arXiv subjects

Heng Li

Publications and source records attributed to Heng Li.

At least 127 records · Page 7Linked to original sources

arXiv2024

Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions

Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. However, current VLN frameworks often rely on static environments and optimal expert supervision, limiting their real-world applicability. To address this, we introduce Human-Aware Vision-and-Language Navigation (HA-VLN), extending traditional VLN by incorporating dynamic human activities and relaxing key assumptions. We propose the Human-Aware 3D (HA3D) simulator, which combines dynamic human activities with the Matterport3D dataset, and the Human-Aware Room-to-Room (HA-R2R) dataset, extending R2R with human activity descriptions. To tackle HA-VLN challenges, we present the Expert-Supervised Cross-Modal (VLN-CM) and Non-Expert-Supervised Decision Transformer (VLN-DT) agents, utilizing cross-modal fusion and diverse training strategies for effective navigation in dynamic human environments. A comprehensive evaluation, including metrics considering human activities, and systematic analysis of HA-VLN's unique challenges, underscores the need for further research to enhance HA-VLN agents' real-world robustness and adaptability. Ultimately, this work provides benchmarks and insights for future research on embodied AI and Sim2Real transfer, paving the way for more realistic and applicable VLN systems in human-populated environments.

cs.AI↗

arXiv2024

Toward a density Corrádi--Hajnal theorem for degenerate hypergraphs

Given an $r$-graph $F$ with $r \ge 2$, let $\mathrm{ex}(n, (t+1) F)$ denote the maximum number of edges in an $n$-vertex $r$-graph with at most $t$ pairwise vertex-disjoint copies of $F$. Extending several old results and complementing prior work [J. Hou, H. Li, X. Liu, L.-T. Yuan, and Y. Zhang. A step towards a general density Corrádi--Hajnal theorem. arXiv:2302.09849, 2023.] on nondegenerate hypergraphs, we initiate a systematic study on $\mathrm{ex}(n, (t+1) F)$ for degenerate hypergraphs $F$. For a broad class of degenerate hypergraphs $F$, we present near-optimal upper bounds for $\mathrm{ex}(n, (t+1) F)$ when $n$ is sufficiently large and $t$ lies in intervals $\left[0, \frac{\varepsilon \cdot \mathrm{ex}(n,F)}{n^{r-1}}\right]$, $\left[\frac{\mathrm{ex}(n,F)}{\varepsilon n^{r-1}}, \varepsilon n \right]$, and $\left[ (1-\varepsilon)\frac{n}{v(F)}, \frac{n}{v(F)} \right]$, where $\varepsilon > 0$ is a constant depending only on $F$. Our results reveal very different structures for extremal constructions across the three intervals, and we provide characterizations of extremal constructions within the first interval. Additionally, for graphs, we offer a characterization of extremal constructions within the second interval. Our proof for the first interval also applies to a special class of nondegenerate hypergraphs, including those with undetermined Turán densities, partially improving a result in [J. Hou, H. Li, X. Liu, L.-T. Yuan, and Y. Zhang. A step towards a general density Corrádi--Hajnal theorem. arXiv:2302.09849, 2023.]

math.CO↗

arXiv2024

Understanding Web Application Workloads and Their Applications: Systematic Literature Review and Characterization

Web applications, accessible via web browsers over the Internet, facilitate complex functionalities without local software installation. In the context of web applications, a workload refers to the number of user requests sent by users or applications to the underlying system. Existing studies have leveraged web application workloads to achieve various objectives, such as workload prediction and auto-scaling. However, these studies are conducted in an ad hoc manner, lacking a systematic understanding of the characteristics of web application workloads. In this study, we first conduct a systematic literature review to identify and analyze existing studies leveraging web application workloads. Our analysis sheds light on their workload utilization, analysis techniques, and high-level objectives. We further systematically analyze the characteristics of the web application workloads identified in the literature review. Our analysis centers on characterizing these workloads at two distinct temporal granularities: daily and weekly. We successfully identify and categorize three daily and three weekly patterns within the workloads. By providing a statistical characterization of these workload patterns, our study highlights the uniqueness of each pattern, paving the way for the development of realistic workload generation and resource provisioning techniques that can benefit a range of applications and research areas.

cs.SE↗

arXiv2024

Early Detection of Performance Regressions by Bridging Local Performance Data and Architectural Models

During software development, developers often make numerous modifications to the software to address existing issues or implement new features. However, certain changes may inadvertently have a detrimental impact on the overall system performance. To ensure that the performance of new software releases does not degrade, existing practices rely on system-level performance testing, such as load testing, or component-level performance testing to detect performance regressions. However, performance testing for the entire system is often expensive and time-consuming, posing challenges to adapting to the rapid release cycles common in modern DevOps practices. System-level performance testing cannot be conducted until the system is fully built and deployed. On the other hand, component-level testing focuses on isolated components, neglecting overall system performance and the impact of system workloads. In this paper, we propose a novel approach to early detection of performance regressions by bridging the local performance data generated by component-level testing and the system-level architectural models. Our approach uses local performance data to identify deviations at the component level, and then propagate these deviations to the architectural model. We then use the architectural model to predict regressions in the performance of the overall system. We evaluate our approach on two open-source benchmark systems and show that it can effectively detect end-to-end system performance regressions from local performance deviations with different intensities and under various system workloads. More importantly, our approach can detect regressions as early as in the development phase, in contrast to existing approaches that require the system to be fully built and deployed. Our approach is lightweight and can complement traditional system performance testing when testing resources are scarce.

cs.SE↗

arXiv2024

HIVE: HIerarchical Volume Encoding for Neural Implicit Surface Reconstruction

Neural implicit surface reconstruction has become a new trend in reconstructing a detailed 3D shape from images. In previous methods, however, the 3D scene is only encoded by the MLPs which do not have an explicit 3D structure. To better represent 3D shapes, we introduce a volume encoding to explicitly encode the spatial information. We further design hierarchical volumes to encode the scene structures in multiple scales. The high-resolution volumes capture the high-frequency geometry details since spatially varying features could be learned from different 3D points, while the low-resolution volumes enforce the spatial consistency to keep the shape smooth since adjacent locations possess the same low-resolution feature. In addition, we adopt a sparse structure to reduce the memory consumption at high-resolution volumes, and two regularization terms to enhance results smoothness. This hierarchical volume encoding could be appended to any implicit surface reconstruction method as a plug-and-play module, and can generate a smooth and clean reconstruction with more details. Superior performance is demonstrated in DTU, EPFL, and BlendedMVS datasets with significant improvement on the standard metrics.

cs.CV↗

arXiv2024

Localizing axial dense emitters based onsingle-helix point spread function andcompressed sensing

Among the approaches in three-dimensional (3D) single molecule localization microscopy, there are several point spread function (PSF) engineering approaches, in which depth information of molecules is encoded in 2D images. Usually,the molecules are excited sparsely in each raw image. The consequence is that the temporal resolution has to be sacrificed. In order to improve temporal resolution and ensure localization accuracy, we propose a method, SH-CS, based on light needle excitation, detection system with single helix-point spread function (SH-PSF), and compressed sensing (CS). Although the SH-CS method still has a limitation about the molecule density, it is suited for relatively dense molecules. For each light needle scanning position, an SH image of excited molecules is processed with CS algorithm to decode their axial information. Simulations demonstrated, for random distributed 1 ~ 15 molecules in depth range of 4 μm, the axial localization accuracy is 12.1 nm ~ 73.5 nm. The feasibility of this method is validated by experimental data.

physics.optics↗

arXiv2024

On the boundedness of degenerate hypergraphs

We investigate the impact of a high-degree vertex in Turán problems for degenerate hypergraphs (including graphs). We say an $r$-graph $F$ is bounded if there exist constants $α, β>0$ such that for large $n$, every $n$-vertex $F$-free $r$-graph with a vertex of degree at least $α\binom{n-1}{r-1}$ has fewer than $(1-β) \cdot \mathrm{ex}(n,F)$ edges. The boundedness property is crucial for recent works~\cite{HHLLYZ23a,DHLY24} that aim to extend the classical Hajnal--Szemerédi Theorem and the anti-Ramsey theorems of Erdős--Simonovits--Sós. We show that many well-studied degenerate hypergraphs, such as all even cycles, most complete bipartite graphs, and the expansion of most complete bipartite graphs, are bounded. In addition, to prove the boundedness of the expansion of complete bipartite graphs, we introduce and solve a Zarankiewicz-type problem for $3$-graphs, strengthening a theorem by Kostochka--Mubayi--Verstraëte~\cite{KMV15}.

math.CO↗

arXiv2024

Exploring gene content with pangene graphs

Motivation: The gene content regulates the biology of an organism. It varies between species and between individuals of the same species. Although tools have been developed to identify gene content changes in bacterial genomes, none is applicable to collections of large eukaryotic genomes such as the human pangenome. Results: We developed pangene, a computational tool to identify gene orientation, gene order and gene copy-number changes in a collection of genomes. Pangene aligns a set of input protein sequences to the genomes, resolves redundancies between protein sequences and constructs a gene graph with each genome represented as a walk in the graph. It additionally finds subgraphs, which we call bibubbles, that capture gene content changes. Applied to the human pangenome, pangene identifies known gene-level variations and reveals complex haplotypes that are not well studied before. Pangene also works with high-quality bacterial pangenome and reports similar numbers of core and accessory genes in comparison to existing tools. Availability and implementation: Source code at https://github.com/lh3/pangene; pre-built pangene graphs can be downloaded from https://zenodo.org/records/8118576 and visualized at https://pangene.bioinweb.org

q-bio.GN↗

arXiv2024

Wrangling Data Issues to be Wrangled: Literature Review, Taxonomy, and Industry Case Study

Data quality is vital for user experience in products reliant on data. As solutions for data quality problems, researchers have developed various taxonomies for different types of issues. However, although some of the existing taxonomies are near-comprehensive, the over-complexity has limited their actionability in data issue solution development. Hence, recent researchers issued new sets of data issue categories that are more concise for better usability. Although more concise, modern data issue labeling's over-catering to the solution systems may sometimes cause the taxonomy to be not mutually exclusive. Consequently, different categories sometimes overlap in determining the issue types, or the same categories share different definitions across research. This hinders solution development and confounds issue detection. Therefore, based on observations from a literature review and feedback from our industry partner, we propose a comprehensive taxonomy of data quality issues from two distinct dimensions: the attribute dimension represents the intrinsic characteristics and the outcome dimension that indicates the manifestation of the issues. With the categories redefined, we labeled the reported data issues in our industry partner's data warehouse. The labeled issues provide us with a general idea of the distributions of each type of problem and which types of issues require the most effort and care to deal with. Our work aims to address a widely generalizable taxonomy rule in modern data quality issue engineering and helps practitioners and researchers understand their data issues and estimate the efforts required for issue fixing.

cs.DB↗

arXiv2024

Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?

Recent advancements in pre-trained large foundation models (LFM) have yielded significant breakthroughs across various domains, including natural language processing and computer vision. These models have been particularly impactful in the domain of medical diagnostic tasks. With abundant unlabeled data, an LFM has been developed for fundus images using the Vision Transformer (VIT) and a self-supervised learning framework. This LFM has shown promising performance in fundus disease diagnosis across multiple datasets. On the other hand, deep learning models have long been challenged by dataset quality issues, such as image quality and dataset bias. To investigate the influence of data quality on LFM, we conducted explorations in two fundus diagnosis tasks using datasets of varying quality. Specifically, we explored the following questions: Is LFM more robust to image quality? Is LFM affected by dataset bias? Can fine-tuning techniques alleviate these effects? Our investigation found that LFM exhibits greater resilience to dataset quality issues, including image quality and dataset bias, compared to typical convolutional networks. Furthermore, we discovered that overall fine-tuning is an effective adapter for LFM to mitigate the impact of dataset quality issues.

eess.IV↗

arXiv2024

Hindered settling of log-normally distributed particulate suspensions: theoretical models vs. Stokesian simulations

Settling velocity statistics for dilute, non-Brownian suspensions of polydisperse spheres having a log-normal size distribution are analysed by Stokesian Dynamics, as a function of the total volume fraction and width of the size distribution. Several hundred instantaneous configurations are averaged to obtain reliable statistics. Average velocities for each particle class are compared to the models proposed by Batchelor, Richardson & Zaki, Davis & Gecol, and Masliyah-Lockett-Bassoon (MLB). Batchelor's model is shown to give reasonably accurate predictions when the volume fraction is within 5%. Because of its complexity, this model is however hardly used in practice, so lower-order models are needed. We found that while the other hindered settling models can give reasonably accurate predictions of the velocity of the largest particles, all of them overestimate - in certain cases by a large margin - the velocity of the smaller particles. By computing the fluid-particle velocity slip for each particle class and using Batchelor's model, we explain why predicting the lower tail of the particle size distribution is challenging, and propose possible avenues for model improvement. The analysis of velocity fluctuations suggest quantitative similarities between velocity fluctuations in monodisperse and polydisperse suspensions.

physics.flu-dyn↗

arXiv2024

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data. In this paper, we introduce a more realistic attack scenario where victims collect data from multiple sources, and attackers cannot access the complete training data. We refer to this scenario as data-constrained backdoor attacks. In such cases, previous attack methods suffer from severe efficiency degradation due to the entanglement between benign and poisoning features during the backdoor injection process. To tackle this problem, we introduce three CLIP-based technologies from two distinct streams: Clean Feature Suppression and Poisoning Feature Augmentation.effective solution for data-constrained backdoor attacks. The results demonstrate remarkable improvements, with some settings achieving over 100% improvement compared to existing attacks in data-constrained scenarios. Code is available at https://github.com/sunh1113/Efficient-backdoor-attacks-for-deep-neural-networks-in-real-world-scenarios

cs.CR↗

arXiv2024

On the Model Update Strategies for Supervised Learning in AIOps Solutions

AIOps (Artificial Intelligence for IT Operations) solutions leverage the massive data produced during the operation of large-scale systems and machine learning models to assist software engineers in their system operations. As operation data produced in the field are constantly evolving due to factors such as the changing operational environment and user base, the models in AIOps solutions need to be constantly maintained after deployment. While prior works focus on innovative modeling techniques to improve the performance of AIOps models before releasing them into the field, when and how to update AIOps models remain an under-investigated topic. In this work, we performed a case study on three large-scale public operation data and empirically assessed five different types of model update strategies for supervised learning regarding their performance, updating cost, and stability. We observed that active model update strategies (e.g., periodical retraining, concept drift guided retraining, time-based model ensembles, and online learning) achieve better and more stable performance than a stationary model. Particularly, applying sophisticated model update strategies could provide better performance, efficiency, and stability than simply retraining AIOps models periodically. In addition, we observed that, although some update strategies can save model training time, they significantly sacrifice model testing time, which could hinder their applications in AIOps solutions where the operation data arrive at high pace and volume and where immediate inferences are required. Our findings highlight that practitioners should consider the evolution of operation data and actively maintain AIOps models over time. Our observations can also guide researchers and practitioners in investigating more efficient and effective model update strategies that fit in the context of AIOps.

cs.SE↗

arXiv2024

Characterizing and Classifying Developer Forum Posts with their Intentions

With the rapid growth of the developer community, the amount of posts on online technical forums has been growing rapidly, which poses difficulties for users to filter useful posts and find important information. Tags provide a concise feature dimension for users to locate their interested posts and for search engines to index the most relevant posts according to the queries. However, most tags are only focused on the technical perspective (e.g., program language, platform, tool). In most cases, forum posts in online developer communities reveal the author's intentions to solve a problem, ask for advice, share information, etc. The modeling of the intentions of posts can provide an extra dimension to the current tag taxonomy. By referencing previous studies and learning from industrial perspectives, we create a refined taxonomy for the intentions of technical forum posts. Through manual labeling and analysis on a sampled post dataset extracted from online forums, we understand the relevance between the constitution of posts (code, error messages) and their intentions. Furthermore, inspired by our manual study, we design a pre-trained transformer-based model to automatically predict post intentions. The best variant of our intention prediction framework, which achieves a Micro F1-score of 0.589, Top 1-3 accuracy of 62.6% to 87.8%, and an average AUC of 0.787, outperforms the state-of-the-art baseline approach. Our characterization and automated classification of forum posts regarding their intentions may help forum maintainers or third-party tool developers improve the organization and retrieval of posts on technical forums. We have released our annotated dataset and codes in our supplementary material package.

cs.SE↗

arXiv2024

Impact of Extensions on Browser Performance: An Empirical Study on Google Chrome

Web browsers have been used widely by users to conduct various online activities, such as information seeking or online shopping. To improve user experience and extend the functionality of browsers, practitioners provide mechanisms to allow users to install third-party-provided plugins (i.e., extensions) on their browsers. However, little is known about the performance implications caused by such extensions. In this paper, we conduct an empirical study to understand the impact of extensions on the user-perceived performance (i.e., energy consumption and page load time) of Google Chrome, the most popular browser. We study a total of 72 representative extensions from 11 categories (e.g., Developer Tools and Sports). We observe that browser performance can be negatively impacted by the use of extensions, even when the extensions are used in unintended circumstances (e.g., when logging into an extension is not granted but required, or when an extension is not used for designated websites). We also identify a set of factors that significantly influence the performance impact of extensions, such as code complexity and privacy practices (i.e., collection of user data) adopted by the extensions. Based on our empirical observations, we provide recommendations for developers and users to mitigate the performance impact of browser extensions, such as conducting performance testing and optimization for unintended usage scenarios of extensions, or adhering to proper usage practices of extensions (e.g., logging into an extension when required).

cs.PF↗

arXiv2024

Detecting Refactoring Commits in Machine Learning Python Projects: A Machine Learning-Based Approach

Refactoring enhances software quality without altering its functional behaviors. Understanding the refactoring activities of developers is crucial to improving software maintainability. With the increasing use of machine learning (ML) libraries and frameworks, maximizing their maintainability is crucial. Due to the data-driven nature of ML projects, they often undergo different refactoring operations (e.g., data manipulation), for which existing refactoring tools lack ML-specific detection capabilities. Furthermore, a large number of ML libraries are written in Python, which has limited tools for refactoring detection. PyRef, a rule-based and state-of-the-art tool for Python refactoring detection, can identify 11 types of refactoring operations. In comparison, Rminer can detect 99 types of refactoring for Java projects. We introduce MLRefScanner, a prototype tool that applies machine-learning techniques to detect refactoring commits in ML Python projects. MLRefScanner identifies commits with both ML-specific and general refactoring operations. Evaluating MLRefScanner on 199 ML projects demonstrates its superior performance compared to state-of-the-art approaches, achieving an overall 94% precision and 82% recall. Combining it with PyRef further boosts performance to 95% precision and 99% recall. Our study highlights the potential of ML-driven approaches in detecting refactoring across diverse programming languages and technical domains, addressing the limitations of rule-based detection methods.

cs.SE↗

arXiv2024

On the Effectiveness of Log Representation for Log-based Anomaly Detection

Logs are an essential source of information for people to understand the running status of a software system. Due to the evolving modern software architecture and maintenance methods, more research efforts have been devoted to automated log analysis. In particular, machine learning (ML) has been widely used in log analysis tasks. In ML-based log analysis tasks, converting textual log data into numerical feature vectors is a critical and indispensable step. However, the impact of using different log representation techniques on the performance of the downstream models is not clear, which limits researchers and practitioners' opportunities of choosing the optimal log representation techniques in their automated log analysis workflows. Therefore, this work investigates and compares the commonly adopted log representation techniques from previous log analysis research. Particularly, we select six log representation techniques and evaluate them with seven ML models and four public log datasets (i.e., HDFS, BGL, Spirit and Thunderbird) in the context of log-based anomaly detection. We also examine the impacts of the log parsing process and the different feature aggregation approaches when they are employed with log representation techniques. From the experiments, we provide some heuristic guidelines for future researchers and developers to follow when designing an automated log analysis workflow. We believe our comprehensive comparison of log representation techniques can help researchers and practitioners better understand the characteristics of different log representation techniques and provide them with guidance for selecting the most suitable ones for their ML-based log analysis workflow.

cs.SE↗

arXiv2024

OCC-VO: Dense Mapping via 3D Occupancy-Based Visual Odometry for Autonomous Driving

Visual Odometry (VO) plays a pivotal role in autonomous systems, with a principal challenge being the lack of depth information in camera images. This paper introduces OCC-VO, a novel framework that capitalizes on recent advances in deep learning to transform 2D camera images into 3D semantic occupancy, thereby circumventing the traditional need for concurrent estimation of ego poses and landmark locations. Within this framework, we utilize the TPV-Former to convert surround view cameras' images into 3D semantic occupancy. Addressing the challenges presented by this transformation, we have specifically tailored a pose estimation and mapping algorithm that incorporates Semantic Label Filter, Dynamic Object Filter, and finally, utilizes Voxel PFilter for maintaining a consistent global semantic map. Evaluations on the Occ3D-nuScenes not only showcase a 20.6% improvement in Success Ratio and a 29.6% enhancement in trajectory accuracy against ORB-SLAM3, but also emphasize our ability to construct a comprehensive map. Our implementation is open-sourced and available at: https://github.com/USTCLH/OCC-VO.

cs.RO↗