arXiv subjects

Xiaolong Yu

Publications and source records attributed to Xiaolong Yu.

7 recordsLinked to original sources

arXiv2026

LightSplat: Real-Time High-Fidelity 3D Gaussian SLAM with Loop Closure

SLAM systems based on 3D Gaussian Splatting (3DGS) have recently demonstrated promising reconstruction accuracy for dense 3D scene representations. However, current 3DGS systems struggle to meet the strict demands of real-world deployments due to severe limitations in operational performance and map adaptability. To this end, we propose LightSplat, a hybrid-representation RGB-D SLAM framework. It synergizes local sparse features for robust and fast tracking with a dual-thread backend that progressively constructs dense Gaussian submaps. Crucially, we enable online loop closure through feature-accelerated 3DGS registration, refining overall map consistency through pose graph optimization. Ultimately, LightSplat achieves the online reconstruction of high-fidelity Gaussian map. Extensive experiments on multiple datasets and real-world robotic platform demonstrate that our method achieves near state-of-the-art reconstruction quality and the capability to accommodate practical camera motions, maintaining an average framerate of 8 FPS. Overall, LightSplat provides an efficient and robust foundation for deploying high-fidelity 3DGS in real-world environments.

cs.RO↗

arXiv2026

RESTOR: Automated Test Oracle Generation for RESTful APIs via Reinforcement Learning

Modern REST API testing faces a critical challenge in defining reliable test oracles, particularly in agile industrial environments where formal specifications (e.g., OpenAPI) are frequently missing or outdated, and historical execution logs are unavailable for newly deployed endpoints. In this paper, we present Restor (Reinforcement Enhanced Single-Traffic Oracle generator for REST APIs), a framework that generates executable test assertions from a single observed request-response pair in a black-box setting. Unlike existing approaches that rely on rule-based templates or massive training logs, Restor utilizes a novel data augmentation pipeline to fine-tune a lightweight Large Language Model (LLM) via Group Relative Policy Optimization (GRPO). This training process enables the model to internalize testing "common sense" by optimizing a reward function that jointly encourages: (i) the selection of stable, semantically meaningful fields for validation and the avoidance of dynamic noise (e.g., timestamps or trace IDs); (ii) the generation of robust assertions that withstand logic variations. We evaluate Restor on an industrial dataset comprising over 2,300 API traces across 246 real-world services. Comprehensive experiments demonstrate that Restor significantly outperforms prompt-engineered baselines and generalist models, achieving a superior $F_1$ score of 85.42% in key field identification and increasing the proportion of semantically accurate assertions. Furthermore, deployment in a production CI/CD workflow at ByteDance confirms its practical value: the system raised the adoption rate of automatically generated test cases from 74.1% to over 96%, substantially reducing manual Quality Assurance (QA) effort while ensuring high execution stability.

cs.SE↗

arXiv2025

Convex Hull-based Algebraic Constraint for Visual Quadric SLAM

Using Quadrics as the object representation has the benefits of both generality and closed-form projection derivation between image and world spaces. Although numerous constraints have been proposed for dual quadric reconstruction, we found that many of them are imprecise and provide minimal improvements to localization.After scrutinizing the existing constraints, we introduce a concise yet more precise convex hull-based algebraic constraint for object landmarks, which is applied to object reconstruction, frontend pose estimation, and backend bundle adjustment.This constraint is designed to fully leverage precise semantic segmentation, effectively mitigating mismatches between complex-shaped object contours and dual quadrics.Experiments on public datasets demonstrate that our approach is applicable to both monocular and RGB-D SLAM and achieves improved object mapping and localization than existing quadric SLAM methods. The implementation of our method is available at https://github.com/tiev-tongji/convexhull-based-algebraic-constraint.

cs.CV↗

arXiv2024

Dual sparse training framework: inducing activation map sparsity via Transformed $\ell1$ regularization

Although deep convolutional neural networks have achieved rapid development, it is challenging to widely promote and apply these models on low-power devices, due to computational and storage limitations. To address this issue, researchers have proposed techniques such as model compression, activation sparsity induction, and hardware accelerators. This paper presents a method to induce the sparsity of activation maps based on Transformed $\ell1$ regularization, so as to improve the research in the field of activation sparsity induction. Further, the method is innovatively combined with traditional pruning, constituting a dual sparse training framework. Compared to previous methods, Transformed $\ell1$ can achieve higher sparsity and better adapt to different network structures. Experimental results show that the method achieves improvements by more than 20\% in activation map sparsity on most models and corresponding datasets without compromising the accuracy. Specifically, it achieves a 27.52\% improvement for ResNet18 on the ImageNet dataset, and a 44.04\% improvement for LeNet5 on the MNIST dataset. In addition, the dual sparse training framework can greatly reduce the computational load and provide potential for reducing the required storage during runtime. Specifically, the ResNet18 and ResNet50 models obtained by the dual sparse training framework respectively reduce 81.7\% and 84.13\% of multiplicative floating-point operations, while maintaining accuracy and a low pruning rate.

cs.CV↗

arXiv2022

Frequency dependence of near-surface oceanic kinetic energy from drifter observations and global high-resolution models

The geographical variability, frequency content, and vertical structure of near-surface oceanic kinetic energy (KE) are important for air-sea interaction, marine ecosystems, operational oceanography, pollutant tracking, and interpreting remotely sensed velocity measurements. Here, KE in high-resolution global simulations (HYbrid Coordinate Ocean Model; HYCOM, and Massachusetts Institute of Technology general circulation model; MITgcm), at the sea surface (0 m) and 15 m, are respectively compared with KE from undrogued and drogued surface drifters. Global maps and zonal averages are computed for low-frequency ($<$ 0.5 cpd), near-inertial, diurnal, and semi-diurnal bands. Both models exhibit low-frequency equatorial KE that is low relative to drifter values. HYCOM near-inertial KE is higher than in MITgcm, and closer to drifter values, probably due to more frequently updated atmospheric forcing. HYCOM semi-diurnal KE is lower than in MITgcm, and closer to drifter values, likely due to inclusion of a parameterized topographic internal wave drag. A concurrent tidal harmonic analysis in the diurnal band demonstrates that much of the diurnal flow is non-tidal. We compute a simple proxy of near-surface vertical structure, the ratio of 0 m KE to 0 m KE plus 15 m KE in model outputs, and undrogued KE to undrogued KE plus drogued KE in drifter observations. Over most latitudes and frequency bands, model ratios track the drifter ratios to within error bars. Values of this ratio demonstrate significant vertical structure in all frequency bands except the semidiurnal band. Latitudinal dependence in the ratio is greatest in diurnal and low-frequency bands.

physics.ao-ph↗

arXiv2016

Capacity-achieving and Flicker-free FEC coding scheme for Dimmable Visible Light Communication Based on Polar Codes

Visible light communication (VLC) could provide short-range optical wireless communication together with illumination using LED lighting. However, conventional forward error correction (FEC) codes for reliable communication do not have the features for dimming support and flicker mitigation which are required in VLC for the main functionality of lighting. Therefore, auxiliary coding techniques are usually needed, which eventually reduce the coding efficiency and increase the complexity. In this paper, a polar codes-based FEC coding scheme for dimmable VLC is proposed to increase the coding efficiency and simplify the coding structure. Experimental results show that the proposed scheme has the following advantages: 1) equal probability of 1's and 0's in codewords, which is inherently supporting 50% dimming balance; 2) short run length property (about 90% bits have runs shorter than 5) which can avoid flickers and additional run-length limited line coding; 3) higher coding efficiency about twofold than that of other coding schemes; 4) capacity achieving error correction performance with low-complexity encoding and decoding, which is about 3 dB higher coding gain than that of RS(64,32) in IEEE standard for dimming ratio 50% and about 1 dB higher coding gain than that of LDPC codes for dimming ratio 25% (or 75%).

cs.IT↗

arXiv2014

The influence of $\mathfrak{F_{\mathrm s}}$-quasinormality of subgroups on the structure of finite groups

Let $\frak{F}$ be a class of finite groups. A subgroup $H$ of a finite group $G$ is said to be $\mathfrak{F_{\mathrm s}}$-quasinormal in $G$ if there exists a normal subgroup $T$ of $G$ such that $HT$ is $s$-permutable in $G$ and $(H\cap T)H_G/H_G$ is contained in the $\frak{F}$-hypercenter $Z_\infty^\mathfrak{F}(G/H_G)$ of $G/H_G$. In this paper, we investigate further the influence of $\mathfrak{F_{\mathrm s}}$-quasinormality of some subgroups on the structure of finite groups. New characterization of some classes of finite groups are obtained.

math.GR↗