arXiv subjects

Sibo Wang

Publications and source records attributed to Sibo Wang.

At least 19 recordsLinked to original sources

arXiv2026

Microscopic Realization of Topologically Quantized Alignment in Fast-Rotating Nuclei

We present the first quantitative microscopic realization of topologically quantized alignment in a finite nuclear system. The realization is obtained by exact diagonalization of a cranking seniority model, with the first Chern number evaluated over the sphere of cranking-axis orientations and analyzed together with the orientation-averaged alignment and cranking-frame configuration probabilities. The Chern number changes in integer steps as the system evolves from initially paired configurations to increasingly aligned configurations. A new intermediate phase is found in which the Chern number is already nonzero while the alignment continues to evolve toward its quantized value. We show that this deviation originates from the competition among pairing, axial quadrupole splitting, and Coriolis mixing. Thus, our microscopic approach reveals a more nuanced emergence of topologically quantized alignment in realistic nuclei, providing a quantitative stepping stone toward experimental investigations.

nucl-th↗

arXiv2026

Relativistic dynamical effects in proton emission: the Wentzel-Kramers-Brillouin method for 1+1 dimensional Dirac equation

Starting from the $1+1$ dimensional (one spatial and one temporal dimension) Dirac equation, we employ the Wentzel-Kramers-Brillouin (WKB) approximation to derive the corresponding relativistic penetration probability. The derivation shows that the semiclassical momentum is determined by the Schr\"odinger-equivalent potential $ U_{\text{eff}}(r) = S(r) + \frac{E}{m}V(r) + \frac{S^{2}(r)-V^{2}(r)}{2m}$, instead of the simple sum of scalar and vector potentials $S(r)+V(r)$, which has been adopted widely in the studies of relativistic quantum tunneling. We then quantify the relativistic dynamical effects in proton emission by comparing the results obtained with $U_{\text{eff}}(r)$ and those obtained with $S(r)+V(r)$. Incorporating $U_{\text{eff}}(r)$ systematically reduces the penetration probability and the assault frequency, and consequently increases the predicted half-life. The relativistic dynamical effect becomes more pronounced with higher orbital angular momentum and can reach about $84\%$ in the half-life of $^{144}\mathrm{Tm}$.

nucl-th↗

arXiv2026

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.g., zero-shot classification) and consequently lack generalizability across various multimodal tasks. To address this limitation, we propose a dual adversarial fine-tuning framework that jointly optimizes visual and semantic supervision signals from two modalities, enhancing model robustness while generalizing across multiple downstream tasks. The proposed framework comprises two core components, i.e., $\textbf{Visual}$ supervision branch and $\textbf{Semantic}$ supervision branch. The former branch leverages features from clean images, extracted via a frozen original vision encoder, to guide adversarial robustness while the latter incorporates caption-image alignment as a contextual signal to preserve semantic coherence under attack. Moreover, our method achieves cross-task robustness by simply replacing the CLIP vision encoder in the original model, with no need of separate task-specific retraining or architecture modifications.Extensive experiments demonstrate that our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering (VQA) tasks.

cs.CV↗

arXiv2026

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less understood. Analyzing roughly 38,000 hours of agent interaction with the environment across 134 real world tasks, we find, to the best of our knowledge, the first evidence that overall performance during environment learning follows a log-sigmoid scaling law with remarkably high precision, reaching R^2 = 0.998. Across model generations, we also find that agent learning speed roughly doubles every three months. This discovery stems from EdgeBench, a suite of 134 real world tasks with ultra-long horizons, spanning scientific discovery, software engineering, combinatorial optimization, professional knowledge work, formal mathematics, and interactive games. Each task sustains at least 12 hours of continuous agent operation under rich, multilevel feedback, and is built through substantial expert effort. We publicly release 51 tasks and our full evaluation framework to accelerate the study of how agents learn from real world experience.

cs.CL↗

arXiv2026

Functional methods for quantum thermodynamics

The functional renormalization group provides a nonperturbative and systematically improvable route to constructing density functionals for quantum many-body systems from microscopic Hamiltonians. Here we advance this program by benchmarking functional-renormalization-group density functional theory (FRG-DFT) against the exact thermodynamics of the single-site Bose-Hubbard model. This model provides an ideal testing ground because it is analytically solvable, yet remains subtle in the imaginary-time coherent-state path integral, where a naive continuum treatment generates a spurious self-interaction. We show that a careful Hubbard-Stratonovich derivation identifies the self-interaction correction term that must be included in the FRG-DFT flow to recover the exact thermodynamics. We then systematically compare several closures of the resulting hierarchy of flow equations for the free energy, chemical potential, and connected density correlators over broad ranges of density, temperature, and interaction strength. The benchmark shows that the free energy is comparatively robust, whereas the chemical potential and fluctuation observables provide much sharper diagnostics of the hierarchy closure. A maximum-entropy closure gives the most accurate overall description and reproduces even the low-temperature oscillatory structure of the connected two-density correlator. These results identify two general requirements for functional approaches to quantum thermodynamics: the renormalization group flow equation must retain the equal-time contact subtraction to avoid spurious self-interactions, and any closure of the hierarchy must preserve the statistical consistency of density correlators. This work provides a controlled foundation for deriving ab initio density functionals for quantum many-body systems across condensed-matter, ultracold-atom, and nuclear physics, as well as quantum chemistry.

cond-mat.quant-gas↗

arXiv2026

R&D of cosmic ray detection module with liquid scintillator and wavelength shift fiber

For neutrino physics and rare event searches, background related to cosmic muons poses a notable challenge, and must be identified and rejected. It is also a challenge to control the cost with good performance for a large array of cosmic ray detection. We proposed a cosmic ray detection module with liquid scintillator and wavelength-shifting fibers for its reasonable cost and performances. The results from the measurements of a prototype with Muon indicate that the detector's photoelectron response is good. % comparing to the expectation. The outcomes of this study hold significant potential for applications in cosmic ray observation experiments and underground rare-event detection, providing a viable option for future large-scale observatories. This work highlights the feasibility of liquid scintillator-based detectors in addressing current and emerging challenges in particle physics and astrophysics.

physics.ins-det↗

arXiv2026

Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework

Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative reasoning and self-evolution. A number of memory methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework that covers existing representative agent memory methods from a high-level perspective. We then extensively compare representative agent memory methods on two long-term conversational benchmarks and an agentic memory benchmark, and examine the effectiveness of representative methods, providing a thorough analysis of those methods. As a byproduct of our experimental analysis, we also design a new memory method by exploiting modules in the existing methods, which outperforms the state-of-the-art methods. Finally, based on these findings, we offer promising future research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide valuable new insights for future research.

cs.CL↗

arXiv2026

Collective quantum tunneling with time-dependent generator coordinate method

Inspired by the work of McGlynn and Simenel [Phys. Rev. C {\bf 102}, 064614 (2020)], this study investigates the quantum tunneling of two interacting distinguishable particles in two potential wells. We first benchmark the system by reproducing key established results: the exact quantum solution and the spurious self-trapping effect that arises in the real-time mean-field dynamics for strong interactions. To exactly capture the tunneling dynamics, we apply the time-dependent generator coordinate method (TDGCM) to the model. Numerical simulations demonstrate that the TDGCM, by utilizing the real-time mean-field states as generator states, successfully overcomes the self-trapping effect, yielding tunneling dynamics in excellent agreement with the exact solution. Furthermore, we explore the expectation values of the generator coordinates from the correlated TDGCM many-body wave function. While different methods for calculating expectation values show consistent results in some cases, significant discrepancies are observed in others, providing critical insights into the emergence of collective and single-particle behaviors in interacting systems. This work also verifies the TDGCM as a robust framework for describing collective quantum tunneling and opens avenues for its application to more complex and realistic systems.

nucl-th↗

arXiv2026

Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the linkage between visual evidence and intermediate steps and often causing unstable optimization and visual hallucinations. We propose Differential Feedback, which automatically constructs token/step-level supervision masks by repairing erroneous reasoning trajectories, explicitly marking the key positions that require correction. Without costly large-scale step-by-step human annotations, our method enables process-level visual alignment and can be seamlessly integrated into existing GRPO-like frameworks. Experiments on multimodal reasoning benchmarks including MMMStar and MathVista show an average 3% improvement under matched compute budgets. Our approach offers an effective, low-cost solution for accurate vision--reasoning process alignment.

cs.CV↗

arXiv2025

PoseStreamer: A Multi-modal Framework for 3D Tracking of Unseen Moving Objects

Six degree of freedom (6DoF) pose estimation for novel objects is a critical task in computer vision, yet it faces significant challenges in high-speed and low-light scenarios where standard RGB cameras suffer from motion blur. While event cameras offer a promising solution due to their high temporal resolution, current 6DoF pose estimation methods typically yield suboptimal performance in high-speed object moving scenarios. To address this gap, we propose PoseStreamer, a robust multi-modal 6DoF pose estimation framework designed specifically on high-speed moving scenarios. Our approach integrates three core components: an Adaptive Pose Memory Queue that utilizes historical orientation cues for temporal consistency, an Object-centric 2D Tracker that provides strong 2D priors to boost 3D center recall, and a Ray Pose Filter for geometric refinement along camera rays. Furthermore, we introduce MoCapCube6D, a novel multi-modal dataset constructed to benchmark performance under rapid motion. Extensive experiments demonstrate that PoseStreamer not only achieves superior accuracy in high-speed moving scenarios, but also exhibits strong generalizability as a template-free framework for unseen moving objects.

cs.CV↗

arXiv2025

Neural Network Construction of the Equation of State from Relativistic ab initio Calculations

Constraining the nuclear matter equation of state (EOS) beyond saturation density is a central goal of nuclear physics and astrophysics. While the relativistic Brueckner-Hartree-Fock (RBHF) theory, an \textit{ab initio,} non-perturbative nuclear many-body theory starting from realistic interactions, accurately describes nuclear matter properties near the saturation density $\rho_0 \approx 0.16$ fm$^{-3}$, its applicability is currently limited to densities up to $3 \rho_0$, necessitating a reliable extrapolation to higher densities. In this work, we employ supervised machine learning to train thousands of fully connected neural networks on low-density RBHF data. By enforcing thermodynamic consistency and smoothness, we finally select a subset of 264 optimal models. These models employ the Swish activation function, which we identify as the most reliable choice for stable extrapolation after extensive testing and comparison. Using these models to extend the EOS over the full density range, we obtain the nuclear matter symmetry energy and then compute the neutron star mass-radius relation and tidal deformability, which are in a great harmony with current astronomical observations. The corresponding extrapolation uncertainty originates from the combined contributions of both the 264 optimal models and the linear regression on nuclear matter EOS, yielding a symmetry energy of $E\mathrm{_{sym}(5\rho_0)=136.0 \pm 52.8 MeV}$, a pressure of $P(5\rho_0) = 346.3 \pm 97.4 \mathrm{MeV/fm^{3}}$, a maximum neutron star mass of $M\mathrm{_{max}=2.18 \pm 0.18} M_{\odot}$, and a tidal deformability of $\Lambda_{1.4M_\odot} = 532 \pm 34$. This work establishes a general and data-driven framework to explore dense matter EOS by integrating \textit{ab initio} calculations with modern machine learning techniques.

nucl-th↗

arXiv2025

ACGraph: An Efficient Asynchronous Out-of-Core Graph Processing Framework

Graphs are a ubiquitous data structure in diverse domains such as machine learning, social networks, and data mining. As real-world graphs continue to grow beyond the memory capacity of single machines, out-of-core graph processing systems have emerged as a viable solution. Yet, existing systems that rely on strictly synchronous, iteration-by-iteration execution incur significant overheads. In particular, their scheduling mechanisms lead to I/O inefficiencies, stemming from read and work amplification, and induce costly synchronization stalls hindering sustained disk utilization. To overcome these limitations, we present {\em ACGraph}, a novel asynchronous graph processing system optimized for SSD-based environments with constrained memory resources. ACGraph employs a dynamic, block-centric priority scheduler that adjusts in real time based on workload, along with an online asynchronous worklist that minimizes redundant disk accesses by efficiently reusing active blocks in memory. Moreover, ACGraph unifies asynchronous I/O with computation in a pipelined execution model that maintains sustained I/O activation, and leverages a highly optimized hybrid storage format to expedite access to low-degree vertices. We implement popular graph algorithms, such as Breadth-First Search (BFS), Weakly Connected Components (WCC), personalized PageRank (PPR), PageRank (PR), and $k$-core on ACGraph and demonstrate that ACGraph substantially outperforms state-of-the-art out-of-core graph processing systems in both runtime and I/O efficiency.

cs.DB↗

arXiv2025

FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervision

Graph-level anomaly detection (GAD) is critical in diverse domains such as drug discovery, yet high labeling costs and dataset imbalance hamper the performance of Graph Neural Networks (GNNs). To address these issues, we propose FracAug, an innovative plug-in augmentation framework that enhances GNNs by generating semantically consistent graph variants and pseudo-labeling with mutual verification. Unlike previous heuristic methods, FracAug learns semantics within given graphs and synthesizes fractional variants, guided by a novel weighted distance-aware margin loss. This captures multi-scale topology to generate diverse, semantic-preserving graphs unaffected by data imbalance. Then, FracAug utilizes predictions from both original and augmented graphs to pseudo-label unlabeled data, iteratively expanding the training set. As a model-agnostic module compatible with various GNNs, FracAug demonstrates remarkable universality and efficacy: experiments across 14 GNNs on 12 real-world datasets show consistent gains, boosting average AUROC, AUPRC, and F1-score by up to 5.72%, 7.23%, and 4.18%, respectively.

cs.LG↗

arXiv2025

Study of a Compact Device for Water Attenuation Length Measurements

This study presents the development and validation of a compact device for measuring the water attenuation length (WAL), utilizing photomultiplier tubes (PMTs), optical fibers, and light-emitting diodes (LEDs). An 8 m water tank and the device was constructed and validated in the laboratory. The device is capable of measuring WAL values up to 50 m. The stray light was blocked mainly by a custom-designed shutter. Toy Monte Carlo simulations were employed to evaluate the measurement uncertainty, which was found to be within reasonable limits. These simulations further indicate that the uncertainty can be reduced and more accurately predicted for a larger-scale device with a length of 30 m. Real-time monitoring was achieved by integrating the device into a water purification circulation system, providing a practical, scalable solution for WAL measurement in future large-scale water Cherenkov detectors.

physics.ins-det↗

arXiv2025

Collaborative Evolution of Intelligent Agents in Large-Scale Microservice Systems

This paper proposes an intelligent service optimization method based on a multi-agent collaborative evolution mechanism to address governance challenges in large-scale microservice architectures. These challenges include complex service dependencies, dynamic topology structures, and fluctuating workloads. The method models each service as an agent and introduces graph representation learning to construct a service dependency graph. This enables agents to perceive and embed structural changes within the system. Each agent learns its policy based on a Markov Decision Process. A centralized training and decentralized execution framework is used to integrate local autonomy with global coordination. To enhance overall system performance and adaptability, a game-driven policy optimization mechanism is designed. Through a selection-mutation process, agent strategy distributions are dynamically adjusted. This supports adaptive collaboration and behavioral evolution among services. Under this mechanism, the system can quickly respond and achieve stable policy convergence when facing scenarios such as sudden workload spikes, topology reconfigurations, or resource conflicts. To evaluate the effectiveness of the proposed method, experiments are conducted on a representative microservice simulation platform. Comparative analyses are performed against several advanced approaches, focusing on coordination efficiency, adaptability, and policy convergence performance. Experimental results show that the proposed method outperforms others in several key metrics. It significantly improves governance efficiency and operational stability in large-scale microservice systems. The method demonstrates strong practical value and engineering feasibility.

cs.DC↗

arXiv2025

Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services

This study proposes an anomaly detection method based on the Transformer architecture with integrated multiscale feature perception, aiming to address the limitations of temporal modeling and scale-aware feature representation in cloud service environments. The method first employs an improved Transformer module to perform temporal modeling on high-dimensional monitoring data, using a self-attention mechanism to capture long-range dependencies and contextual semantics. Then, a multiscale feature construction path is introduced to extract temporal features at different granularities through downsampling and parallel encoding. An attention-weighted fusion module is designed to dynamically adjust the contribution of each scale to the final decision, enhancing the model's robustness in anomaly pattern modeling. In the input modeling stage, standardized multidimensional time series are constructed, covering core signals such as CPU utilization, memory usage, and task scheduling states, while positional encoding is used to strengthen the model's temporal awareness. A systematic experimental setup is designed to evaluate performance, including comparative experiments and hyperparameter sensitivity analysis, focusing on the impact of optimizers, learning rates, anomaly ratios, and noise levels. Experimental results show that the proposed method outperforms mainstream baseline models in key metrics, including precision, recall, AUC, and F1-score, and maintains strong stability and detection performance under various perturbation conditions, demonstrating its superior capability in complex cloud environments.

cs.LG↗

arXiv2025

Efficient Integration of Multi-View Attributed Graphs for Clustering and Embedding

A multi-view attributed graph (MVAG) G captures the diverse relationships and properties of real-world entities through multiple graph views and attribute views. Effectively utilizing all views in G is essential for MVAG clustering and embedding, which are important for applications like recommendation systems, anomaly detection, social network analysis, etc. Existing methods either achieve inferior result quality or incur significant computational costs to handle large-scale MVAGs. In this paper, we present a spectrum-guided Laplacian aggregation scheme with an effective objective formulation and two efficient algorithms SGLA and SGLA+, to cohesively integrate all views of G into an MVAG Laplacian matrix, which readily enables classic graph algorithms to handle G with superior performance in clustering and embedding tasks. We begin by conducting a theoretical analysis to design an integrated objective that consists of two components, the eigengap and connectivity objectives, aiming to link the spectral properties of the aggregated MVAG Laplacian with the underlying community and connectivity properties of G. A constrained optimization problem is then formulated for the integration, which is computationally expensive to solve. Thus, we first develop the SGLA algorithm, which already achieves excellent performance compared with existing methods. To further enhance efficiency, we design SGLA+ to reduce the number of costly objective evaluations via sampling and approximation to quickly find an approximate optimum. Extensive experiments compare our methods against 12 baselines for clustering and 8 baselines for embedding on 8 multi-view attributed graphs, validating the superior performance of SGLA and SGLA+ in terms of result quality and efficiency. Compared with the most effective baselines, our methods are significantly faster, often by up to orders of magnitude.

cs.SI↗

arXiv2025

Proton radioactivity in deformed nuclei with microscopic optical potential: A novel angular-dependent emission mechanism in the nanosecond-lived $^{149}$Lu

We present a theoretical description of proton radioactivity in 149Lu, the most oblate deformed proton emitter known, by combining a deformed microscopic optical potential derived from ab initio nuclear matter calculations with the Wentzel-Kramers-Brillouin penetration probabilities and the assault frequency of the emitted proton estimated through a new harmonic-oscillator-inspired scheme. We predict a novel angular-dependent phenomenon unprecedented in spherical proton emitters: the disappearance of classically allowed regions at small polar angles $(\theta\leq 21^\circ)$. Our framework yields a half-life $T_{1/2}=467^{+143}_{-108}$ ns for 149Lu, in excellent agreement within uncertainties with the experimental value $450^{+170}_{-100}$ ns. Deformation analysis rigorously excludes configurations with $|\beta_2|\geq 0.32$. Extensions to 150, 151Lu and their isomers also achieve excellent agreement with experimental half-life data. We further predict 148Lu as another highly oblate $(\beta_2 = -0.166)$ proton emitter with a half-life $T_{1/2}=4.42$ ns. This work validates deformed microscopic optical potentials as a robust predictive tool for drip-line proton emitters and provides quantitative evidence for deformation effects in exotic decays.

nucl-th↗