arXiv subjects

Teng Li

Publications and source records attributed to Teng Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Slot: Provenance-Driven APT Detection through Graph Reinforcement Learning

Advanced Persistent Threats (APTs) represent sophisticated cyberattacks characterized by their ability to remain undetected within the victim system for extended periods, aiming to exfiltrate sensitive data or disrupt operations. Existing detection approaches often struggle to effectively identify these complex threats, construct the attack chain for defense facilitation, or resist adversarial attacks. To overcome these challenges, we propose Slot, an advanced APT detection approach based on provenance graphs and graph reinforcement learning. Slot excels in uncovering multi-level hidden relationships, such as causal, contextual, and indirect connections, among system behaviors through provenance graph mining. By pioneering the integration of graph reinforcement learning, Slot dynamically adapts to new user activities and evolving attack strategies, enhancing its resilience against adversarial attacks. Additionally, Slot automatically constructs the attack chain according to detected attacks with clustering algorithms, providing precise identification of attack paths and facilitating the development of defense strategies. Evaluations with real-world datasets demonstrate Slot's outstanding accuracy, efficiency, adaptability, and robustness in APT detection, with most metrics surpassing state-of-the-art methods. Additionally, case studies conducted to assess Slot's effectiveness in supporting APT defense further establish it as a practical and reliable tool for cybersecurity protection.

cs.CR↗

arXiv2025

RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control

Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges, as users often struggle to provide precise camera parameters when working with arbitrary real-world images without knowledge of their depth nor scene scale. To address these real-world application issues, we propose RealCam-I2V, a novel diffusion-based video generation framework that integrates monocular metric depth estimation to establish 3D scene reconstruction in a preprocessing step. During training, the reconstructed 3D scene enables scaling camera parameters from relative to metric scales, ensuring compatibility and scale consistency across diverse real-world images. In inference, RealCam-I2V offers an intuitive interface where users can precisely draw camera trajectories by dragging within the 3D scene. To further enhance precise camera control and scene consistency, we propose scene-constrained noise shaping, which shapes high-level noise and also allows the framework to maintain dynamic and coherent video generation in lower noise stages. RealCam-I2V achieves significant improvements in controllability and video quality on the RealEstate10K and out-of-domain images. We further enables applications like camera-controlled looping video generation and generative frame interpolation. Project page: https://zgctroy.github.io/RealCam-I2V.

cs.CV↗

arXiv2025

Noise Filtering Algorithm Based on Graph Neural Network for STCF Drift Chamber

The super $τ$-charm facility (STCF) is a next-generation electron-positron collider with high luminosity proposed in China. The higher luminosity leads to increased background level, posing significant challenges for track reconstruction of charged particles. Particularly in the low transverse momentum region, the current track reconstruction algorithm is notably affected by background, resulting in suboptimal reconstruction efficiency and a high fake rate. To address this challenge, we propose a Graph Neural Network (GNN)-based noise filtering algorithm (GNF Algorithm) as a preprocessing step for the track reconstruction. The GNF Algorithm introduces a novel method to convert detector data into graphs and applies a tiered threshold strategy to map GNN-based edge classification results onto signal-noise separation. The study based on Monte Carlo (MC) data shows that with the implementation of the GNF Algorithm, the reconstruction efficiency with the standard background is comparable to the case without background, while the fake rate is significantly reduced. Thus, GNF Algorithm provides essential support for the STCF tracking software.

hep-ex↗

arXiv2025

Chain-of-Memory: Enhancing GUI Agents for Cross-Application Navigation

Multimodal large language models (MLLMs) are attracting growing attention in the development of Graphical User Interface (GUI) agents. Existing approaches often rely on historical screenshots or actions to implicitly represent the task state. This reliance poses challenges for GUI agents in accurately understanding task states and underscores the absence of effective mechanisms to store critical information in complex and lengthy cross-app tasks. To address these challenges, we propose Chain-of-Memory (CoM), a novel approach for explicitly modeling short-term and long-term memory in GUI agents. CoM achieves this by capturing action descriptions, integrating task-relevant screen information, and maintaining a dedicated memory module to store and manage this information. By leveraging explicit memory representations, CoM enables GUI agents to better understand task states and retain critical historical information persistently. To equip GUI agents with memory management capabilities and evaluate the effectiveness of CoM, we developed the GUI Odyssey-CoM, a dataset comprising 111k screen-action pairs annotated with Chain-of-Memory. Experimental results demonstrate that CoM significantly improves GUI agents' performance in cross-application tasks. Additionally, GUI Odyssey-CoM enables 7B models to achieve memory management capabilities comparable to 72B models. The dataset and code will be open-sourced.

cs.AI↗

arXiv2025

UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation

Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work, we start by analyzing the modality alignment behaviors of task-specific expert models for understanding and generation, as well as current unified models. Our analysis reveals a crucial observation: understanding tasks benefit from a progressively increasing modality alignment across network depth, which helps build up semantic information for better comprehension; In contrast, generation tasks follow a different trend: modality alignment increases in the early layers but decreases in the deep layers to recover spatial details. These divergent alignment patterns create a fundamental conflict in fully shared Transformer backbones, where a uniform representational flow often leads to performance compromises across two tasks. Motivated by this finding, we introduce UniFork, a novel Y-shaped architecture that shares the shallow layers for cross-task representation learning, while employing task-specific branches in deeper layers to avoid task interference. This design effectively balances shared learning and task specialization. Through extensive ablation experiments, we demonstrate that Unifork consistently outperforms conventional fully shared Transformer architectures, and achieves performance on par with or better than task-specific models.

cs.CV↗

arXiv2025

Neutrino type identification for atmospheric neutrinos in a large homogeneous liquid scintillation detector

Atmospheric neutrino oscillations are important to the study of neutrino properties, including the neutrino mass ordering problem. A good capability to identify neutrinos' flavor and neutrinos against antineutrinos is crucial in such measurements. In this paper, we present a machine-learning-based approach for identifying atmospheric neutrino events in a large homogeneous liquid scintillator detector. This method identifies features of PMT waveforms that reflect event topologies and uses them as input to machine learning models. In addition, neutron-capture information is utilized to achieve neutrino versus antineutrino discrimination. Preliminary performances based on Monte Carlo simulations are presented, which demonstrate such a detector's potential in future measurements of atmospheric neutrinos such as the one planned for the JUNO experiment.

hep-ex↗

arXiv2025

RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements

Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K. While these datasets enable basic viewpoint control, they fail to capture dynamic scene interactions and lack metric-scale geometric consistency-critical for synthesizing realistic object motions and precise camera trajectories in complex environments. To bridge this gap, we introduce the first fully open-source, high-resolution dynamic-scene dataset with metric-scale camera annotations in https://github.com/ZGCTroy/RealCam-Vid.

cs.CV↗

arXiv2025

Multi-threaded Simulation Software for the JUNO Experiment

The Jiangmen Underground Neutrino Observatory (JUNO) is a multi-purpose experiment under construction in southern China. JUNO aims to determine the neutrino mass ordering and precisely measure the neutrino oscillation parameters by detecting reactor neutrinos from nuclear power plants. In addition to reactor neutrinos, JUNO can study atmospheric neutrinos, solar neutrinos, geo-neutrinos, supernova burst neutrinos, the Diffuse Supernova Neutrino Background (DSNB), and nucleon decay, covering an energy range from keV to TeV. JUNO consists of a 20 kton liquid scintillator detector, equipped with 17,612 20-inch PMTs and 25,600 3-inch PMTs, achieving a 3\% energy resolution (at 1~MeV). Precise simulation plays a crucial role in the experiment. Developed using the SNiPER framework and Geant4 toolkit, the JUNO simulation software is a key component of the JUNO offline software (JUNOSW). The large detector size and the broad energy range of interest pose challenges for detector simulation in terms of CPU time and memory consumption. As the computing nodes shift to include multiple integrated CPU cores, traditional single-threaded computing model can lead to large memory footprints and inefficient use of system resources. Multi-threading on many-core architectures can significantly improve resource utilization. This paper introduces the design and implementation of multi-threaded simulation software for the JUNO experiment.

physics.ins-det↗

arXiv2025

Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios

Ensuring the safety of autonomous vehicles necessitates comprehensive simulation of multi-sensor data, encompassing inputs from both cameras and LiDAR sensors, across various dynamic driving scenarios. Neural rendering techniques, which utilize collected raw sensor data to simulate these dynamic environments, have emerged as a leading methodology. While NeRF-based approaches can uniformly represent scenes for rendering data from both camera and LiDAR, they are hindered by slow rendering speeds due to dense sampling. Conversely, Gaussian Splatting-based methods employ Gaussian primitives for scene representation and achieve rapid rendering through rasterization. However, these rasterization-based techniques struggle to accurately model non-linear optical sensors. This limitation restricts their applicability to sensors beyond pinhole cameras. To address these challenges and enable unified representation of dynamic driving scenarios using Gaussian primitives, this study proposes a novel hybrid approach. Our method utilizes rasterization for rendering image data while employing Gaussian ray-tracing for LiDAR data rendering. Experimental results on public datasets demonstrate that our approach outperforms current state-of-the-art methods. This work presents a unified and efficient solution for realistic simulation of camera and LiDAR data in autonomous driving scenarios using Gaussian primitives, offering significant advancements in both rendering quality and computational efficiency.

cs.RO↗

arXiv2025

Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion Models

The rapid advancement of pretrained text-driven diffusion models has significantly enriched applications in image generation and editing. However, as the demand for personalized content editing increases, new challenges emerge especially when dealing with arbitrary objects and complex scenes. Existing methods usually mistakes mask as the object shape prior, which struggle to achieve a seamless integration result. The mostly used inversion noise initialization also hinders the identity consistency towards the target object. To address these challenges, we propose a novel training-free framework that formulates personalized content editing as the optimization of edited images in the latent space, using diffusion models as the energy function guidance conditioned by reference text-image pairs. A coarse-to-fine strategy is proposed that employs text energy guidance at the early stage to achieve a natural transition toward the target class and uses point-to-point feature-level image energy guidance to perform fine-grained appearance alignment with the target object. Additionally, we introduce the latent space content composition to enhance overall identity consistency with the target. Extensive experiments demonstrate that our method excels in object replacement even with a large domain gap, highlighting its potential for high-quality, personalized image editing.

cs.CV↗

arXiv2025

Parallelized Event Data Management System Based on MT-SNiPER Framework and PODIO

Software framework serves as a skeleton for the offline data processing software for many high energy physics (HEP) experiments. The event data management, including the event data model (EDM), transient event store and data input/output, implements the core functionalities of the framework, and has a great impact on the performance of the entire offline software. Future HEP experiments are generating increasingly large amounts of data, bringing challenges to offline data processing. To address this issue, a common event data management system that supports efficient parallelized data processing applications has been developed based on SNiPER (Software for Non-collider Physics ExpeRiments) common software framework as well as PODIO, a common EDM toolkit for future HEP experiments. In this paper, the implementation of a parallelized event data management (PEDM) system is introduced, including the integration with MT-SNiPER and PODIO, as well as the implementation of GlobalStore to support multi-threaded event processing. Finally, the application and performance evaluation of the data management system in OSCAR (offline software of Super Tau Charm Facility) is presented.

hep-ex↗

arXiv2025

Enhancing The Open Network: Definition and Automated Detection of Smart Contract Defects

The Open Network (TON), designed to support Telegram's extensive user base of hundreds of millions, has garnered considerable attention since its launch in 2022. FunC is the most popular programming language for writing smart contracts on TON. It is distinguished by a unique syntax compared to other smart contract languages. Despite growing interest, research on the practical defects of TON smart contracts is still in its early stages. In this paper, we summarize eight smart contract defects identified from TON's official blogs and audit reports, each with detailed definitions and code examples. Furthermore, we propose a static analysis framework called TONScanner to facilitate the detection of these defects. Specifically, TONScanner reuses FunC compiler's frontend code to transform the FunC source code into FunC intermediate representation (IR) in the form of a directed acyclic graph (DAG). Based on this IR, TONScanner constructs a control flow graph (CFG), then transforms it into a static single assignment (SSA) form to simplify further analysis. TONScanner also integrates Data Dependency, Call Graph, Taint Analysis, and Cell Construct, which are specifically tailored for TON blockchain's unique data structures. These components finally facilitate the identification of the eight defects. We evaluate the effectiveness of TONScanner by applying it to 1,640 smart contracts and find a total of 14,995 defects. Through random sampling and manual labeling, we find that TONScanner achieves an overall precision of 97.49%. The results reveal that current TON contracts contain numerous defects, indicating that developers are prone to making errors. TONScanner has proven its ability to accurately identify these defects, thereby aiding in their correction.

cs.SE↗

arXiv2025

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks

Transferable adversarial examples highlight the vulnerability of deep neural networks (DNNs) to imperceptible perturbations across various real-world applications. While there have been notable advancements in untargeted transferable attacks, targeted transferable attacks remain a significant challenge. In this work, we focus on generative approaches for targeted transferable attacks. Current generative attacks focus on reducing overfitting to surrogate models and the source data domain, but they often overlook the importance of enhancing transferability through additional semantics. To address this issue, we introduce a novel plug-and-play module into the general generator architecture to enhance adversarial transferability. Specifically, we propose a \emph{Semantic Injection Module} (SIM) that utilizes the semantics contained in an additional guiding image to improve transferability. The guiding image provides a simple yet effective method to incorporate target semantics from the target class to create targeted and highly transferable attacks. Additionally, we propose new loss formulations that can integrate the semantic injection module more effectively for both targeted and untargeted attacks. We conduct comprehensive experiments under both targeted and untargeted attack settings to demonstrate the efficacy of our proposed approach.

cs.CV↗

arXiv2024

DynaShard: Secure and Adaptive Blockchain Sharding Protocol with Hybrid Consensus and Dynamic Shard Management

Blockchain sharding has emerged as a promising solution to the scalability challenges in traditional blockchain systems by partitioning the network into smaller, manageable subsets called shards. Despite its potential, existing sharding solutions face significant limitations in handling dynamic workloads, ensuring secure cross-shard transactions, and maintaining system integrity. To address these gaps, we propose DynaShard, a dynamic and secure cross-shard transaction processing mechanism designed to enhance blockchain sharding efficiency and security. DynaShard combines adaptive shard management, a hybrid consensus approach, plus an efficient state synchronization and dispute resolution protocol. Our performance evaluation, conducted using a robust experimental setup with real-world network conditions and transaction workloads, demonstrates DynaShard's superior throughput, reduced latency, and improved shard utilization compared to the FTBS method. Specifically, DynaShard achieves up to a 42.6% reduction in latency and a 78.77% improvement in shard utilization under high transaction volumes and varying cross-shard transaction ratios. These results highlight DynaShard's ability to outperform state-of-the-art sharding methods, ensuring scalable and resilient blockchain systems. We believe that DynaShard's innovative approach will significantly impact future developments in blockchain technology, paving the way for more efficient and secure distributed systems.

cs.DC↗

arXiv2024

HeteroSample: Meta-path Guided Sampling for Heterogeneous Graph Representation Learning

The rapid expansion of Internet of Things (IoT) has resulted in vast, heterogeneous graphs that capture complex interactions among devices, sensors, and systems. Efficient analysis of these graphs is critical for deriving insights in IoT scenarios such as smart cities, industrial IoT, and intelligent transportation systems. However, the scale and diversity of IoT-generated data present significant challenges, and existing methods often struggle with preserving the structural integrity and semantic richness of these complex graphs. Many current approaches fail to maintain the balance between computational efficiency and the quality of the insights generated, leading to potential loss of critical information necessary for accurate decision-making in IoT applications. We introduce HeteroSample, a novel sampling method designed to address these challenges by preserving the structural integrity, node and edge type distributions, and semantic patterns of IoT-related graphs. HeteroSample works by incorporating the novel top-leader selection, balanced neighborhood expansion, and meta-path guided sampling strategies. The key idea is to leverage the inherent heterogeneous structure and semantic relationships encoded by meta-paths to guide the sampling process. This approach ensures that the resulting subgraphs are representative of the original data while significantly reducing computational overhead. Extensive experiments demonstrate that HeteroSample outperforms state-of-the-art methods, achieving up to 15% higher F1 scores in tasks such as link prediction and node classification, while reducing runtime by 20%.These advantages make HeteroSample a transformative tool for scalable and accurate IoT applications, enabling more effective and efficient analysis of complex IoT systems, ultimately driving advancements in smart cities, industrial IoT, and beyond.

cs.LG↗

arXiv2024

Priority-Aware Model-Distributed Inference at Edge Networks

Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire Machine Learning (ML) model but processes only a subset of the data. However, feeding the data to workers results in high communication costs, especially when the data is large. An emerging paradigm is model-distributed inference (MDI), where each worker carries only a subset of ML layers. In MDI, a source device that has data processes a few layers of ML model and sends the output to a neighboring device, i.e., offloads the rest of the layers. This process ends when all layers are processed in a distributed manner. In this paper, we investigate the design and development of MDI when multiple data sources co-exist. We consider that each data source has a different importance and, hence, a priority. We formulate and solve a priority-aware model allocation optimization problem. Based on the structure of the optimal solution, we design a practical Priority-Aware Model- Distributed Inference (PA-MDI) algorithm that determines model allocation and distribution over devices by taking into account the priorities of different sources. Experiments were conducted on a real-life testbed of NVIDIA Jetson Xavier and Nano edge devices as well as in the Colosseum testbed with ResNet-50, ResNet- 56, and GPT-2 models. The experimental results show that PA-MDI performs priority-aware model allocation successfully while reducing the inference time as compared to baselines.

cs.DC↗

arXiv2024

CamI2V: Camera-Controlled Image-to-Video Diffusion Model

Recent advancements have integrated camera pose as a user-friendly and physics-informed condition in video diffusion models, enabling precise camera control. In this paper, we identify one of the key challenges as effectively modeling noisy cross-frame interactions to enhance geometry consistency and camera controllability. We innovatively associate the quality of a condition with its ability to reduce uncertainty and interpret noisy cross-frame features as a form of noisy condition. Recognizing that noisy conditions provide deterministic information while also introducing randomness and potential misguidance due to added noise, we propose applying epipolar attention to only aggregate features along corresponding epipolar lines, thereby accessing an optimal amount of noisy conditions. Additionally, we address scenarios where epipolar lines disappear, commonly caused by rapid camera movements, dynamic objects, or occlusions, ensuring robust performance in diverse environments. Furthermore, we develop a more robust and reproducible evaluation pipeline to address the inaccuracies and instabilities of existing camera control metrics. Our method achieves a 25.64% improvement in camera controllability on the RealEstate10K dataset without compromising dynamics or generation quality and demonstrates strong generalization to out-of-domain images. Training and inference require only 24GB and 12GB of memory, respectively, for 16-frame sequences at 256x256 resolution. We will release all checkpoints, along with training and evaluation code. Dynamic videos are best viewed at https://zgctroy.github.io/CamI2V.

cs.CV↗

arXiv2024

A Teleoperation System with Impedance Control and Disturbance Observer for Robot-Assisted Rehabilitation

Physical movement therapy is a crucial method of rehabilitation aimed at reinstating mobility among patients facing motor dysfunction due to neurological conditions or accidents. Such therapy is usually featured as patient-specific, repetitive, and labor-intensive. The conventional method, where therapists collaborate with patients to conduct repetitive physical training, proves strenuous due to these characteristics. The concept of robot-assisted rehabilitation, assisting therapists with robotic systems, has gained substantial popularity. However, building such systems presents challenges, such as diverse task demands, uncertainties in dynamic models, and safety issues. To address these concerns, in this paper, we proposed a bilateral teleoperation system for rehabilitation. The control scheme of the system is designed as an integrated framework of impedance control and disturbance observer where the former can ensure compliant human-robot interaction without the need for force sensors while the latter can compensate for dynamic uncertainties when only a roughly identified dynamic model is available. Furthermore, the scheme allows free switching between tracking tasks and physical human-robot interaction (pHRI). The presented system can execute a wide array of pre-defined trajectories with varying patterns, adaptable to diverse needs. Moreover, the system can capture therapists' demonstrations, replaying them as many times as necessary. The effectiveness of the teleoperation system is experimentally evaluated and demonstrated.

cs.RO↗