arXiv subjects

Qi Guo

Publications and source records attributed to Qi Guo.

At least 181 records · Page 10Linked to original sources

arXiv2024

Forklens: Accurate weak-lensing shear measurement with deep learning

Weak gravitational lensing is one of the most important probes of the nature of dark matter and dark energy. In order to extract cosmological information from next-generation weak lensing surveys (e.g., Euclid, Roman, LSST, and CSST) as much as possible, accurate measurements of weak lensing shear are required. There are existing algorithms to measure the weak lensing shear on imaging data, which have been successfully applied in previous surveys. In the meantime, machine learning (ML) has been widely recognized in various astrophysics applications in modeling and observations. In this work, we present a fully deep-learning-based approach to measuring weak lensing shear accurately. Our approach comprises two modules. The first one contains a convolutional neural network (CNN) with two branches for taking galaxy images and point spread function (PSF) simultaneously, and the output of this module includes the galaxy's magnitude, size, and shape. The second module includes a multiple-layer neural network (NN) to calibrate weak-lensing shear measurements. We name the program Forklens and make it publicly available online. Applying Forklens to CSST-like mock images, we achieve consistent accuracy with traditional approaches (such as moment-based measurement and forward model fitting) on the sources with high signal-to-noise ratios (S/N, > 20). For the sources with S/N < 10, Forklens exhibits an $\sim 36\%$ higher Pearson coefficient on galaxy ellipticity measurements. After adopting galaxy weighting, the shear measurements with Forklens deliver accuracy levels to $0.2\%$. The whole procedure of Forklens is automated and costs about $0.7$ milliseconds per galaxy, which is appropriate for adequately taking advantage of the sky coverage and depth of the upcoming weak lensing surveys.

astro-ph.CO↗

arXiv2024

HyperColorization: Propagating spatially sparse noisy spectral clues for reconstructing hyperspectral images

Hyperspectral cameras face challenging spatial-spectral resolution trade-offs and are more affected by shot noise than RGB photos taken over the same total exposure time. Here, we present a colorization algorithm to reconstruct hyperspectral images from a grayscale guide image and spatially sparse spectral clues. We demonstrate that our algorithm generalizes to varying spectral dimensions for hyperspectral images, and show that colorizing in a low-rank space reduces compute time and the impact of shot noise. To enhance robustness, we incorporate guided sampling, edge-aware filtering, and dimensionality estimation techniques. Our method surpasses previous algorithms in various performance metrics, including SSIM, PSNR, GFC, and EMD, which we analyze as metrics for characterizing hyperspectral image quality. Collectively, these findings provide a promising avenue for overcoming the time-space-wavelength resolution trade-off by reconstructing a dense hyperspectral image from samples obtained by whisk or push broom scanners, as well as hybrid spatial-spectral computational imaging systems.

cs.CV↗

arXiv2024

ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs

Automated Program Repair (APR) aims to automatically generate patches for rectifying software bugs. Recent strides in Large Language Models (LLM), such as ChatGPT, have yielded encouraging outcomes in APR, especially within the conversation-driven APR framework. Nevertheless, the efficacy of conversation-driven APR is contingent on the quality of the feedback information. In this paper, we propose ContrastRepair, a novel conversation-based APR approach that augments conversation-driven APR by providing LLMs with contrastive test pairs. A test pair consists of a failing test and a passing test, which offer contrastive feedback to the LLM. Our key insight is to minimize the difference between the generated passing test and the given failing test, which can better isolate the root causes of bugs. By providing informative and specific feedback, ContrastRepair enables the LLM to produce effective bug fixes. The implementation of ContrastRepair is based on the state-of-the-art LLM, ChatGPT, and it iteratively interacts with ChatGPT until plausible patches are generated. We evaluate ContrastRepair on multiple benchmark datasets, including Defects4j, QuixBugs, and HumanEval-Java. The results demonstrate that ContrastRepair significantly outperforms existing methods, achieving a new state-of-the-art in program repair. For instance, among Defects4j 1.2 and 2.0, ContrastRepair correctly repairs 143 out of all 337 bug cases, while the best-performing baseline fixes 124 bugs.

cs.SE↗

arXiv2024

Learning to Retrieve for Job Matching

Web-scale search systems typically tackle the scalability challenge with a two-step paradigm: retrieval and ranking. The retrieval step, also known as candidate selection, often involves extracting standardized entities, creating an inverted index, and performing term matching for retrieval. Such traditional methods require manual and time-consuming development of query models. In this paper, we discuss applying learning-to-retrieve technology to enhance LinkedIns job search and recommendation systems. In the realm of promoted jobs, the key objective is to improve the quality of applicants, thereby delivering value to recruiter customers. To achieve this, we leverage confirmed hire data to construct a graph that evaluates a seeker's qualification for a job, and utilize learned links for retrieval. Our learned model is easy to explain, debug, and adjust. On the other hand, the focus for organic jobs is to optimize seeker engagement. We accomplished this by training embeddings for personalized retrieval, fortified by a set of rules derived from the categorization of member feedback. In addition to a solution based on a conventional inverted index, we developed an on-GPU solution capable of supporting both KNN and term matching efficiently.

cs.IR↗

arXiv2024

Collaborative Large Language Model for Recommender Systems

Recently, there has been growing interest in developing the next-generation recommender systems (RSs) based on pretrained large language models (LLMs). However, the semantic gap between natural language and recommendation tasks is still not well addressed, leading to multiple issues such as spuriously correlated user/item descriptors, ineffective language modeling on user/item data, inefficient recommendations via auto-regression, etc. In this paper, we propose CLLM4Rec, the first generative RS that tightly integrates the LLM paradigm and ID paradigm of RSs, aiming to address the above challenges simultaneously. We first extend the vocabulary of pretrained LLMs with user/item ID tokens to faithfully model user/item collaborative and content semantics. Accordingly, a novel soft+hard prompting strategy is proposed to effectively learn user/item collaborative/content token embeddings via language modeling on RS-specific corpora, where each document is split into a prompt consisting of heterogeneous soft (user/item) tokens and hard (vocab) tokens and a main text consisting of homogeneous item tokens or vocab tokens to facilitate stable and effective language modeling. In addition, a novel mutual regularization strategy is introduced to encourage CLLM4Rec to capture recommendation-related information from noisy user/item content. Finally, we propose a novel recommendation-oriented finetuning strategy for CLLM4Rec, where an item prediction head with multinomial likelihood is added to the pretrained CLLM4Rec backbone to predict hold-out items based on soft+hard prompts established from masked user-item interaction history, where recommendations of multiple items can be generated efficiently without hallucination. Codes are released at https://github.com/yaochenzhu/llm4rec.

cs.IR↗

arXiv2024

HiFAST: an HI data calibration and imaging pipeline for FAST

The Five-hundred-meter Aperture Spherical radio Telescope (FAST) has the largest aperture and a 19-beam L-band receiver, making it powerful for investigating the neutral hydrogen atomic gas (HI) in the universe. We present HiFAST (https://hifast.readthedocs.io), a dedicated, modular, and self-contained calibration and imaging pipeline for processing the HI data of FAST. The pipeline consists of frequency-dependent noise diode calibration, baseline fitting, standing wave removal using an FFT-based method, flux density calibration, stray radiation correction, and gridding to produce data cubes. These modules can be combined as needed to process the data from most FAST observation modes: tracking, drift scanning, On-The-Fly mapping, and most of their variants. With HiFAST, the RMS noises of the calibrated spectra from all 19 beams were only slightly (~ 5%) higher than the theoretical expectation. The results for the extended source M33 and the point sources are consistent with the results from Arecibo. The moment maps (0,1 and 2) of M33 agree well with the results from the Arecibo Galaxy Environment Survey (AGES) with a fractional difference of less than 10%. For a common sample of 221 sources with signal-to-noise ratio S/N >10 from the Arecibo Legacy Fast ALFA (ALFALFA) survey, the mean value of fractional difference in the integrated flux density, $S_{\mathrm{int}}$, between the two datasets is approximately 0.005 %, with a dispersion of 15.4%. Further checks on the integrated flux density of 23 sources with seven observations indicate that the variance in the flux density of the source with luminous objects ($S_\mathrm{int}$ $ > 2.5$ Jy km s$^{-1}$) is less than 5%. Our tests suggest that the FAST telescope, with the efficient, precise, and user-friendly pipeline HiFAST, will yield numerous significant scientific findings in the investigation of the HI in the universe.

astro-ph.GA↗

arXiv2024

Assessing and Understanding Creativity in Large Language Models

In the field of natural language processing, the rapid development of large language model (LLM) has attracted more and more attention. LLMs have shown a high level of creativity in various tasks, but the methods for assessing such creativity are inadequate. The assessment of LLM creativity needs to consider differences from humans, requiring multi-dimensional measurement while balancing accuracy and efficiency. This paper aims to establish an efficient framework for assessing the level of creativity in LLMs. By adapting the modified Torrance Tests of Creative Thinking, the research evaluates the creative performance of various LLMs across 7 tasks, emphasizing 4 criteria including Fluency, Flexibility, Originality, and Elaboration. In this context, we develop a comprehensive dataset of 700 questions for testing and an LLM-based evaluation method. In addition, this study presents a novel analysis of LLMs' responses to diverse prompts and role-play situations. We found that the creativity of LLMs primarily falls short in originality, while excelling in elaboration. Besides, the use of prompts and the role-play settings of the model significantly influence creativity. Additionally, the experimental results also indicate that collaboration among multiple LLMs can enhance originality. Notably, our findings reveal a consensus between human evaluations and LLMs regarding the personality traits that influence creativity. The findings underscore the significant impact of LLM design on creativity and bridges artificial intelligence and human creativity, offering insights into LLMs' creativity and potential applications.

cs.CL↗

arXiv2024

A younger Universe implied by satellite pair correlations from SDSS observations of massive galaxy groups

Many of the satellites of galactic-mass systems such as the Miky Way, Andromeda and Centaurus A show evidence of coherent motions to a larger extent than most of the systems predicted by the standard cosmological model. It is an open question if correlations in satellite orbits are present in systems of different masses. Here , we report an analysis of the kinematics of satellite galaxies around massive galaxy groups. Unlike what is seen in Milky Way analogues, we find an excess of diametrically opposed pairs of satellites that have line-of-sight velocity offsets from the central galaxy of the same sign. This corresponds to a $\pmb{6.0σ}$ ($\pmb{p}$-value $\pmb{=\ 9.9\times10^{-10}}$) detection of non-random satellite motions. Such excess is predicted by up-to-date cosmological simulations but the magnitude of the effect is considerably lower than in observations. The observational data is discrepant at the $\pmb{4.1σ}$ and $\pmb{3.6σ}$ level with the expectations of the Millennium and the Illustris TNG300 cosmological simulations, potentially indicating that massive galaxy groups assembled later in the real Universe. The detection of velocity correlations of satellite galaxies and tension with theoretical predictions is robust against changes in sample selection. Using the largest sample to date, our findings demonstrate that the motions of satellite galaxies represent a challenge to the current cosmological model.

astro-ph.GA↗

arXiv2023

Multi-Modality is All You Need for Transferable Recommender Systems

ID-based Recommender Systems (RecSys), where each item is assigned a unique identifier and subsequently converted into an embedding vector, have dominated the designing of RecSys. Though prevalent, such ID-based paradigm is not suitable for developing transferable RecSys and is also susceptible to the cold-start issue. In this paper, we unleash the boundaries of the ID-based paradigm and propose a Pure Multi-Modality based Recommender system (PMMRec), which relies solely on the multi-modal contents of the items (e.g., texts and images) and learns transition patterns general enough to transfer across domains and platforms. Specifically, we design a plug-and-play framework architecture consisting of multi-modal item encoders, a fusion module, and a user encoder. To align the cross-modal item representations, we propose a novel next-item enhanced cross-modal contrastive learning objective, which is equipped with both inter- and intra-modality negative samples and explicitly incorporates the transition patterns of user behaviors into the item encoders. To ensure the robustness of user representations, we propose a novel noised item detection objective and a robustness-aware contrastive learning objective, which work together to denoise user sequences in a self-supervised manner. PMMRec is designed to be loosely coupled, so after being pre-trained on the source data, each component can be transferred alone, or in conjunction with other components, allowing PMMRec to achieve versatility under both multi-modality and single-modality transfer learning settings. Extensive experiments on 4 sources and 10 target datasets demonstrate that PMMRec surpasses the state-of-the-art recommenders in both recommendation performance and transferability. Our code and dataset is available at: https://github.com/ICDE24/PMMRec.

cs.IR↗

arXiv2023

Merging history of massive galaxies at 3<z<6

The observational data of high redshift galaxies become increasingly abundant, especially since the operation of the James Webb Space Telescope (JWST), which allows us to verify and optimize the galaxy formation model at high redshifts. In this work, we investigate the merging history of massive galaxies at $3 < z < 6$ using a well-developed semi-analytic galaxy formation catalogue. We find that the major merger rate increases with redshift up to 3 and then flattens. The fraction of wet mergers, during which the sum of the cold gas mass is higher than the sum of the stellar mass in two merging galaxies, also increases from $\sim$ 34\% at $z = 0$ to 96\% at $z = 3$. Interestingly, almost all major mergers are wet at $z > 3$ . This can be attributed to the high fraction ($> 50\%$) of cold gas at $z > 3$. In addition, we study some special systems of massive merging galaxies at $3 < z < 6$, including the massive gas-rich major merging systems and extreme dense proto-clusters, and investigate the supermassive black hole-dark matter halo mass relation and dual AGNs. We find that the galaxy formation model reproduces the incidence of those observed massive galaxies, but fails to reproduce the relation between the supermassive black hole mass and the dark matter halo mass at $z \sim 6$. The latter requires more careful estimates of the supermassive black hole masses observationally. Otherwise, it could suggest modifications of the modeling of the supermassive black hole growth at high redshifts.

astro-ph.GA↗

arXiv2023

Exploring the multiband gravitational wave background with a semi-analytic galaxy formation model

An enormous number of compact binary systems, spanning from stellar to supermassive levels, emit substantial gravitational waves during their final evolutionary stages, thereby creating a stochastic gravitational wave background (SGWB). We calculate the merger rates of stellar compact binaries and massive black hole binaries using a semi-analytic galaxy formation model -- Galaxy Assembly with Binary Evolution (GABE) in a unified and self-consistent approach, followed by an estimation of the multi-band SGWB contributed by those systems. We find that the amplitudes of the principal peaks of the SGWB energy density are within one order of magnitude $Ω_{GW} \sim 10^{-9}- 10^{-8}$. This SGWB could easily be detected by the Square Kilometre Array (SKA), as well as planned interferometric detectors, such as the Einstein Telescope (ET) and the Laser Interferometer Space Antenna (LISA). The energy density of this background varies as $Ω_{GW} \propto f^{2/3}$ in SKA band. The shape of the SGWB spectrum in the frequency range $\sim[10^{-4}$,$1]$Hz could allow the LISA to distinguish the black hole seed models. The amplitude of the SGWB from merging stellar binary black holes (BBHs) at $\sim 100$ Hz is approximately 10 and 100 times greater than those from merging binary neutron stars (BNSs) and neutron-star-black-hole (NSBH) mergers, respectively. Note that, since the cosmic star formation rate density predicted by GABE is somewhat lower than observational results by $\sim 0.2$ dex at z < $\sim 2$, the amplitude of the SGWB in the frequency range $\sim[1$, $10^{4}]$ Hz may be underestimated by a similar factor at most.

gr-qc↗

arXiv2023

ANPL: Towards Natural Programming with Interactive Decomposition

Though LLMs are capable of generating plausible programs, it's challenging to interact with the LLMs further to revise the program, especially if the user's specific requirements are different from the initial proposal. In this paper, we introduce ANPL, an interactive programming system that ensures users can always refine the generated code towards their specific programmatic intents via structured decompositions. Borrowing the paradigm of sketching from program synthesis, an ANPL program consists of a set of input-outputs that it must satisfy, a ``sketch'' -- control/data flow expressed in precise code (e.g. Python), and ``holes'' -- sub-modules to be implemented by the LLM specified with natural language. The user revises an ANPL program by either modifying the sketch, changing the language used to describe the holes, or providing additional input-outputs to a particular hole, turning it into a sub-ANPL program that can be solved recursively. This workflow allows the users to offload programming burdens to the LLM as much as possible while retaining the ability to pinpoint and resolve bugs locally, without exposing the rest of the program to the LLM. We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together. Additional evaluations on APPS, HumanEval, and real-world programming tasks have validated that the ANPL framework is applicable to multiple programming domains. We release the ANPL solutions to the ARC tasks as a dataset, providing insights into how humans decompose novel tasks programmatically. See our code at https://iprc-dip.github.io/ANPL/.

cs.PL↗

arXiv2023

Magnon squeezing by two-tone driving of a qubit in cavity-magnon-qubit systems

We propose a scheme for preparing magnon squeezed states in a hybrid cavity-magnon-qubit system. The system consists of a microwave cavity that simultaneously couples to a magnon mode of a macroscopic yttrium-iron-garnet (YIG) sphere via the magnetic-dipole interaction and to a transmon-type superconducting qubit via the electric-dipole interaction. By far detuning from the magnon-qubit system, the microwave cavity is adiabatically eliminated. The magnon mode and the qubit then get effectively coupled via the mediation of virtual photons of the microwave cavity. We show that by driving the qubit with two microwave fields and by appropriately choosing the drive frequencies and strengths, magnonic parametric amplification can be realized, which leads to magnon quadrature squeezing with the noise below vacuum fluctuation. We provide optimal conditions for achieving magnon squeezing, and moderate squeezing can be obtained using currently available parameters. The generated squeezed states are of a magnon mode involving more than $10^{18}$ spins and thus macroscopic quantum states. The work may find promising applications in quantum information processing and high-precision measurements based on magnons and in the study of macroscopic quantum states.

quant-ph↗

arXiv2023

Emergent Communication for Rules Reasoning

Research on emergent communication between deep-learning-based agents has received extensive attention due to its inspiration for linguistics and artificial intelligence. However, previous attempts have hovered around emerging communication under perception-oriented environmental settings, that forces agents to describe low-level perceptual features intra image or symbol contexts. In this work, inspired by the classic human reasoning test (namely Raven's Progressive Matrix), we propose the Reasoning Game, a cognition-oriented environment that encourages agents to reason and communicate high-level rules, rather than perceived low-level contexts. Moreover, we propose 1) an unbiased dataset (namely rule-RAVEN) as a benchmark to avoid overfitting, 2) and a two-stage curriculum agent training method as a baseline for more stable convergence in the Reasoning Game, where contexts and semantics are bilaterally drifting. Experimental results show that, in the Reasoning Game, a semantically stable and compositional language emerges to solve reasoning problems. The emerged language helps agents apply the extracted rules to the generalization of unseen context attributes, and to the transfer between different context attributes or even tasks.

cs.AI↗

arXiv2023

Context Shift Reduction for Offline Meta-Reinforcement Learning

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets. The key insight of CSRO is to minimize the influence of policy in context during both the meta-training and meta-test phases. During meta-training, we design a max-min mutual information representation learning mechanism to diminish the impact of the behavior policy on task representation. In the meta-test phase, we introduce the non-prior context collection strategy to reduce the effect of the exploration policy. Experimental results demonstrate that CSRO significantly reduces the context shift and improves the generalization ability, surpassing previous methods across various challenging domains.

cs.LG↗

arXiv2023

Efficient Symbolic Policy Learning with Differentiable Symbolic Expression

Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the complexity of neural network policies makes it difficult to understand and deploy with limited computational resources. Currently, employing compact symbolic expressions as symbolic policies is a promising strategy to obtain simple and interpretable policies. Previous symbolic policy methods usually involve complex training processes and pre-trained neural network policies, which are inefficient and limit the application of symbolic policies. In this paper, we propose an efficient gradient-based learning method named Efficient Symbolic Policy Learning (ESPL) that learns the symbolic policy from scratch in an end-to-end way. We introduce a symbolic network as the search space and employ a path selector to find the compact symbolic policy. By doing so we represent the policy with a differentiable symbolic expression and train it in an off-policy manner which further improves the efficiency. In addition, in contrast with previous symbolic policies which only work in single-task RL because of complexity, we expand ESPL on meta-RL to generate symbolic policies for unseen tasks. Experimentally, we show that our approach generates symbolic policies with higher performance and greatly improves data efficiency for single-task RL. In meta-RL, we demonstrate that compared with neural network policies the proposed symbolic policy achieves higher performance and efficiency and shows the potential to be interpretable.

cs.LG↗

arXiv2023

Nonrelativistic Limit of Normalized Solutions to a class of nonlinear Dirac equations

In this paper, we investigate the nonrelativistic limit of normalized solutions to a nonlinear Dirac equation as given below: \begin{equation*} \begin{cases} &-i c\sum\limits_{k=1}^3α_k\partial_k u +mc^2 β{u}- Γ* (K |{u}|^κ) K|{u}|^{κ-2}{u}- P |{u}|^{s-2}{u}=ω{u}, \\ &\displaystyle\int_{\mathbb{R}^3}\vert u \vert^2 dx =1. \end{cases} \end{equation*} Here, $c>0$ represents the speed of light, $m > 0$ is the mass of the Dirac particle, $ω\in\mathbb{R}$ emerges as an indeterminate Lagrange multiplier, $Γ$, $K$, $P$ are real-valued function defined on $\mathbb{R}^3$, also known as potential functions. Our research first confirms the presence of normalized solutions to the Dirac equation under high-speed light conditions. We then illustrate that these solutions progress to become the ground states of a system of nonlinear Schrödinger equations with a normalized constraint, exhibiting uniform boundedness and exponential decay irrespective of the light speed. Our results form the first discussion on nonrelativistic limit of normalized solutions to nonlinear Dirac equations. This not only aids in the study of normalized solutions of the nonlinear Schrödinger equations, but also physically explains that the normalized ground states of high-speed particles and low-speed motion particles are consistent.

math.AP↗

arXiv2023

Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study

Code review is an essential activity for ensuring the quality and maintainability of software projects. However, it is a time-consuming and often error-prone task that can significantly impact the development process. Recently, ChatGPT, a cutting-edge language model, has demonstrated impressive performance in various natural language processing tasks, suggesting its potential to automate code review processes. However, it is still unclear how well ChatGPT performs in code review tasks. To fill this gap, in this paper, we conduct the first empirical study to understand the capabilities of ChatGPT in code review tasks, specifically focusing on automated code refinement based on given code reviews. To conduct the study, we select the existing benchmark CodeReview and construct a new code review dataset with high quality. We use CodeReviewer, a state-of-the-art code review tool, as a baseline for comparison with ChatGPT. Our results show that ChatGPT outperforms CodeReviewer in code refinement tasks. Specifically, our results show that ChatGPT achieves higher EM and BLEU scores of 22.78 and 76.44 respectively, while the state-of-the-art method achieves only 15.50 and 62.88 on a high-quality code review dataset. We further identify the root causes for ChatGPT's underperformance and propose several strategies to mitigate these challenges. Our study provides insights into the potential of ChatGPT in automating the code review process, and highlights the potential research directions.

cs.SE↗