinsic to the alternating Bi$_{2}$O$_{2}$/perovskite-block stacking topology and is independent of the number of perovskite layers, we identify interlayer sliding as a general, layer-number-independent structural mechanism for ferroelectricity in Aurivillius oxides. Our findings establish a unified microscopic picture linking structural distortions, ferroelectric polarization, piezoelectric response, and electronic insulation in CaBi$_{2}$B$_{2}$O$_{9}$ (B = Ta, Nb), and provide theoretical guidance for designing layered ferroelectric oxides with high Curie temperatures and robust insulating behavior.

cond-mat.mtrl-sci↗

arXiv2026

SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces

Large language models are increasingly deployed as coding agents, shifting safety from individual responses to action sequences. Existing benchmarks, however, primarily assess whether models refuse unsafe prompts, leaving impacts on stateful workspaces largely unexamined. We present SABER, a benchmark for environment-aware operational safety that places models in realistic agent-style projects and evaluates safety from the final environment state after a sequence of actions. Beyond binary safety-violation reports, SABER categorizes violations by cause, enabling analysis of model-specific safety profiles. Our evaluations show that even the best-performing model has more than a 54% harmful safety-violation rate (HSR), suggesting that current alignment remains insufficient for realistic project environments. SABER further reveals distinct safety profiles across models. Our benchmark is publicly available at https://github.com/sssr-lab/saber.

cs.SE↗

arXiv2026

Depth-adapted adaptive optics for three-photon microscopy

Three-photon (3-P) fluorescence microscopy enables deep in vivo imaging with subcellular resolution, but its performance is fundamentally constrained by the maximum permissible laser power required to avoid tissue heating and photodamage. Under these power-limited conditions, fluorescence signal generation, image contrast, and achievable imaging depth are strongly affected by the illumination beam profile and aberration correction strategy. In this paper, we showed that using a fixed illumination beam size was suboptimal across different imaging depths. We further showed that conventional Zernike-based adaptive optics (AO) correction degrades under reduced Gaussian illumination beam sizes due to loss of modal orthogonality. This degradation results in slow convergence, unintended focal and field-of-view shifts, and excessive wavefront deformations. To overcome these limitations, we introduced a depth-adapted AO framework in which both the illumination beam profile and the aberration correction basis were dynamically matched to the imaging conditions. By combining depth-optimised beam underfilling with a bespoke set of illumination-matched aberration modes, we achieved faster and more stable AO convergence, enhanced fluorescence signal and image quality during deep in vivo multi-channel neuroimaging. Together, these results established a practical and robust AO-enabled three-photon microscopy strategy that maximised imaging performance under realistic power constraints.

physics.optics↗

arXiv2025

XTrace: A Non-Invasive Dynamic Tracing Framework for Android Applications in Production

As the complexity of mobile applications grows exponentially and the fragmentation of user device environments intensifies, ensuring online application stability faces unprecedented challenges. Traditional methods, such as static logging and post-crash analysis, lack real-time contextual information, rendering them ineffective against "ghost bugs" that only manifest in specific scenarios. This highlights an urgent need for dynamic runtime observability: intercepting and tracing arbitrary methods in production without requiring an app release. We propose XTrace, a novel dynamic tracing framework. XTrace introduces a new paradigm of non-invasive proxying, which avoids direct modification of the virtual machine's underlying data structures. It achieves high-performance method interception by leveraging and optimizing the highly stable, built-in instrumentation mechanism of the Android ART virtual machine. Evaluated in a ByteDance application with hundreds of millions of daily active users, XTrace demonstrated production-grade stability and performance. Large-scale online A/B experiments confirmed its stability, showing no statistically significant impact (p > 0.05) on Crash User Rate or ANR rate, while maintaining minimal overhead (<7 ms startup latency, <0.01 ms per-method call) and broad compatibility (Android 5.0-15+). Critically, XTrace diagnosed over 11 severe online crashes and multiple performance bottlenecks, improving root-cause localization efficiency by over 90%. This confirms XTrace provides a production-grade solution that reconciles the long-standing conflict between stability and comprehensive coverage in Android dynamic tracing.

cs.SE↗

arXiv2025

GTCN-G: A Residual Graph-Temporal Fusion Network for Imbalanced Intrusion Detection

The escalating complexity of network threats and the inherent class imbalance in traffic data present formidable challenges for modern Intrusion Detection Systems (IDS). While Graph Neural Networks (GNNs) excel in modeling topological structures and Temporal Convolutional Networks (TCNs) are proficient in capturing time-series dependencies, a framework that synergistically integrates both while explicitly addressing data imbalance remains an open challenge. This paper introduces a novel deep learning framework, named Gated Temporal Convolutional Network and Graph (GTCN-G), engineered to overcome these limitations. Our model uniquely fuses a Gated TCN (G-TCN) for extracting hierarchical temporal features from network flows with a Graph Convolutional Network (GCN) designed to learn from the underlying graph structure. The core innovation lies in the integration of a residual learning mechanism, implemented via a Graph Attention Network (GAT). This mechanism preserves original feature information through residual connections, which is critical for mitigating the class imbalance problem and enhancing detection sensitivity for rare malicious activities (minority classes). We conducted extensive experiments on two public benchmark datasets, UNSW-NB15 and ToN-IoT, to validate our approach. The empirical results demonstrate that the proposed GTCN-G model achieves state-of-the-art performance, significantly outperforming existing baseline models in both binary and multi-class classification tasks.

cs.LG↗

arXiv2025

Single image sensorless adaptive optics using phase-diversified multifocal array

Image-based sensorless adaptive optics is commonly used to improve microscope image quality through aberration compensation. However, its sequential nature leads to repeated sample exposures and a prolonged aberration estimation and correction process. In this work, we used a phase-diversified foci array to enhance the aberration-related information in multi-photon fluorescence microscope images. We showed that, through use of a neural network-based image processing algorithm, we can extract aberration from a single image frame. We discussed how the number of foci can affect the wavefront correction on a bead sample, and we showed that six foci, in general, perform better than two-foci or ten-foci arrangements. We also applied our technique to correct aberrations in biological samples, including a fixed brain tissue and BPAE cells slide.

physics.optics↗

arXiv2025

Information-guided optimization of image-based sensorless adaptive optics methods

Adaptive optics (AO) are reconfigurable devices that compensate for wavefront distortions or aberrations in optical systems such as microscopes, telescopes and ophthalmoscopes. Aberrations have detrimental effects that can reduce imaging quality and compromise scientific information. Sensorless AO methods were introduced to correct aberrations without a separate wavefront sensor, inferring wavefront-related information directly from phase-diverse sample images. Most sensorless AO control systems, although effective and flexible to use, were operated based on empirical experience with suboptimal performance. In this paper, we introduced a Fisher information-based analysis framework to provide information-guided method optimization. Results suggested that our framework can effectively improve the accuracy and efficiency of different sensorless AO methods. The framework is not specific to any AO method or imaging modality and has the potential to benefit a wide range of applications.

physics.optics↗

arXiv2025

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora

We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models to simultaneously extract knowledge triples and induce comprehensive schemas directly from text, modeling both entities and events while employing conceptualization to organize instances into semantic categories. Processing over 50 million documents, we construct ATLAS (Automated Triple Linking And Schema induction), a family of knowledge graphs with 900+ million nodes and 5.9 billion edges. This approach outperforms state-of-the-art baselines on multi-hop QA tasks and enhances LLM factuality. Notably, our schema induction achieves 92\% semantic alignment with human-crafted schemas with zero manual intervention, demonstrating that billion-scale knowledge graphs with dynamically induced schemas can effectively complement parametric knowledge in large language models.

cs.CL↗

arXiv2025

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning

While Large Language Models (LLMs) exhibit remarkable capabilities, they also introduce significant safety and privacy risks. Current mitigation strategies often fail to preserve contextual reasoning capabilities in risky scenarios. Instead, they rely heavily on sensitive pattern matching to protect LLMs, which limits the scope. Furthermore, they overlook established safety and privacy standards, leading to systemic risks for legal compliance. To address these gaps, we formulate safety and privacy issues into contextualized compliance problems following the Contextual Integrity (CI) theory. Under the CI framework, we align our model with three critical regulatory standards: GDPR, EU AI Act, and HIPAA. Specifically, we employ reinforcement learning (RL) with a rule-based reward to incentivize contextual reasoning capabilities while enhancing compliance with safety and privacy norms. Through extensive experiments, we demonstrate that our method not only significantly enhances legal compliance (achieving a +8.58% accuracy improvement in safety/privacy benchmarks) but also further improves general reasoning capability. For OpenThinker-7B, a strong reasoning model that significantly outperforms its base model Qwen2.5-7B-Instruct across diverse subjects, our method enhances its general reasoning capabilities, with +2.05% and +8.98% accuracy improvement on the MMLU and LegalBench benchmark, respectively.

cs.CL↗

arXiv2025

MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks. Its decentralized architecture, which separates clients and servers, poses unique challenges for systematic safety analysis. This paper proposes a novel framework to enhance MCP safety. Guided by the MAESTRO framework, we first analyze the missing safety mechanisms in MCP, and based on this analysis, we propose the Model Contextual Integrity Protocol (MCIP), a refined version of MCP that addresses these gaps. Next, we develop a fine-grained taxonomy that captures a diverse range of unsafe behaviors observed in MCP scenarios. Building on this taxonomy, we develop benchmark and training data that support the evaluation and improvement of LLMs' capabilities in identifying safety risks within MCP interactions. Leveraging the proposed benchmark and training data, we conduct extensive experiments on state-of-the-art LLMs. The results highlight LLMs' vulnerabilities in MCP interactions and demonstrate that our approach substantially improves their safety performance.

cs.CL↗

arXiv2025

Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has recently emerged as a promising solution for enhancing the accuracy and credibility of Large Language Models (LLMs), particularly in Question & Answer tasks. This is achieved by incorporating proprietary and private data from integrated databases. However, private RAG systems face significant challenges due to the scarcity of private domain data and critical data privacy issues. These obstacles impede the deployment of private RAG systems, as developing privacy-preserving RAG systems requires a delicate balance between data security and data availability. To address these challenges, we regard federated learning (FL) as a highly promising technology for privacy-preserving RAG services. We propose a novel framework called Federated Retrieval-Augmented Generation (FedE4RAG). This framework facilitates collaborative training of client-side RAG retrieval models. The parameters of these models are aggregated and distributed on a central-server, ensuring data privacy without direct sharing of raw data. In FedE4RAG, knowledge distillation is employed for communication between the server and client models. This technique improves the generalization of local RAG retrievers during the federated learning process. Additionally, we apply homomorphic encryption within federated learning to safeguard model parameters and mitigate concerns related to data leakage. Extensive experiments conducted on the real-world dataset have validated the effectiveness of FedE4RAG. The results demonstrate that our proposed framework can markedly enhance the performance of private RAG systems while maintaining robust data privacy protection.

cs.CL↗

arXiv2025

A Deep Single Image Rectification Approach for Pan-Tilt-Zoom Cameras

Pan-Tilt-Zoom (PTZ) cameras with wide-angle lenses are widely used in surveillance but often require image rectification due to their inherent nonlinear distortions. Current deep learning approaches typically struggle to maintain fine-grained geometric details, resulting in inaccurate rectification. This paper presents a Forward Distortion and Backward Warping Network (FDBW-Net), a novel framework for wide-angle image rectification. It begins by using a forward distortion model to synthesize barrel-distorted images, reducing pixel redundancy and preventing blur. The network employs a pyramid context encoder with attention mechanisms to generate backward warping flows containing geometric details. Then, a multi-scale decoder is used to restore distorted features and output rectified images. FDBW-Net's performance is validated on diverse datasets: public benchmarks, AirSim-rendered PTZ camera imagery, and real-scene PTZ camera datasets. It demonstrates that FDBW-Net achieves SOTA performance in distortion rectification, boosting the adaptability of PTZ cameras for practical visual applications.

cs.CV↗

arXiv2025

PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance

Recent advancements in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. However, their reliability and trustworthiness are still in doubt, especially for concerns regarding individuals' data privacy. Great efforts have been made on privacy by building various evaluation benchmarks to study LLMs' privacy awareness and robustness from their generated outputs to their hidden representations. Unfortunately, most of these works adopt a narrow formulation of privacy and only investigate personally identifiable information (PII). In this paper, we follow the merit of the Contextual Integrity (CI) theory, which posits that privacy evaluation should not only cover the transmitted attributes but also encompass the whole relevant social context through private information flows. We present PrivaCI-Bench, a comprehensive contextual privacy evaluation benchmark targeted at legal compliance to cover well-annotated privacy and safety regulations, real court cases, privacy policies, and synthetic data built from the official toolkit to study LLMs' privacy and safety compliance. We evaluate the latest LLMs, including the recent reasoner models QwQ-32B and Deepseek R1. Our experimental results suggest that though LLMs can effectively capture key CI parameters inside a given context, they still require further advancements for privacy compliance.

cs.CL↗

arXiv2025

Top Ten Challenges Towards Agentic Neural Graph Databases

Graph databases (GDBs) like Neo4j and TigerGraph excel at handling interconnected data but lack advanced inference capabilities. Neural Graph Databases (NGDBs) address this by integrating Graph Neural Networks (GNNs) for predictive analysis and reasoning over incomplete or noisy data. However, NGDBs rely on predefined queries and lack autonomy and adaptability. This paper introduces Agentic Neural Graph Databases (Agentic NGDBs), which extend NGDBs with three core functionalities: autonomous query construction, neural query execution, and continuous learning. We identify ten key challenges in realizing Agentic NGDBs: semantic unit representation, abductive reasoning, scalable query execution, and integration with foundation models like large language models (LLMs). By addressing these challenges, Agentic NGDBs can enable intelligent, self-improving systems for modern data-driven applications, paving the way for adaptable and autonomous data management solutions.

cs.AI↗

arXiv2024

Node Level Graph Autoencoder: Unified Pretraining for Textual Graph Learning

Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate low-dimensional feature embeddings from textual graphs that can improve the performance of downstream tasks. A high-quality feature embedding should effectively capture both the structural and the textual information in a textual graph. However, most textual graph dataset benchmarks rely on word2vec techniques to generate feature embeddings, which inherently limits their capabilities. Recent works on textual graph representation learning can be categorized into two folds: supervised and unsupervised methods. Supervised methods finetune a language model on labeled nodes, which have limited capabilities when labeled data is scarce. Unsupervised methods, on the other hand, extract feature embeddings by developing complex training pipelines. To address these limitations, we propose a novel unified unsupervised learning autoencoder framework, named Node Level Graph AutoEncoder (NodeGAE). We employ language models as the backbone of the autoencoder, with pretraining on text reconstruction. Additionally, we add an auxiliary loss term to make the feature embeddings aware of the local graph structure. Our method maintains simplicity in the training process and demonstrates generalizability across diverse textual graphs and downstream tasks. We evaluate our method on two core graph representation learning downstream tasks: node classification and link prediction. Comprehensive experiments demonstrate that our approach substantially enhances the performance of diverse graph neural networks (GNNs) across multiple textual graph datasets.

cs.LG↗

arXiv2024

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased accessibility and unrestricted model training on massive data. A malicious adversary may publish poisoned data online and conduct backdoor attacks on the victim LLMs pre-trained on the poisoned data. Backdoored LLMs behave innocuously for normal queries and generate harmful responses when the backdoor trigger is activated. Despite significant efforts paid to LLMs' safety issues, LLMs are still struggling against backdoor attacks. As Anthropic recently revealed, existing safety training strategies, including supervised fine-tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), fail to revoke the backdoors once the LLM is backdoored during the pre-training stage. In this paper, we present Simulate and Eliminate (SANDE) to erase the undesired backdoored mappings for generative LLMs. We initially propose Overwrite Supervised Fine-tuning (OSFT) for effective backdoor removal when the trigger is known. Then, to handle scenarios where trigger patterns are unknown, we integrate OSFT into our two-stage framework, SANDE. Unlike other works that assume access to cleanly trained models, our safety-enhanced LLMs are able to revoke backdoors without any reference. Consequently, our safety-enhanced LLMs no longer produce targeted responses when the backdoor triggers are activated. We conduct comprehensive experiments to show that our proposed SANDE is effective against backdoor attacks while bringing minimal harm to LLMs' powerful capability.

cs.CR↗

arXiv2024

CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weather

Visible-infrared image pairs provide complementary information, enhancing the reliability and robustness of object detection applications in real-world scenarios. However, most existing methods face challenges in maintaining robustness under complex weather conditions, which limits their applicability. Meanwhile, the reliance on attention mechanisms in modality fusion introduces significant computational complexity and storage overhead, particularly when dealing with high-resolution images. To address these challenges, we propose the Cross-modality Fusion Mamba with Weather-removal (CFMW) to augment stability and cost-effectiveness under adverse weather conditions. Leveraging the proposed Perturbation-Adaptive Diffusion Model (PADM) and Cross-modality Fusion Mamba (CFM) modules, CFMW is able to reconstruct visual features affected by adverse weather, enriching the representation of image details. With efficient architecture design, CFMW is 3 times faster than Transformer-style fusion (e.g., CFT). To bridge the gap in relevant datasets, we construct a new Severe Weather Visible-Infrared (SWVI) dataset, encompassing diverse adverse weather scenarios such as rain, haze, and snow. The dataset contains 64,281 paired visible-infrared images, providing a valuable resource for future research. Extensive experiments on public datasets (i.e., M3FD and LLVIP) and the newly constructed SWVI dataset conclusively demonstrate that CFMW achieves state-of-the-art detection performance. Both the dataset and source code will be made publicly available at https://github.com/lhy-zjut/CFMW.

cs.CV↗