arXiv subjects

Yumeng Song

Publications and source records attributed to Yumeng Song.

12 recordsLinked to original sources

arXiv2026

Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay

Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attribution cannot distinguish a jointly necessary repair from alternative singleton repairs. We formulate Minimal Repair Family Recovery (MRFR): recovering all inclusion-minimal event sets whose counterfactual replay restores task success within a declared size bound. We propose Graph-Constrained Joint Replay (GCJR), which slices failure-relevant events from an execution dependency graph, constructs graph-feasible singleton and pair candidates, and verifies them by replay with paired clean counterparts. For fixed replay outcomes, GCJR is exact within its declared graph domain. On 90 in-scope cases from a 120-DAG controlled benchmark, GCJR achieves 1.000 Family Exact Match while reducing mean replay calls from 56.3 to 25.3 (55.1%) relative to exhaustive search. On a 24-case, four-agent LLM pilot, it again achieves 1.000 Family Exact Match and reduces mean model calls from 21.0 to 10.0 (52.4%); single-event replay misses jointly necessary repairs.

cs.AI↗

arXiv2026

VTRQ: Enabling Verifiable Trajectory Range Queries in Hybrid-Storage Blockchains

Due to their increasingly large volumes, outsourcing of trajectory storage and querying to third-party service providers has become attractive. However, in such outsourced environments, service providers may return incorrect, e.g., incomplete, tampered, or invalid query results, making verifiability of query results an important consideration. Existing hybrid-storage blockchains offer limited support for trajectory data, lacking authenticated data structures (ADS) that enable efficient verification. For example, ADSs designed for queries on one-dimensional data are unsuitable for queries on multidimensional trajectory data, while ADSs tailored for discrete data may yield incomplete results when applied to continuous trajectory data. We propose the first framework for verifiable trajectory range queries in hybrid-storage blockchains, called VTRQ. It features two efficient ADSs: (i) a spatial ADS for road networks that leverages hierarchical organization to aggregate trajectory, edge, and node hashes, thus reducing redundant computations and improving spatial verification efficiency; and (ii) a temporal ADS based on interval trees, which indexes only the start and end times of trajectories, thereby enabling pruning and efficient temporal verification. By separating spatial and temporal indexing, the method reduces the need for data comparison, enhancing both query and verification efficiency. To aggregate spatial and temporal query results, VTRQ provides a spatio-temporal edge aggregation mechanism that combines temporal verification of spatial nodes, spatial intersection computation, and temporal intersection analysis to achieve spatio-temporal filtering.

cs.DB↗

arXiv2026

FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data

Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation models (SFMs) aim to support data analysis and mining tasks over such data, but still face scalability and generalization challenges when applied to real-world enterprise databases. First, many SFMs rely on full self-attention, which introduces an O(N^2) computational bottleneck and limits the number of tuples that can be processed jointly. Second, directly replacing attention with linear-complexity sequence models may conflict with the permutation-invariant nature of structured data, introducing artificial order bias and degrading representation quality. Moreover, models trained only on synthetic data may struggle to generalize to the heavy-tailed and heterogeneous distributions commonly found in real-world databases. To address these challenges, we propose FEAT, a linear-complexity foundation model for extremely large structured data. FEAT replaces quadratic attention with a multi-layer dual-axis encoding architecture. It integrates an adaptive-fusion bidirectional state-space model (AFBM) with convolutional gated linear attention (Conv-GLA), enabling cross-tuple contextualization in O(N) time while supporting permutation-invariant representation learning. To improve robustness under real-world data skewness, FEAT further adopts a hybrid structural causal pre-training pipeline with a robust reconstruction objective. Experiments on 12 real-world database benchmarks show that FEAT consistently outperforms representative SFMs on zero-shot tasks and scales linearly with structured-data sample length, achieving up to 50x faster inference latency.

cs.LG↗

arXiv2026

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to execute complex workflows. This level of access creates unprecedented security challenges. Consequently, traditional content-filtering defenses have become obsolete. This report presents a comprehensive security analysis of the OpenClaw ecosystem. We systematically investigate its current threat landscape, highlighting critical vulnerabilities such as prompt injection-driven Remote Code Execution (RCE), sequential tool attack chains, context amnesia, and supply chain contamination. To systematically contextualize these threats, we propose a novel tri-layered risk taxonomy for autonomous Agents, categorizing vulnerabilities across AI Cognitive, Software Execution, and Information System dimensions. To address these systemic architectural flaws, we introduce the Full-Lifecycle Agent Security Architecture (FASA). This theoretical defense blueprint advocates for zero-trust agentic execution, dynamic intent verification, and cross-layer reasoning-action correlation. Building on this framework, we present Project ClawGuard, our ongoing engineering initiative. This project aims to implement the FASA paradigm and transition autonomous agents from high-risk experimental utilities into trustworthy systems. Our code and dataset are available at https://github.com/NY1024/ClawGuard.

cs.CR↗

arXiv2026

TCRL: Temporal-Coupled Adversarial Training for Robust Constrained Reinforcement Learning in Worst-Case Scenarios

Constrained Reinforcement Learning (CRL) aims to optimize decision-making policies under constraint conditions, making it highly applicable to safety-critical domains such as autonomous driving, robotics, and power grid management. However, existing robust CRL approaches predominantly focus on single-step perturbations and temporally independent adversarial models, lacking explicit modeling of robustness against temporally coupled perturbations. To tackle these challenges, we propose TCRL, a novel temporal-coupled adversarial training framework for robust constrained reinforcement learning (TCRL) in worst-case scenarios. First, TCRL introduces a worst-case-perceived cost constraint function that estimates safety costs under temporally coupled perturbations without the need to explicitly model adversarial attackers. Second, TCRL establishes a dual-constraint defense mechanism on the reward to counter temporally coupled adversaries while maintaining reward unpredictability. Experimental results demonstrate that TCRL consistently outperforms existing methods in terms of robustness against temporally coupled perturbation attacks across a variety of CRL tasks.

cs.LG↗

arXiv2025

Host dependence of PL5 ensemble in 4H-SiC

Color center PL5 in 4H silicon carbide (4H-SiC) has drawn significant attention due to its room-temperature quantum coherence properties and promising potential of quantum sensing applications. The preparation of PL5 ensemble is a critical prerequisite for practical applications. In this work, we investigated the formation of PL5 ensembles in types of 4H-SiC wafers, focusing on their suitability as hosts for PL5 ensemble. Results demonstrate that PL5 signals are exclusively observed in high-purity semi-insulating (HPSI) substrates, whereas divacancies PL1-PL4 can be detected in both HPSI and epitaxial samples. The type of in-plane stress in HPSI and epitaxial hosts is compressive in the same order of magnitude. Defects like stacking faults and dislocations are not observed simultaneously in the PL5 ensemble. Notably, the PL5 ensemble exhibits a relatively uniform distribution in the HPSI host, highlighting its readiness for integration into quantum sensing platforms. Furthermore, signal of PL5 can always be detected in the HPSI samples with different doses of electron irradiation, which suggests that HPSI wafers are more suitable hosts for the production of PL5 ensemble. This work provides critical insights into the material-specific requirements for PL5 ensemble formation and advances the development of 4H-SiC-based quantum technologies.

cond-mat.mtrl-sci↗

arXiv2025

Quantifying Point Contributions: A Lightweight Framework for Efficient and Effective Query-Driven Trajectory Simplification

As large volumes of trajectory data accumulate, simplifying trajectories to reduce storage and querying costs is increasingly studied. Existing proposals face three main problems. First, they require numerous iterations to decide which GPS points to delete. Second, they focus only on the relationships between neighboring points (local information) while neglecting the overall structure (global information), reducing the global similarity between the simplified and original trajectories and making it difficult to maintain consistency in query results, especially for similarity-based queries. Finally, they fail to differentiate the importance of points with similar features, leading to suboptimal selection of points to retain the original trajectory information. We propose MLSimp, a novel Mutual Learning query-driven trajectory simplification framework that integrates two distinct models: GNN-TS, based on graph neural networks, and Diff-TS, based on diffusion models. GNN-TS evaluates the importance of a point according to its globality, capturing its correlation with the entire trajectory, and its uniqueness, capturing its differences from neighboring points. It also incorporates attention mechanisms in the GNN layers, enabling simultaneous data integration from all points within the same trajectory and refining representations, thus avoiding iterative processes. Diff-TS generates amplified signals to enable the retention of the most important points at low compression rates. Experiments involving eight baselines on three databases show that MLSimp reduces the simplification time by 42%--70% and improves query accuracy over simplified trajectories by up to 34.6%.

cs.DB↗

arXiv2023

CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network

Hypergraphs can model higher-order relationships among data objects that are found in applications such as social networks and bioinformatics. However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data. To such learning, we propose a contrastive hypergraph neural network, CHGNN, that exploits self-supervised contrastive learning techniques to learn from labeled and unlabeled data. First, CHGNN includes an adaptive hypergraph view generator that adopts an auto-augmentation strategy and learns a perturbed probability distribution of minimal sufficient views. Second, CHGNN encompasses an improved hypergraph encoder that considers hyperedge homogeneity to fuse information effectively. Third, CHGNN is equipped with a joint loss function that combines a similarity loss for the view generator, a node classification loss, and a hyperedge homogeneity loss to inject supervision signals. It also includes basic and cross-validation contrastive losses, associated with an enhanced contrastive loss training process. Experimental results on nine real datasets offer insight into the effectiveness of CHGNN, showing that it outperforms 13 competitors in terms of classification accuracy consistently.

cs.LG↗

arXiv2022

Online optimization for optical readout of a single electron spin in diamond

The nitrogen-vacancy (NV) center in diamond has been developed as a promising platform for quantum sensing, especially for magnetic field measurements in the nano-tesla range with a nanometer resolution. Optical spin readout performance has a direct effect on the signal-to-noise ratio (SNR) of experiments. In this work, we introduce an online optimization method to customize the laser waveform for readout. Both simulations and experiments reveal that our new scheme optimizes the optically detected magnetic resonance in NV center. The SNR of optical spin readout has been witnessed a 44.1% increase in experiments. In addition, we applied the scheme to the Rabi oscillation experiment, which shows an improvement of 46.0% in contrast and a reduction of 12.1% in mean deviation compared to traditional constant laser power SNR optimization. This scheme is promising to improve sensitivities for a wide range of NV-based applications in the future.

quant-ph↗

arXiv2022

Preserving Entanglement in a Solid-Spin System Using Quantum Autoencoders

Entanglement, as a key resource for modern quantum technologies, is extremely fragile due to the decoherence. Here, we show that a quantum autoencoder, which is trained to compress a particular set of quantum entangled states into a subspace that is robust to decoherence, can be employed to preserve entanglement. The training process is based on a hybrid quantum-classical approach to improve the efficiency in building the autoencoder and reduce the experimental errors during the optimization. Using nitrogen-vacancy centers in diamond, we demonstrate that the entangled states between the electron and nuclear spins can be encoded into the nucleus subspace which has much longer coherence time. As a result, lifetime of the Bell states in this solid-spin system is extended from 2.22 {\pm} 0.43 {\mu}s to 3.03 {\pm} 0.56 ms, yielding a three orders of magnitude improvement. The quantum autoencoder approach is universal, paving the way of utilizing long lifetime nuclear spins as immediate-access quantum memories in quantum information tasks.

quant-ph↗

arXiv2021

In-situ non-equilibrium nanomechanics in a proton-conducting ceramic at low temperatures

Nanostructured proton-conducting ceramics (PCCs) have attracted considerable interest as moderate-temperature proton conductors. Structure dynamics during proton conduction, particularly at grain boundaries, are crucial for stability and proton transport in nanostructured PCCs. A common assumption is that PCCs are structurally stable at low operating temperatures; however, material polycrystallinity, absorption, and reactive operating conditions have so far prevented verifying this assumption by nano resolved in-situ structure measurements. Here, in an archetypal PCC BaZr0.8Y0.2O3-d the premise of structural stability is demonstrated to be inaccurate at temperatures as low as 200 {\deg}C. Coherent X-ray diffraction on a nanostructured BaZr0.8Y0.2O3-d sintered pellet is adapted to image in-situ three-dimensional structural processes inside the constituent submicron grains in a humid nitrogen atmosphere at 200 {\deg}C. Direct observation reveals non-equilibrium defect generation and subsequent grain cracking on a timescale of hours, forming new, otherwise energetically unfavorable facets in BaZr0.8Y0.2O3-d. Furthermore, the structural rearrangements correlate with dynamic inhomogeneities of the lattice constant within the grains, showing potential heterogeneous H+ transport. Our results elucidate the mechanisms behind PCCs structural degradation, overturn existing assumptions about the structure dynamics in PCCs, and fill a method gap for further in-depth in-situ studies of the PCC nanostructure.

cond-mat.mtrl-sci↗

arXiv2019

Pulse-width-induced polarization enhancement of optically-pumped N-V electron spin in diamond

The nitrogen-vacancy (N-V) center in diamond is a widely-used platform for quantum information processing and metrology. The electron-spin state of N-V center could be initialized and readout optically, and manipulated by resonate microwave fields. In this work, we analyze the dependence of electron-spin initialization on widths of laser pulses. We build a numerical model to simulate this process and verify the simulation results in experiment. Both simulations and experiments reveal a fact that shorter laser pulses are helpful to the electron-spin polarization. We therefore propose to use extremely-short laser pulses for electron-spin initialization. In this new scheme, the spin-state contrast could be improved about 10% in experiment by using laser pulses as short as 4 ns in width. Furthermore, we provide a mechanism to explain this effect which is due to the occupation time in the meta-stable spin-singlet states of N-V center. Our new scheme is applicable in a broad range of NV-based applications in the future.

quant-ph↗