Search arXiv⌕ Search

arXiv subjects

Zhuo Li

Publications and source records attributed to Zhuo Li.

At least 127 records · Page 7Linked to original sources
arXiv2024

Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of Techniques

The integration of Large Language Models (LLMs) with Graph Representation Learning (GRL) marks a significant evolution in analyzing complex data structures. This collaboration harnesses the sophisticated linguistic capabilities of LLMs to improve the contextual understanding and adaptability of graph models, thereby broadening the scope and potential of GRL. Despite a growing body of research dedicated to integrating LLMs into the graph domain, a comprehensive review that deeply analyzes the core components and operations within these models is notably lacking. Our survey fills this gap by proposing a novel taxonomy that breaks down these models into primary components and operation techniques from a novel technical perspective. We further dissect recent literature into two primary components including knowledge extractors and organizers, and two operation techniques including integration and training stratigies, shedding light on effective model design and training strategies. Additionally, we identify and explore potential future research avenues in this nascent yet underexplored field, proposing paths for continued progress.

cs.LG↗
arXiv2024

Accessing the Host Galaxies of Long Gamma-Ray Bursts with Next-Generation Telescopes

We present a method to estimate the detection expectations of host galaxies of long gamma-ray bursts (LGRBs) in the {\it grizJHKL} bands. It is found that given the same limiting magnitude $m_{grizJHKL,\rm lim}$ in each band, the {\it z} band produces the largest number of overall LGRB hosts and low-mass hosts ($M_\ast\leq10^8$ M$_\odot$) at $m_{grizJHKL,\rm lim}\gtrsim 26$ mag. For the detection of high-redshift LGRB hosts (redshift $\geq5$), it is recommended to prioritize the {\it L} band due to its good performance at both low and high limiting magnitudes. We specifically estimate the expectation of LGRB-host detection with $m_{grizJHKL,\rm lim}=28$ mag, which the James Webb Space Telescope can partially attain. We find that there may exist 116, 259, 277, 439, 266, 294, 274, and 316 LGRB hosts, including 0.54, 31, 28, 143, 12, 20, 14, and 35 low-mass ones in the {\it grizJHKL} bands and 13, 14, 15, 14, and 15 high-redshift ones in the {\it zJHKL} bands, for 15 yr {\it Swift} LGRBs with $S\geq10^{-6}$ erg cm$^{-2}$. The results show that the study of LGRB hosts under next-generation observational conditions holds significant potential, especially for low-mass host studies. However, it appears that deeper sensitivities of galaxy telescopes may not significantly enhance statistical studies of high-redshift hosts. Strategies aimed at increasing the number of distant LGRB hosts may require the expansion of high-redshift LGRB detection.

astro-ph.HE↗
arXiv2024

GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting

We introduce a novel large-scale scene reconstruction benchmark using the newly developed 3D representation approach, Gaussian Splatting, on our expansive U-Scene dataset. U-Scene encompasses over one and a half square kilometres, featuring a comprehensive RGB dataset coupled with LiDAR ground truth. For data acquisition, we employed the Matrix 300 drone equipped with the high-accuracy Zenmuse L1 LiDAR, enabling precise rooftop data collection. This dataset, offers a unique blend of urban and academic environments for advanced spatial analysis convers more than 1.5 km$^2$. Our evaluation of U-Scene with Gaussian Splatting includes a detailed analysis across various novel viewpoints. We also juxtapose these results with those derived from our accurate point cloud dataset, highlighting significant differences that underscore the importance of combine multi-modal information

cs.CV↗
arXiv2024

The Effects of Generative AI on Computing Students' Help-Seeking Preferences

Help-seeking is a critical way for students to learn new concepts, acquire new skills, and get unstuck when problem-solving in their computing courses. The recent proliferation of generative AI tools, such as ChatGPT, offers students a new source of help that is always available on-demand. However, it is unclear how this new resource compares to existing help-seeking resources along dimensions of perceived quality, latency, and trustworthiness. In this paper, we investigate the help-seeking preferences and experiences of computing students now that generative AI tools are available to them. We collected survey data (n=47) and conducted interviews (n=8) with computing students. Our results suggest that although these models are being rapidly adopted, they have not yet fully eclipsed traditional help resources. The help-seeking resources that students rely on continue to vary depending on the task and other factors. Finally, we observed preliminary evidence about how help-seeking with generative AI is a skill that needs to be developed, with disproportionate benefits for those who are better able to harness the capabilities of LLMs. We discuss potential implications for integrating generative AI into computing classrooms and the future of help-seeking in the era of generative AI.

cs.HC↗
arXiv2023

Brochosome-inspired binary metastructures for pixel-by-pixel thermal signature control

In nature, nano/micro-structured materials are adopted by various species to generate colors or achieve camouflage. Here, inspired by leafhopper-generated brochosomes, we design binary metastructures composed of pixel twins to achieve pixelated thermal signature control at the microscale. In the infrared range, the pixel twins exhibit distinct emissivities, creating thermal counterparts of '0-1' binary states for storing and displaying information. In the visible range, the engineered surface morphology of the pixel twins enables similar scattering behaviors, rendering the pixel twins visually indistinguishable, which achieves the camouflage of stored information. Compared to the previous work based on plasmonic holographic metasurfaces, the brochosome-like pixel twins are thermally driven, and their structure-enabled functions do not rely on permittivities of any specific material. The unique combination of visible camouflage and infrared display provides a systemic solution to the spatial control of thermal signatures, and has important implications for optical security, anticounterfeiting, and data encryption.

physics.optics↗
arXiv2023

Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features

Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this paper, the flaws of the speaker features inherent in the text-to-speech (TTS) process are analyzed. Differences in the temporal consistency of intra-utterance speaker features arise due to the lack of fine-grained control over speaker features in TTS. Since the speaker representations in TTS are based on speaker embeddings extracted by encoders, the distribution of inter-utterance speaker features differs between synthetic and bonafide speech. Based on these analyzes, an SSD method based on temporal consistency and distribution of speaker features is proposed. On one hand, modeling the temporal consistency of intra-utterance speaker features can aid speech anti-spoofing. On the other hand, distribution differences in inter-utterance speaker features can be utilized for SSD. The proposed method offers low computational complexity and performs well in both cross-dataset and silence trimming scenarios.

eess.AS↗
arXiv2023

The Impact of Silence on Speech Anti-Spoofing

The current speech anti-spoofing countermeasures (CMs) show excellent performance on specific datasets. However, removing the silence of test speech through Voice Activity Detection (VAD) can severely degrade performance. In this paper, the impact of silence on speech anti-spoofing is analyzed. First, the reasons for the impact are explored, including the proportion of silence duration and the content of silence. The proportion of silence duration in spoof speech generated by text-to-speech (TTS) algorithms is lower than that in bonafide speech. And the content of silence generated by different waveform generators varies compared to bonafide speech. Then the impact of silence on model prediction is explored. Even after retraining, the spoof speech generated by neural network based end-to-end TTS algorithms suffers a significant rise in error rates when the silence is removed. To demonstrate the reasons for the impact of silence on CMs, the attention distribution of a CM is visualized through class activation mapping (CAM). Furthermore, the implementation and analysis of the experiments masking silence or non-silence demonstrates the significance of the proportion of silence duration for detecting TTS and the importance of silence content for detecting voice conversion (VC). Based on the experimental results, improving the robustness of CMs against unknown spoofing attacks by masking silence is also proposed. Finally, the attacks on anti-spoofing CMs through concatenating silence, and the mitigation of VAD and silence attack through low-pass filtering are introduced.

eess.AS↗
arXiv2023

On the maximum local mean order of sub-k-trees of a k-tree

For a k-tree T, a generalization of a tree, the local mean order of sub-k-trees of T is the average order of sub-k-trees of T containing a given k-clique. The problem whether the largest local mean order of a tree (i.e., a 1-tree) at a vertex always takes on at a leaf was asked by Jamison in 1984 and was answered by Wagner and Wang in 2016. In 2018, Stephens and Oellermann asked a similar problem: for any k-tree T, does the maximum local mean order of sub-k-trees containing a given k-clique occur at a k-clique that is not a major k-clique of T? In this paper, we give it an affirmative answer.

math.CO↗
arXiv2023

Visible and NIR Image Fusion Algorithm Based on Information Complementarity

Visible and near-infrared(NIR) band sensors provide images that capture complementary spectral radiations from a scene. And the fusion of the visible and NIR image aims at utilizing their spectrum properties to enhance image quality. However, currently visible and NIR fusion algorithms cannot well take advantage of spectrum properties, as well as lack information complementarity, which results in color distortion and artifacts. Therefore, this paper designs a complementary fusion model from the level of physical signals. First, in order to distinguish between noise and useful information, we use two layers of the weight-guided filter and guided filter to obtain texture and edge layers, respectively. Second, to generate the initial visible-NIR complementarity weight map, the difference maps of visible and NIR are filtered by the extend-DoG filter. After that, the significant region of NIR night-time compensation guides the initial complementarity weight map by the arctanI function. Finally, the fusion images can be generated by the complementarity weight maps of visible and NIR images, respectively. The experimental results demonstrate that the proposed algorithm can not only well take advantage of the spectrum properties and the information complementarity, but also avoid color unnatural while maintaining naturalness, which outperforms the state-of-the-art.

cs.CV↗
arXiv2023

ToolCoder: Teach Code Generation Models to use API search tools

Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs for specific contexts. These models may generate APIs that do not meet requirements or refer to non-existent APIs in third-party libraries, especially for lesser-known or private libraries. Inspired by the process of human developers using tools to search APIs, we propose ToolCoder, a novel approach that integrates API search tools with existing models to assist in code generation and API selection. To teach our model to use tools, we introduce an automated data annotation method using ChatGPT to add tool usage information into the source code data and fine-tune code generation models. During inference, we integrate API search tools into the generation process so that our model can automatically use the search tool to get suggestions when selecting an API. Our experimental results demonstrate that ToolCoder exhibits excellent performance and generalization across five public and private library code generation benchmarks, with at least 6.21\% improvement on average pass@1 metrics and 9.64\% improvement on average pass@10 metrics compared to state-of-the-art methods. Furthermore, we show that our relatively small ToolCoder model is comparable to one of the current best models, GPT-3.5, highlighting the potential of incorporating programming tools into the code generation process.

cs.SE↗
arXiv2023

Self-Edit: Fault-Aware Code Editor for Code Generation

Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task. We execute the generated code on the example test case provided in the question and wrap execution results into a supplementary comment. Utilizing this comment as guidance, our fault-aware code editor is employed to correct errors in the generated code. We perform extensive evaluations across two competitive programming datasets with nine different LLMs. Compared to directly generating from LLMs, our approach can improve the average of pass@1 by 89\% on APPS-dev, 31\% on APPS-test, and 48\% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B. Compared to other post-processing methods, our method demonstrates superior accuracy and efficiency.

cs.SE↗
arXiv2023

CodeEditor: Learning to Edit Source Code with Pre-trained Models

Developers often perform repetitive code editing activities for various reasons (e.g., code refactoring) during software development. Pre-trained code editing models have achieved the state-of-the-art (SOTA) results. Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task. Existing pre-training tasks mainly are code infilling tasks (e.g., masked language modeling), which are derived from the natural language processing field and are not designed for automatic code editing. This paper proposes a novel pre-training task specialized in code editing and presents an effective pre-trained code editing model named CodeEditor. Our pre-training task further improves the performance and generalization ability of code editing models. Specifically, we collect lots of real-world code snippets as the ground truth and use a powerful generator to rewrite them into mutated versions. Then, we pre-train our CodeEditor to edit mutated versions into the corresponding ground truth, to learn edit patterns. We conduct experiments on four code editing datasets and evaluate the pre-trained CodeEditor in three settings. (1) In the fine-tuning setting, we train the pre-trained CodeEditor with four datasets and evaluate it on the test data. CodeEditor outperforms the SOTA baselines by 15%, 25.5%, and 9.4% and 26.6% on four datasets. (2) In the few-shot setting, we train the pre-trained CodeEditor with limited data and evaluate it on the test data. CodeEditor substantially performs better than all baselines. (3) In the zero-shot setting, CodeEditor correctly edits 1,113 programs while the SOTA baselines can not work.

cs.SE↗
arXiv2023

Nanodevice-Enabled Near-Field Thermal Radiation between Sub-Wavelength Surfaces

With the continuous advancement of nanotechnology, nanodevices have become crucial components in computing, sensing and energy conversion applications. However, the structures of nanodevices typically possess sub-wavelength dimensions and separations, which pose significant challenges for understanding energy transport phenomena in nanodevices. Here, based on a judiciously designed thermal nanodevice, we report the first measurement of near-field energy transport between two coplanar sub-wavelength structures over temperature bias up to ~190 K. Our experimental results demonstrate a remarkable 20-fold enhancement in heat transfer beyond blackbody radiation. In contrast with the well-established near-field interactions between two semi-infinite bodies, the sub-wavelength confinements in nanodevices lead to the increased polariton scattering and the reduction of supporting modes and therefore a lower heat flow at a given separation. Our work unveils exciting opportunities for the rational design of nanodevices, particularly for on-chip near-field energy transport, with important implications for the development of efficient nanodevices for energy harvesting and thermal management.

physics.optics↗
arXiv2023

Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL

Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games. However, their effectiveness is hindered when applied to continuous control problems due to the challenge of dimensional explosion. In this paper, we present the Soft Decomposed Policy-Critic (SDPC) architecture, which combines soft RL and actor-critic techniques with discrete RL methods to overcome this limitation. SDPC discretizes each action dimension independently and employs a shared critic network to maximize the soft $Q$-function. This novel approach enables SDPC to support two types of policies: decomposed actors that lead to the Soft Decomposed Actor-Critic (SDAC) algorithm, and decomposed $Q$-networks that generate Boltzmann soft exploration policies, resulting in the Soft Decomposed-Critic Q (SDCQ) algorithm. Through extensive experiments, we demonstrate that our proposed approach outperforms state-of-the-art continuous RL algorithms in a variety of continuous control tasks, including Mujoco's Humanoid and Box2d's BipedalWalker. These empirical results validate the effectiveness of the SDPC architecture in addressing the challenges associated with continuous control.

cs.LG↗
arXiv2023

An Empirical Study of Bugs in Quantum Machine Learning Frameworks

Quantum computing has emerged as a promising domain for the machine learning (ML) area, offering significant computational advantages over classical counterparts. With the growing interest in quantum machine learning (QML), ensuring the correctness and robustness of software platforms to develop such QML programs is critical. A necessary step for ensuring the reliability of such platforms is to understand the bugs they typically suffer from. To address this need, this paper presents the first comprehensive study of bugs in QML frameworks. We inspect 391 real-world bugs collected from 22 open-source repositories of nine popular QML frameworks. We find that 1) 28% of the bugs are quantum-specific, such as erroneous unitary matrix implementation, calling for dedicated approaches to find and prevent them; 2) We manually distilled a taxonomy of five symptoms and nine root cause of bugs in QML platforms; 3) We summarized four critical challenges for QML framework developers. The study results provide researchers with insights into how to ensure QML framework quality and present several actionable suggestions for QML framework developers to improve their code quality.

cs.SE↗
arXiv2023

WELL: Applying Bug Detectors to Bug Localization via Weakly Supervised Learning

Bug localization, which is used to help programmers identify the location of bugs in source code, is an essential task in software development. Researchers have already made efforts to harness the powerful deep learning (DL) techniques to automate it. However, training bug localization model is usually challenging because it requires a large quantity of data labeled with the bug's exact location, which is difficult and time-consuming to collect. By contrast, obtaining bug detection data with binary labels of whether there is a bug in the source code is much simpler. This paper proposes a WEakly supervised bug LocaLization (WELL) method, which only uses the bug detection data with binary labels to train a bug localization model. With CodeBERT finetuned on the buggy-or-not binary labeled data, WELL can address bug localization in a weakly supervised manner. The evaluations on three method-level synthetic datasets and one file-level real-world dataset show that WELL is significantly better than the existing SOTA model in typical bug localization tasks such as variable misuse and other programming bugs.

cs.SE↗
arXiv2023

Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases

Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description. However, existing methods only consider the dependency between the entire sentence and the target object, ignoring fine-grained relationships between contexts and non-target ones. In this paper, we extend 3DVG to a more fine-grained and interpretable task, called 3D Phrase Aware Grounding (3DPAG). The 3DPAG task aims to localize the target objects in a 3D scene by explicitly identifying all phrase-related objects and then conducting the reasoning according to contextual phrases. To tackle this problem, we manually labeled about 227K phrase-level annotations using a self-developed platform, from 88K sentences of widely used 3DVG datasets, i.e., Nr3D, Sr3D and ScanRefer. By tapping on our datasets, we can extend previous 3DVG methods to the fine-grained phrase-aware scenario. It is achieved through the proposed novel phrase-object alignment optimization and phrase-specific pre-training, boosting conventional 3DVG performance as well. Extensive results confirm significant improvements, i.e., previous state-of-the-art method achieves 3.9%, 3.5% and 4.6% overall accuracy gains on Nr3D, Sr3D and ScanRefer respectively.

cs.CV↗