arXiv subjects

Ning Jia

Publications and source records attributed to Ning Jia.

At least 19 recordsLinked to original sources

arXiv2026

STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework

Incident response planning is critical for restoring compromised software systems after cyberattacks. Common practice relies on expert-driven playbooks that encode fixed response procedures, but these static workflows struggle to adapt to evolving incident states, changing recovery objectives, and execution feedback. Recent LLM-based planners and tool-using agents improve automation, yet they remain unstable in long-horizon response because they lack a unified basis for maintaining incident state, aligning actions with the current recovery stage, and reusing historical experience. We present STAIR, an end-to-end agentic planning framework for incident response. The framework maintains the current incident as Graph-as-State, uses a Stage Router to dispatch planning to stage-specialized agents, and retrieves historical experiences to guide action selection. An Execution Harness executes actions, returns feedback to update the incident state, and validates action effects for future experience reuse. Across 100 Docker-based cyber ranges, our framework achieves a normalized defense score of 0.94 and improves over the strongest baseline by 9.5%.

cs.CR↗

arXiv2026

RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges

Real-world cyberattacks often require sustained progress across multiple hosts and network segments, making multi-hop cyber ranges essential infrastructure for studying and improving LLM agents' ability to sustain complete attack chains. Prior work has scaled isolated vulnerability tasks and constructed multi-host scenarios from manually specified vulnerability semantics. However, they are still unable to automatically orchestrate the growing supply of vulnerability environments into end-to-end validated multi-hop ranges. To this end, we present RangeFactory, an automated cyber-range orchestration framework that constructs multi-hop cyber ranges at scale from isolated vulnerability environments. RangeFactory formulates range construction as dependency resolution: it extracts dependency information from agents' actual attacks against real vulnerabilities, resolves known dependencies through template-guided orchestration, and uses end-to-end attack execution to validate runtime dependencies that emerge after composition. Using RangeFactory, we construct RangeBench with 1,148 validated range instances spanning 287 distinct attack chains and evaluate frontier attack agents across attack depth, network scale, and task information. Among runs that compromise the entry vulnerability, 24.5-47.0% still fail to complete the remaining attack path, revealing a substantial sustained-compromise gap between establishing an initial foothold and completing a multi-hop attack. RangeFactory further produces a corpus of 5,541 outcome-annotated multi-hop attack trajectories, providing execution data for attack-process analysis and future agent training.

cs.CR↗

arXiv2026

Expert Behavior Prior Reinforcement Learning

Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations. However, most existing BPRL methods rely on static offline datasets, which often suffer from low data diversity and suboptimal trajectory quality. This reliance restricts the effectiveness of policy priors, hindering both policy exploitation and stability during online training. Consequently, agents are prone to inefficient exploration and unstable learning dynamics. To address these limitations, we deviate from existing offline pre-training methods and propose an Expert Behavior Prior (EBP) algorithm. Specifically, we introduce a Q-guided conditional variational autoencoder (Q-CVAE) that learns to generate expert policy priors directly from the online replay buffer. This enables the generation of high-value actions for guiding policy updates without relying on pre-collected expert trajectories. To further enhance policy exploitation, we propose an expert policy guidance (EPG) mechanism that selects expert actions from a generative support set, and we integrate a policy gradient correction (PGC) module to harmonize Q-guidance with expert supervision, promoting stable and consistent policy improvement. Extensive experiments conducted on robotic control (Gym, PyBullet) and industrial control (DMControl) benchmarks demonstrate that EBP significantly outperforms state-of-the-art online RL algorithms, achieving higher sample efficiency and more stable convergence.

cs.AI↗

arXiv2026

Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling

Human choice behavior, including route choice, exhibits systematic behavioral biases that deviate from the assumptions of full rationality. Cumulative prospect theory (CPT) has been widely recognized as an effective framework for characterizing such behavioral patterns. However, its large-scale application, particularly in simulation and agent-based modeling, critically depends on specifying individual-level CPT parameters, which remain a major bottleneck. Conventional approaches typically rely on surveys and controlled experiments to calibrate CPT parameters, yet these methods are difficult to generalize and often fail to capture the full diversity of human decision-making. To address this challenge, this paper investigates whether large language models (LLMs) can reproduce human behavioral biases in choice-making without explicit specification of prospect-theoretic parameters. Using route choice as a representative scenario, we design a behavioral evaluation framework and systematically compare LLM-generated decisions with established human behavioral patterns predicted by CPT. Experimental results demonstrate that LLMs are capable of reproducing non-rational human choice biases and can exhibit decision behaviors consistent with prospect-theoretic effects under uncertainty. These findings suggest that generative AI models may provide a scalable alternative for modeling human decision processes and offer a promising foundation for next-generation large-scale agent-based simulation and AI-driven behavioral research.

cs.AI↗

arXiv2026

EnerInfer: Energy-Aware On-Device LLM Inference

On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck. Existing systems primarily optimize for decoding speed, implicitly assuming that faster execution is always preferable. We show instead that on-device LLM inference often has exploitable configuration slack: modestly lowering NPU and memory frequencies preserves quality of experience (QoE) while substantially improving energy efficiency and reducing heat. Realizing this opportunity in production is challenging. The most energy-efficient NPU/DDR setting varies with the model, inference engine, platform, and runtime conditions, with no stable ranking across configurations. Commercial devices further lack component-level power sensing, and shell temperature evolves with request arrivals, response lengths, and thermal history. To address these challenges, we propose EnerInfer, the first on-device LLM inference framework that jointly manages energy efficiency, throughput, and thermal comfort for LLM workloads. EnerInfer replaces per-model profiling and sensor-heavy control with disaggregated, model-structure-aware prediction and ranking-driven online feedback. It predicts throughput and power for unseen LLMs across NPU/DDR frequency settings, selects QoE-satisfying efficient configurations under runtime interference, and uses lightweight limited-horizon thermal prediction to dynamically switch between energy-optimized and thermally constrained inference. Evaluations on real-world LLMs show that EnerInfer improves energy efficiency by up to 65%, 12%, and 24% on phones, a laptop, and a development board, respectively, without QoE violation.

cs.SE↗

arXiv2026

Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action

Existing value-based online reinforcement learning (RL) algorithms suffer from slow policy exploitation due to ineffective exploration and delayed policy updates. To address these challenges, we propose an algorithm called Instant Retrospect Action (IRA). Specifically, we propose Q-Representation Discrepancy Evolution (RDE) to facilitate Q-network representation learning, enabling discriminative representations for neighboring state-action pairs. In addition, we adopt an explicit method to policy constraints by enabling Greedy Action Guidance (GAG). This is achieved through backtracking historical actions, which effectively enhances the policy update process. Our proposed method relies on providing the learning algorithm with accurate $k$-nearest-neighbor action value estimates and learning to design a fast-adaptable policy through policy constraints. We further propose the Instant Policy Update (IPU) mechanism, which enhances policy exploitation by systematically increasing the frequency of policy updates. We further discover that the early-stage training conservatism of the IRA method can alleviate the overestimation bias problem in value-based RL. Experimental results show that IRA can significantly improve the learning efficiency and final performance of online RL algorithms on eight MuJoCo continuous control tasks.The code is available at https://github.com/2706853499/IRA.

cs.LG↗

arXiv2025

Mitigating the phase-mismatch effect in non-resonant four-wave mixing enabled by optimal control

Phase-mismatch in nonlinear optical processes can severely limit the propagation and conversion efficiency of light fields. Here, we present an efficient optimal-control strategy to mitigate the detrimental effects of phase-mismatch in an electromagnetically induced transparency medium via non-resonant four-wave mixing (FWM). By applying a set of fixed, linearly modulated coupling fields that induce a dark eigenmode, we globally optimize a single coupling detuning to minimize the spontaneous emission loss, the primary factor limiting conversion efficiency. Our approach outperforms existing FWM schemes by providing strong robustness against large phase-mismatch variations while maintaining efficient probe-to-signal conversion. These results offer a promising route toward more efficient nonlinear frequency conversion, alleviating the stringent requirement for phase matching in experiments.

quant-ph↗

arXiv2024

Interference-free Operating System: A 6 Years' Experience in Mitigating Cross-Core Interference in Linux

Real-time operating systems employ spatial and temporal isolation to guarantee predictability and schedulability of real-time systems on multi-core processors. Any unbounded and uncontrolled cross-core performance interference poses a significant threat to system time safety. However, the current Linux kernel has a number of interference issues and represents a primary source of interference. Unfortunately, existing research does not systematically and deeply explore the cross-core performance interference issue within the OS itself. This paper presents our industry practice for mitigating cross-core performance interference in Linux over the past 6 years. We have fixed dozens of interference issues in different Linux subsystems. Compared to the version without our improvements, our enhancements reduce the worst-case jitter by a factor of 8.7, resulting in a maximum 11.5x improvement over system schedulability. For the worst-case latency in the Core Flight System and the Robot Operating System 2, we achieve a 1.6x and 1.64x reduction over RT-Linux. Based on our development experience, we summarize the lessons we learned and offer our suggestions to system developers for systematically eliminating cross-core interference from the following aspects: task management, resource management, and concurrency management. Most of our modifications have been merged into Linux upstream and released in commercial distributions.

cs.OS↗

arXiv2024

Machine Learning Co-pilot for Screening of Organic Molecular Additives for Perovskite Solar Cells

Machine learning (ML) has been extensively employed in planar perovskite photovoltaics to screen effective organic molecular additives, while encountering predictive biases for novel materials due to small datasets and reliance on predefined descriptors. Present work thus proposes an effective approach, Co-Pilot for Perovskite Additive Screener (Co-PAS), an ML-driven framework designed to accelerate additive screening for perovskite solar cells (PSCs). Co-PAS overcomes predictive biases by integrating the Molecular Scaffold Classifier (MSC) for scaffold-based pre-screening and utilizing Junction Tree Variational Autoencoder (JTVAE) latent vectors to enhance molecular structure representation, thereby enhancing the accuracy of power conversion efficiency (PCE) predictions. Leveraging Co-PAS, we integrate domain knowledge to screen an extensive dataset of 250,000 molecules from PubChem, prioritizing candidates based on predicted PCE values and key molecular properties such as donor number, dipole moment, and hydrogen bond acceptor count. This workflow leads to the identification of several promising passivating molecules, including the novel Boc-L-threonine N-hydroxysuccinimide ester (BTN), which, to our knowledge, has not been explored as an additive in PSCs and achieves a device PCE of 25.20%. Our results underscore the potential of Co-PAS in advancing additive discovery for high-performance PSCs.

cs.LG↗

arXiv2024

UltraSeP: Sequence-aware Pre-training for Echocardiography Probe Movement Guidance

Echocardiography is an essential medical technique for diagnosing cardiovascular diseases, but its high operational complexity has led to a shortage of trained professionals. To address this issue, we introduce a novel probe movement guidance algorithm that has the potential to be applied in guiding robotic systems or novices with probe pose adjustment for high-quality standard plane image acquisition.Cardiac ultrasound faces two major challenges: (1) the inherently complex structure of the heart, and (2) significant individual variations. Previous works have only learned the population-averaged structure of the heart rather than personalized cardiac structures, leading to a performance bottleneck. Clinically, we observe that sonographers dynamically adjust their interpretation of a patient's cardiac anatomy based on prior scanning sequences, consequently refining their scanning strategies. Inspired by this, we propose a novel sequence-aware self-supervised pre-training method. Specifically, our approach learns personalized three-dimensional cardiac structural features by predicting the masked-out image features and probe movement actions in a scanning sequence. We hypothesize that if the model can predict the missing content it has acquired a good understanding of personalized cardiac structure. Extensive experiments on a large-scale expert scanning dataset with 1.67 million samples demonstrate that our proposed sequence-aware paradigm can effectively reduce probe guidance errors compared to other advanced baseline methods.

cs.CV↗

arXiv2024

RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion

Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and fuses these features through attention mechanisms, demonstrating compelling efficacy in RGB-Normal road scene parsing. However, its performance significantly deteriorates when handling other types/sources of data or performing more universal, all-category scene parsing tasks. To overcome these limitations, this study introduces RoadFormer+, an efficient, robust, and adaptable model capable of effectively fusing RGB-X data, where ``X'', represents additional types/modalities of data such as depth, thermal, surface normal, and polarization. Specifically, we propose a novel hybrid feature decoupling encoder to extract heterogeneous features and decouple them into global and local components. These decoupled features are then fused through a dual-branch multi-scale heterogeneous feature fusion block, which employs parallel Transformer attentions and convolutional neural network modules to merge multi-scale features across different scales and receptive fields. The fused features are subsequently fed into a decoder to generate the final semantic predictions. Notably, our proposed RoadFormer+ ranks first on the KITTI Road benchmark and achieves state-of-the-art performance in mean intersection over union on the Cityscapes, MFNet, FMB, and ZJU datasets. Moreover, it reduces the number of learnable parameters by 65\% compared to RoadFormer. Our source code will be publicly available at mias.group/RoadFormerPlus.

cs.CV↗

arXiv2024

Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train

The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images. Successful echocardiography requires a thorough understanding of the structures on the two-dimensional plane and the spatial relationships between planes in three-dimensional space. In this paper, we innovatively propose a large-scale self-supervised pre-training method to acquire a cardiac structure-aware world model. The core innovation lies in constructing a self-supervised task that requires structural inference by predicting masked structures on a 2D plane and imagining another plane based on pose transformation in 3D space. To support large-scale pre-training, we collected over 1.36 million echocardiograms from ten standard views, along with their 3D spatial poses. In the downstream probe guidance task, we demonstrate that our pre-trained model consistently reduces guidance errors across the ten most common standard views on the test set with 0.29 million samples from 74 routine clinical scans, indicating that structure-aware pre-training benefits the scanning.

cs.CV↗

arXiv2024

Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model

Echocardiography is the only technique capable of real-time imaging of the heart and is vital for diagnosing the majority of cardiac diseases. However, there is a severe shortage of experienced cardiac sonographers, due to the heart's complex structure and significant operational challenges. To mitigate this situation, we present a Cardiac Copilot system capable of providing real-time probe movement guidance to assist less experienced sonographers in conducting freehand echocardiography. This system can enable non-experts, especially in primary departments and medically underserved areas, to perform cardiac ultrasound examinations, potentially improving global healthcare delivery. The core innovation lies in proposing a data-driven world model, named Cardiac Dreamer, for representing cardiac spatial structures. This world model can provide structure features of any cardiac planes around the current probe position in the latent space, serving as an precise navigation map for autonomous plane localization. We train our model with real-world ultrasound data and corresponding probe motion from 110 routine clinical scans with 151K sample pairs by three certified sonographers. Evaluations on three standard planes with 37K sample pairs demonstrate that the world model can reduce navigation errors by up to 33\% and exhibit more stable performance.

eess.IV↗

arXiv2024

Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model

Deep learning-based image stitching pipelines are typically divided into three cascading stages: registration, fusion, and rectangling. Each stage requires its own network training and is tightly coupled to the others, leading to error propagation and posing significant challenges to parameter tuning and system stability. This paper proposes the Simple and Robust Stitcher (SRStitcher), which revolutionizes the image stitching pipeline by simplifying the fusion and rectangling stages into a unified inpainting model, requiring no model training or fine-tuning. We reformulate the problem definitions of the fusion and rectangling stages and demonstrate that they can be effectively integrated into an inpainting task. Furthermore, we design the weighted masks to guide the reverse process in a pre-trained largescale diffusion model, implementing this integrated inpainting task in a single inference. Through extensive experimentation, we verify the interpretability and generalization capabilities of this unified model, demonstrating that SRStitcher outperforms state-of-the-art methods in both performance and stability. Code: https://github.com/yayoyo66/SRStitcher

cs.CV↗

arXiv2023

Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning

Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the incorporation of online fine-tuning can intensify the well-known distributional shift problem. Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning. They typically advocate a single balance between policy improvement and constraints across diverse data collections. This one-size-fits-all manner may not optimally leverage each collected sample due to the significant variation in data quality across different states. To this end, we introduce Family Offline-to-Online RL (FamO2O), a simple yet effective framework that empowers existing algorithms to determine state-adaptive improvement-constraint balances. FamO2O utilizes a universal model to train a family of policies with different improvement/constraint intensities, and a balance model to select a suitable policy for each state. Theoretically, we prove that state-adaptive balances are necessary for achieving a higher policy performance upper bound. Empirically, extensive experiments show that FamO2O offers a statistically significant improvement over various existing methods, achieving state-of-the-art performance on the D4RL benchmark. Codes are available at https://github.com/LeapLabTHU/FamO2O.

cs.LG↗

arXiv2023

Investigating and modeling day-to-day route choices based on laboratory experiments. Part II: A route-dependent attraction-based stochastic process model

To explain day-to-day (DTD) route-choice behaviors and traffic dynamics observed in a series of lab experiments, Part I of this research proposed a discrete choice-based analytical dynamic model (Qi et al., 2023). Although the deterministic model could well reproduce the experimental observations, it converges to a stable equilibrium of route flow while the observed DTD evolution is apparently with random oscillations. To overcome the limitation, the paper proposes a route-dependent attraction-based stochastic process (RDAB-SP) model based on the same behavioral assumptions in Part I of this research. Through careful comparison between the model-based estimation and experimental observations, it is demonstrated that the proposed RDAB-SP model can accurately reproduce the random oscillations both in terms of flow switching and route flow evolution. To the best of our knowledge, this is the first attempt to explain and model experimental observations by using stochastic process DTD models, and it is interesting to find that the seemingly unanticipated phenomena (i.e., random route switching behavior) is actually dominated by simple rules, i.e., independent and probability-based route-choice behavior. Finally, an approximated model is developed to help simulate the stochastic process and evaluate the equilibrium distribution in a simple and efficient manner, making the proposed model a useful and practical tool in transportation policy design.

physics.soc-ph↗

arXiv2023

Investigating day-to-day route choices based on multi-scenario laboratory experiments. Part I: Route-dependent attraction and its modeling

In the area of urban transportation networks, a growing number of day-to-day (DTD) traffic dynamic theories have been proposed to describe the network flow evolution, and an increasing amount of laboratory experiments have been conducted to observe travelers' behavior regularities. However, the "communication" between theorists and experimentalists has not been made well. This paper devotes to 1) detecting unanticipated behavior regularities by conducting a series of laboratory experiments, and 2) improving existing DTD dynamics theories by embedding the observed behavior regularities into a route choice model. First, 312 subjects participated in one of the eight decision-making scenarios and make route choices repeatedly in congestible parallel-route networks. Second, three route-switching behavior patterns that cannot be fully explained by the classic route-choice models are observed. Third, to enrich the explanation power of a discrete route-choice model, behavioral assumptions of route-dependent attractions, i.e., route-dependent inertia and preference, are introduced. An analytical DTD dynamic model is accordingly proposed and proven to steadily converge to a unique equilibrium state. Finally, the proposed DTD model could satisfactorily reproduce the observations in various datasets. The research results can help transportation science theorists to make the best use of laboratory experimentation and to build network equilibrium or DTD dynamic models with both real behavioral basis and neat mathematical properties.

physics.soc-ph↗

arXiv2022

Assessing the dynamic vulnerability of an urban rail transit system and a case study of Beijing, China

Urban rail transit is the backbone of urban transportation, and thus it is significant to understand its vulnerability, i.e., whether the system can still maintain normal operations when facing operational disturbances with different magnitudes. To this end, this paper proposes a network vulnerability assessment method with the joint consideration of static network topology and dynamic travel demand. The method includes an accessibility-based identification of station importance with time-varying passenger demand and a new dynamic vulnerability evaluation index. An empirical analysis is carried out by taking the rail transit system of Beijing, China as an example. Results show that the distribution of high-importance stations varies with the time of day, affected by both static topology and hourly-changing passenger flow. Under the disturbance of operation delay, the impact of high-importance stations on the network vulnerability changes with the increase of delayed travel demand. It is also found that some stations that serve as bridges (i.e., reasonable paths link the origin station and destination) and are visited by large passenger flow have the greatest impact on network vulnerability. Network performance degradation is obviously segmented and stratified in the case of interval continuous failure. The disruption between different lines is the main reason for system performance degradation, and some important stations within the line will act as catalysts to accelerate the performance degradation. This method provides a reference for measuring dynamic passenger flow-related network vulnerability and supplies the field with a new vulnerability evaluation index.

math.DS↗