arXiv subjects

Long Cheng

Publications and source records attributed to Long Cheng.

At least 37 records · Page 2Linked to original sources

arXiv2026

Real-World Evaluation of Protocol-Compliant Denial-of-Service Attacks on C-V2X-based Forward Collision Warning Systems

Cellular Vehicle-to-Everything (C-V2X) technology enables low-latency, reliable communications essential for safety applications such as a Forward Collision Warning (FCW) system. C-V2X deployments operate under strict protocol compliance with the 3rd Generation Partnership Project (3GPP) and the Society of Automotive Engineers Standard (SAE) J2735 specifications to ensure interoperability. This paper presents a real-world testbed evaluation of protocol-compliant Denial-of-Service (DoS) attacks using User Datagram Protocol (UDP) flooding and oversized Basic Safety Message (BSM) attacks that 7 exploit transport- and application-layer vulnerabilities in C-V2X. The attacks presented in this study transmit valid messages over standard PC5 sidelinks, fully adhering to 3GPP and SAE J2735 specifications, but at abnormally high rates and with oversized payloads that overload the receiver resources without breaching any protocol rules such as IEEE 1609. Using a real-world connected vehicle 11 testbed with commercially available On-Board Units (OBUs), we demonstrate that high-rate UDP flooding and oversized payload of BSM flooding can severely degrade FCW performance. Results show that UDP flooding alone reduces packet delivery ratio by up to 87% and increases latency to over 400ms, while oversized BSM floods overload receiver processing resources, delaying or completely suppressing FCW alerts. When UDP and BSM attacks are executed simultaneously, they cause near-total communication failure, preventing FCW warnings entirely. These findings reveal that protocol-compliant communications do not necessarily guarantee safe or reliable operation of C-V2X-based safety applications.

cs.CR↗

arXiv2026

Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation

Sparse-attention decoders rely on exact Top-K selection to choose the most important key-value entries for each query token. In long-context LLM serving, this Top-K stage runs once per decode query and becomes a meaningful latency bottleneck even when the indexer and attention kernels are already highly optimized. We present \textbf{Guess-Verify-Refine (GVR)}, a data-aware exact Top-K algorithm for sparse-attention decoding on NVIDIA Blackwell. GVR exploits temporal correlation across consecutive decode steps: it uses the previous step's Top-K as a prediction signal, computes pre-indexed statistics, narrows to a valid threshold by secant-style counting in 1-2 global passes, verifies candidates with a ballot-free collector, and finishes exact selection in shared memory. We connect this behavior to the Toeplitz / RoPE structure of DeepSeek Sparse Attention (DSA) indexer scores and validate the design on real DeepSeek-V3.2 workloads integrated into TensorRT-LLM. GVR achieves an average \textbf{1.88x} single-operator speedup over the production radix-select kernel, with up to \textbf{2.42x} per layer per step, while preserving bit-exact Top-K outputs. In controlled TEP8 min-latency deployment, it improves end-to-end TPOT by up to \textbf{7.52%} at 100K context, with larger gains at longer contexts and smaller but still positive gains under speculative decoding. While implemented and validated in the current TensorRT-LLM DSA stack on Blackwell, the same principle may extend to sparse-attention decoders whose decode-phase Top-K exhibits temporal stability.

cs.DC↗

arXiv2026

Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting

Photovoltaic (PV) power forecasting plays a critical role in power system dispatch and market participation. Because PV generation is highly sensitive to weather conditions and cloud motion, accurate forecasting requires effective modeling of complex spatiotemporal dependencies across multiple information sources. Although recent studies have advanced AI-based forecasting methods, most fail to fuse temporal observations, satellite imagery, and textual weather information in a unified framework. This paper proposes Solar-VLM, a large-language-model-driven framework for multimodal PV power forecasting. First, modality-specific encoders are developed to extract complementary features from heterogeneous inputs. The time-series encoder adopts a patch-based design to capture temporal patterns from multivariate observations at each site. The visual encoder, built upon a Qwen-based vision backbone, extracts cloud-cover information from satellite images. The text encoder distills historical weather characteristics from textual descriptions. Second, to capture spatial dependencies across geographically distributed PV stations, a cross-site feature fusion mechanism is introduced. Specifically, a Graph Learner models inter-station correlations through a graph attention network constructed over a K-nearest-neighbor (KNN) graph, while a cross-site attention module further facilitates adaptive information exchange among sites. Finally, experiments conducted on data from eight PV stations in a northern province of China demonstrate the effectiveness of the proposed framework. Our proposed model is publicly available at https://github.com/rhp413/Solar-VLM.

cs.AI↗

arXiv2026

Understanding the Risks of Asphalt Art to the Reliability of Vision-Based Perception Systems

Artistic crosswalks featuring asphalt art, introduced by different organizations in recent years, aim to enhance the visibility and safety of pedestrians. However, their visual complexity may interfere with surveillance systems that rely on vision-based object detection models. In this study, we investigate the impact of asphalt art on pedestrian detection performance of a pretrained vision-based object detection model. We construct realistic crosswalk scenarios by compositing various street art patterns into a fixed surveillance scene and evaluate the model's performance in detecting pedestrians on asphalt-arted crosswalks under both benign and adversarial conditions. A benign case refers to pedestrian crosswalks painted with existing normal asphalt art, whereas an adversarial case involves digitally crafted or altered asphalt art perpetrated by an attacker. Our results show that while simple, color-based designs have minimal effect, complex artistic patterns, particularly those with high visual salience, can significantly degrade pedestrian detection performance. Furthermore, we demonstrate that adversarially crafted asphalt art can be exploited to deliberately obscure real pedestrians or generate non-existent pedestrian detections. These findings highlight a potential vulnerability in urban vision-based pedestrian surveillance systems, and underscore the importance of accounting for environmental visual variations when designing robust pedestrian perception models.

cs.CV↗

arXiv2026

DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Models

Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adversarial patch attacks, which can be easily applied to real-world objects to either conceal actual items or create non-existent ones, leading to severe consequences. In this work, we introduce DisPatch, the first diffusion-based defense framework for object detection. Unlike previous works that aim to "detect and remove" adversarial patches, DisPatch adopts a "regenerate and rectify" strategy, leveraging generative models to disarm attack effects while preserving the integrity of the input image. Specifically, we utilize the in-distribution generative power of diffusion models to regenerate the entire image, aligning it with benign data. A rectification process is then employed to identify and replace adversarial regions with their regenerated benign counterparts. DisPatch is attack-agnostic and requires no prior knowledge of the existing patches. Extensive experiments across multiple detectors demonstrate that DisPatch consistently outperforms state-of-the-art defenses on both hiding attacks and creating attacks, achieving the best overall mAP@0.5 score of 89.3% on hiding attacks, and lowering the attack success rate to 24.8% on untargeted creating attacks. Moreover, it strikes the balance between effectiveness and efficiency, and maintains strong robustness against adaptive attacks, making it a practical and reliable defense method.

cs.CV↗

arXiv2026

Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures

Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for comparative adversarial evaluation across three VLM architectures: Dolphins, OmniDrive (Omni-L), and LeapVAD. Using black-box optimization with semantic homogenization for fair comparison, we evaluate physically realizable patch attacks in CARLA simulation. Results reveal severe vulnerabilities across all architectures, sustained multi-frame failures, and critical object detection degradation. Our analysis exposes distinct architectural vulnerability patterns, demonstrating that current VLM designs inadequately address adversarial threats in safety-critical autonomous driving applications.

cs.CV↗

arXiv2026

Coexistence of Antiferromagnetic Spin Fluctuations and Superconductivity in La2SmNi2O7 Thin Films

The interplay between magnetic fluctuations and superconductivity is fundamental for understanding unconventional high-temperature superconductors. In the recently discovered Ruddlesden-Popper phase nickelates-which achieve superconducting transition temperatures up to ~100 K-this connection has been theoretically predicted but experimentally unverified. Using compressively strained La2SmNi2O7 thin films, we report direct evidence for this interplay. We observe a characteristic 'Mexican hat'-shaped magnetoresistance, a signature of superconductivity coexisting with emergent antiferromagnetic (AFM) fluctuations. This distinctive feature arises from a competition between the magnetic field's suppression of AFM fluctuation-driven scattering and its suppression of superconducting fluctuations. We quantify these AFM fluctuations by a crossover field, B*, whose magnitude decreases with increasing temperature and vanishes near the superconducting onset-behavior contrasting sharply with that in high-Tc cuprates. Our results establish not merely coexistence, but also a direct and novel correlation between AFM instability and superconductivity in nickelates, offering crucial insight into their pairing mechanism.

cond-mat.supr-con↗

arXiv2026

Understanding and Mitigating Errors of LLM-Generated RTL Code

Despite limited success in large language model (LLM)-based register-transfer-level (RTL) code generation, the root causes of errors remain poorly understood. To address this, we conduct a comprehensive error analysis, finding that most failures arise not from deficient reasoning, but from a lack of RTL programming knowledge, insufficient circuit understanding, ambiguous specifications, or misinterpreted multimodal inputs. Leveraging in-context learning, we propose targeted correction techniques: a retrieval-augmented generation (RAG) knowledge base to supply domain expertise; design description rules with rule-checking to clarify inputs; external tools to convert multimodal data into LLM-compatible formats; and an iterative simulation-debugging loop for remaining errors. Integrating these into an LLM-based framework yields significant improvement, achieving 98.1% accuracy on the VerilogEval benchmark with DeepSeek-v3.2-Speciale, demonstrating the effectiveness of our approach.

cs.AR↗

arXiv2026

Lens: A Knowledge-Guided Foundation Model for Network Traffic

Network traffic refers to the amount of data being sent and received over the Internet or any system that connects computers. Analyzing network traffic is vital for security and management, yet remains challenging due to the heterogeneity of plain-text packet headers and encrypted payloads. To capture the latent semantics of traffic, recent studies have adopted Transformer-based pretraining techniques to learn network representations from massive traffic data. However, these methods pre-train on data-driven tasks but overlook network knowledge, such as masking partial digits of the indivisible network port numbers for prediction, thereby limiting semantic understanding. In addition, they struggle to extend classification to new classes during fine-tuning due to the distribution shift. Motivated by these limitations, we propose \Lens, a unified knowledge-guided foundation model for both network traffic classification and generation. In pretraining, we propose a Knowledge-Guided Mask Span Prediction method with textual context for learning knowledge-enriched representations. For extending to new classes in finetuning, we reframe the traffic classification as a closed-ended generation task and introduce context-aware finetuning to adapt to the distribution shift. Evaluation results across various benchmark datasets demonstrate that the proposed Lens~achieves superior performance on both classification and generation tasks. For traffic classification, Lens~outperforms competitive baselines substantially on 8 out of 12 tasks with an average accuracy of \textbf{96.33\%} and extends to novel classes with significantly better performance. For traffic generation, Lens~generates better high-fidelity network traffic for network simulation, gaining up to \textbf{30.46\%} and \textbf{33.3\%} better accuracy and F1 in fuzzing tests. We will open-source the code upon publication.

cs.LG↗

arXiv2025

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in memory, power consumption, and computing capacity of edge devices such as mobile phones. This paper introduces AndesVL, a suite of mobile-side MLLMs with 0.6B to 4B parameters based on Qwen3's LLM and various visual encoders. We comprehensively outline the model architectures, training pipeline, and training data of AndesVL, which achieves first-tier performance across a wide range of open-source benchmarks, including fields such as text-rich image understanding, reasoning and math, multi-image comprehension, general VQA, hallucination mitigation, multilingual understanding, and GUI-related tasks when compared with state-of-the-art models of a similar scale. Furthermore, we introduce a 1+N LoRA architecture alongside a Quantization-Aware LoRA Fine-Tuning (QALFT) framework to facilitate efficient task adaptation and model compression during mobile-side deployment of AndesVL. Moreover, utilizing our cache eviction algorithm -- OKV -- along with customized speculative decoding and compression strategies, we achieve a 6.7x peak decoding speedup ratio, up to 30.9% memory reduction, and 1.8 bits-per-weight when deploying AndesVL-4B on MediaTek Dimensity 9500 chips. We release all models on https://huggingface.co/OPPOer.

cs.CV↗

arXiv2025

Observation of Quantum-Criticality-Class Crossover at the LaAlO$_3$/KTaO$_3$ (111) Interface

In two-dimensional (2D) limit, the quantum fluctuation is significantly enhanced which could induce a quantum phase transition. Investigating the quantum criticality is an effective approach to elucidate the underlying physics of 2D superconductivity. Here we report the observation of different universality classes of quantum criticality at the superconducting LaAlO$_3$/KTaO$_3$ (111) interface, i.e. the normal quantum Griffiths singularity (QGS) and the anomalous QGS. The switch of the quantum criticality class is observed from the normal QGS in a low $T_c$ sample with weaker spin-orbit coupling (SOC) to the anomalous QGS in a high $T_c$ sample with stronger SOC. Moreover, owing to the remarkable SOC strength, the high $T_c$ sample exhibits an unprecedentedly enhanced quantum fluctuation at an unusually elevated temperature approaching the Berezinskii-Kosterlitz-Thouless (BKT) transition temperature $T_{BKT}$. This work provides comprehensive recognition of the different quantum criticality classes in the same superconducting LaAlO$_3$/KTaO$_3$ (111) system, which deepens the understanding of the superconducting mechanism of interfacial superconductors.

cond-mat.supr-con↗

arXiv2025

Interplay of spin-orbit coupling and trigonal crystal field enhances superconductivity in $LaAlO_3/KTaO_3$ (111)

In conventional superconductors, bulk physical properties typically degrade as the film thickness approaches the two-dimensional (2D) limit. Here in the (111) oriented LaAlO3/KTaO3 (LAO/KTO) heterostructure, we demonstrate experimental evidence that reducing the conducting layer thickness at the interface significantly enhances superconducting transition temperature Tc, in direct contrast to conventional wisdom. From the sum frequency generation (SFG) spectroscopy and superconducting upper-critical field measurements, both the trigonal symmetry and spin orbit scattering are enhanced with the increased Tc. We attribute the enhanced superconductivity (SC) to the synergic interplay between spin-orbit coupling (SOC) and trigonal crystal field, resulting in an enhanced electron-phonon coupling. Furthermore, we show the existence of unconventional SC: the approaching linear temperature dependence of normal state resistance with increasing Tc and the existence of a quantum critical point (QCP) near the superconducting phase. Our findings provide important insight into the underlying mechanism of the strong orientation-dependent KTO interface SC.

cond-mat.supr-con↗

arXiv2025

Resource Management Schemes for Cloud-Native Platforms with Computing Containers of Docker and Kubernetes

Businesses have made increasing adoption and incorporation of cloud technology into internal processes in the last decade. The cloud-based deployment provides on-demand availability without active management. More recently, the concept of cloud-native application has been proposed and represents an invaluable step toward helping organizations develop software faster and update it more frequently to achieve dramatic business outcomes. Cloud-native is an approach to build and run applications that exploit the cloud computing delivery model's advantages. It is more about how applications are created and deployed than where. The container-based virtualization technology, such as Docker and Kubernetes, serves as the foundation for cloud-native applications. This paper investigates the performance of two popular computational-intensive applications, big data, and deep learning, in a cloud-native environment. We analyze the system overhead and resource usage for these applications. Through extensive experiments, we show that the completion time reduces by up to 79.4% by changing the default setting and increases by up to 96.7% due to different resource management schemes on two platforms. Additionally, the resource release is delayed by up to 116.7% across different systems. Our work can guide developers, administrators, and researchers to better design and deploy their applications by selecting and configuring a hosting platform.

cs.DC↗

arXiv2025

Motion Adaptation Across Users and Tasks for Exoskeletons via Meta-Learning

Wearable exoskeletons can augment human strength and reduce muscle fatigue during specific tasks. However, developing personalized and task-generalizable assistance algorithms remains a critical challenge. To address this, a meta-imitation learning approach is proposed. This approach leverages a task-specific neural network to predict human elbow joint movements, enabling effective assistance while enhancing generalization to new scenarios. To accelerate data collection, full-body keypoint motions are extracted from publicly available RGB video and motion-capture datasets across multiple tasks, and subsequently retargeted in simulation. Elbow flexion trajectories generated in simulation are then used to train the task-specific neural network within the model-agnostic meta-learning (MAML) framework, which allows the network to rapidly adapt to novel tasks and unseen users with only a few gradient updates. The adapted network outputs personalized references tracked by a gravity-compensated PD controller to ensure stable assistance. Experimental results demonstrate that the exoskeleton significantly reduces both muscle activation and metabolic cost for new users performing untrained tasks, compared to performing without exoskeleton assistance. These findings suggest that the proposed framework effectively improves task generalization and user adaptability for wearable exoskeleton systems.

cs.RO↗

arXiv2025

ViSTR-GP: Online Cyberattack Detection via Vision-to-State Tensor Regression and Gaussian Processes in Automated Robotic Operations

Industrial robotic systems are central to automating smart manufacturing operations. Connected and automated factories face growing cybersecurity risks that can potentially cause interruptions and damages to physical operations. Among these attacks, data-integrity attacks often involve sophisticated exploitation of vulnerabilities that enable an attacker to access and manipulate the operational data and are hence difficult to detect with only existing intrusion detection or model-based detection. This paper addresses the challenges in utilizing existing side-channels to detect data-integrity attacks in robotic manufacturing processes by developing an online detection framework, ViSTR-GP, that cross-checks encoder-reported measurements against a vision-based estimate from an overhead camera outside the controller's authority. In this framework, a one-time interactive segmentation initializes SAM-Track to generate per-frame masks. A low-rank tensor-regression surrogate maps each mask to measurements, while a matrix-variate Gaussian process models nominal residuals, capturing temporal structure and cross-joint correlations. A frame-wise test statistic derived from the predictive distribution provides an online detector with interpretable thresholds. We validate the framework on a real-world robotic testbed with synchronized video frame and encoder data, collecting multiple nominal cycles and constructing replay attack scenarios with graded end-effector deviations. Results on the testbed indicate that the proposed framework recovers joint angles accurately and detects data-integrity attacks earlier with more frequent alarms than all baselines. These improvements are most evident in the most subtle attacks. These results show that plants can detect data-integrity attacks by adding an independent physical channel, bypassing the controller's authority, without needing complex instrumentation.

cs.RO↗

arXiv2025

Boosting Action-Information via a Variational Bottleneck on Unlabelled Robot Videos

Learning from demonstrations (LfD) typically relies on large amounts of action-labeled expert trajectories, which fundamentally constrains the scale of available training data. A promising alternative is to learn directly from unlabeled video demonstrations. However, we find that existing methods tend to encode latent actions that share little mutual information with the true robot actions, leading to suboptimal control performance. To address this limitation, we introduce a novel framework that explicitly maximizes the mutual information between latent actions and true actions, even in the absence of action labels. Our method leverage the variational information-bottleneck to extract action-relevant representations while discarding task-irrelevant information. We provide a theoretical analysis showing that our objective indeed maximizes the mutual information between latent and true actions. Finally, we validate our approach through extensive experiments: first in simulated robotic environments and then on real-world robotic platforms, the experimental results demonstrate that our method significantly enhances mutual information and consistently improves policy performance.

cs.RO↗

arXiv2025

Anomalous Decision Discovery using Inverse Reinforcement Learning

Anomaly detection plays a critical role in Autonomous Vehicles (AVs) by identifying unusual behaviors through perception systems that could compromise safety and lead to hazardous situations. Current approaches, which often rely on predefined thresholds or supervised learning paradigms, exhibit reduced efficacy when confronted with unseen scenarios, sensor noise, and occlusions, leading to potential safety-critical failures. Moreover, supervised methods require large annotated datasets, limiting their real-world feasibility. To address these gaps, we propose an anomaly detection framework based on Inverse Reinforcement Learning (IRL) to infer latent driving intentions from sequential perception data, thus enabling robust identification. Specifically, we present Trajectory-Reward Guided Adaptive Pre-training (TRAP), a novel IRL framework for anomaly detection, to address two critical limitations of existing methods: noise robustness and generalization to unseen scenarios. Our core innovation is implicitly learning temporal credit assignments via reward and worst-case supervision. We leverage pre-training with variable-horizon sampling to maximize time-to-consequence, resulting in early detection of behavior deviation. Experiments on 14,000+ simulated trajectories demonstrate state-of-the-art performance, achieving 0.90 AUC and 82.2\% F1-score - outperforming similarly trained supervised and unsupervised baselines by 39\% on Recall and 12\% on F1-score, respectively. Similar performance is achieved while exhibiting robustness to various noise types and generalization to unseen anomaly types. Our code will be available at: https://github.com/abastola0/TRAP.git

cs.AI↗

arXiv2025

VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations

Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific expertise. Large language models (LLMs), with their ability to capture intricate patterns, provide a promising solution, yet their effective application in compiler optimizations remains an open challenge due to issues such as hallucinations and a lack of domain-specific reasoning. In this paper, we present VecTrans, a novel framework that leverages LLMs to enhance compiler-based code vectorization. VecTrans first employs compiler analysis to identify potentially vectorizable code regions. It then utilizes an LLM to refactor these regions into patterns that are more amenable to the compilers auto-vectorization. To ensure semantic correctness, VecTrans further integrates a hybrid validation mechanism at the intermediate representation (IR) level. With the above efforts, VecTrans combines the adaptability of LLMs with the precision of compiler vectorization, thereby effectively opening up the vectorization opportunities. experimental results show that among all TSVC functions unvectorizable by GCC, ICC, Clang, and BiSheng Compiler, VecTrans achieves an geomean speedup of 1.77x and successfully vectorizes 24 of 51 test cases. This marks a significant advancement over state-of-the-art approaches while maintaining a cost efficiency of $0.012 per function optimization for LLM API usage.

cs.SE↗