arXiv subjects

Zhen Liu

Publications and source records attributed to Zhen Liu.

At least 127 records · Page 7Linked to original sources

arXiv2024

Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining

Graph mining is an important area in data mining and machine learning that involves extracting valuable information from graph-structured data. In recent years, significant progress has been made in this field through the development of graph neural networks (GNNs). However, GNNs are still deficient in generalizing to diverse graph data. Aiming to this issue, Large Language Models (LLMs) could provide new solutions for graph mining tasks with their superior semantic understanding. In this review, we systematically review the combination and application techniques of LLMs and GNNs and present a novel taxonomy for research in this interdisciplinary field, which involves three main categories: GNN-driving-LLM, LLM-driving-GNN, and GNN-LLM-co-driving. Within this framework, we reveal the capabilities of LLMs in enhancing graph feature extraction as well as improving the effectiveness of downstream tasks such as node classification, link prediction, and community detection. Although LLMs have demonstrated their great potential in handling graph-structured data, their high computational requirements and complexity remain challenges. Future research needs to continue to explore how to efficiently fuse LLMs and GNNs to achieve more powerful graph learning and reasoning capabilities and provide new impetus for the development of graph mining techniques.

cs.LG↗

arXiv2024

Ultralight dark matter detection with levitated ferromagnets

Levitated ferromagnets act as ultraprecise magnetometers, which can exhibit high quality factors due to their excellent isolation from the environment. These instruments can be utilized in searches for ultralight dark matter candidates, such as axionlike dark matter or dark-photon dark matter. In addition to being sensitive to an axion-photon coupling or kinetic mixing, which produce physical magnetic fields, ferromagnets are also sensitive to the effective magnetic field (or "axion wind") produced by an axion-electron coupling. While the dynamics of a levitated ferromagnet in response to a DC magnetic field have been well studied, all of these couplings would produce AC fields. In this work, we study the response of a ferromagnet to an applied AC magnetic field and use these results to project their sensitivity to axion and dark-photon dark matter. We pay special attention to the direction of motion induced by an applied AC field, in particular, whether it precesses around the applied field (similar to an electron spin) or librates in the plane of the field (similar to a compass needle). We show that existing levitated ferromagnet setups can already have comparable sensitivity to an axion-electron coupling as comagnetometer or torsion balance experiments. In addition, future setups can become sensitive probes of axion-electron coupling, dark-photon kinetic mixing, and axion-photon coupling, for ultralight dark matter masses $m_\mathrm{DM}\lesssim\mathrm{feV}$.

hep-ph↗

arXiv2024

FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation

Robots can acquire complex manipulation skills by learning policies from expert demonstrations, which is often known as vision-based imitation learning. Generating policies based on diffusion and flow matching models has been shown to be effective, particularly in robotic manipulation tasks. However, recursion-based approaches are inference inefficient in working from noise distributions to policy distributions, posing a challenging trade-off between efficiency and quality. This motivates us to propose FlowPolicy, a novel framework for fast policy generation based on consistency flow matching and 3D vision. Our approach refines the flow dynamics by normalizing the self-consistency of the velocity field, enabling the model to derive task execution policies in a single inference step. Specifically, FlowPolicy conditions on the observed 3D point cloud, where consistency flow matching directly defines straight-line flows from different time states to the same action space, while simultaneously constraining their velocity values, that is, we approximate the trajectories from noise to robot actions by normalizing the self-consistency of the velocity field within the action space, thus improving the inference efficiency. We validate the effectiveness of FlowPolicy in Adroit and Metaworld, demonstrating a 7$\times$ increase in inference speed while maintaining competitive average success rates compared to state-of-the-art methods. Code is available at https://github.com/zql-kk/FlowPolicy.

cs.RO↗

arXiv2024

Machine-Learning based photon counting for PMT waveforms and its application to the improvement of the energy resolution in large liquid scintillator detectors

Photomultiplier tubes (PMTs) are widely used in particle experiments for photon detection. PMT waveform analysis is crucial for high-precision measurements of the position and energy of incident particles in liquid scintillator (LS) detectors. A key factor contributing to the energy resolution in large liquid scintillator detectors with PMTs is the charge smearing of PMTs. This paper presents a machine-learning-based photon counting method for PMT waveforms and its application to the energy reconstruction, using the JUNO experiment as an example. The results indicate that leveraging the photon counting information from the machine learning model can partially mitigate the impact of PMT charge smearing and lead to a relative 2.0% to 2.8% improvement on the energy resolution in the energy range of [1, 9] MeV.

physics.ins-det↗

arXiv2024

Momentum shift and on-shell constructible massive amplitudes

We construct tree-level amplitude for massive particles using on-shell recursion relations based on two classes of momentum shifts: an all-line transverse shift that deforms momentum by its transverse polarization vector, and a massive BCFW-type shift. We illustrate that these shifts allow us to correctly calculate four-point and five-point amplitudes in massive QED, without an ambiguity associated with the contact terms that may arise from a simple ''gluing'' of lower-point on-shell amplitudes. We discuss various aspects and applicability of the two shifts, including the large-z behavior and complexity scaling. We show that there exists a ''good'' all-line transverse shift for all possible little group configurations of the external particles, which can be extended to a broader class of theories with massive particles such as massive QCD and theories with massive spin-1 particles. The massive BCFW-type shift enjoys more simplicity, but a ''good'' shift does not exist for all the spin states due to the specific choice of spin axis.

hep-ph↗

arXiv2024

Momentum shift and on-shell recursion relation for electroweak theory

We study the All-Line Transverse (ALT) shift which we developed for on-shell recursion of amplitudes for particles of any mass. We discuss the validity of the shift for general theories of spin $\leq$ 1, and illustrate the connection between Ward identity and constructibility for massive spin-1 amplitude under the ALT shift. We apply the shift to the electroweak theory, and various four-point scattering amplitudes among electroweak gauge bosons and fermions are constructed. We show explicitly that the four-point gauge boson contact terms in massive electroweak theory automatically arise after recursive construction, independent of UV completion, and they automatically cancel the terms growing as (energy)$^4$ at high energy. We explore UV completion of the electroweak theory that cancels the remaining (energy)$^2$ terms and impose unitarity requirements to constrain additional couplings. The ALT shift framework allows consistent treatment in dealing with contact term ambiguities for renormalizable massive and massless theories, which we show can be useful in studying real-world amplitudes with massive spinors.

hep-ph↗

arXiv2024

MaDiNet: Mamba Diffusion Network for SAR Target Detection

The fundamental challenge in SAR target detection lies in developing discriminative, efficient, and robust representations of target characteristics within intricate non-cooperative environments. However, accurate target detection is impeded by factors including the sparse distribution and discrete features of the targets, as well as complex background interference. In this study, we propose a \textbf{Ma}mba \textbf{Di}ffusion \textbf{Net}work (MaDiNet) for SAR target detection. Specifically, MaDiNet conceptualizes SAR target detection as the task of generating the position (center coordinates) and size (width and height) of the bounding boxes in the image space. Furthermore, we design a MambaSAR module to capture intricate spatial structural information of targets and enhance the capability of the model to differentiate between targets and complex backgrounds. The experimental results on extensive SAR target detection datasets achieve SOTA, proving the effectiveness of the proposed network. Code is available at \href{https://github.com/JoyeZLearning/MaDiNet}{https://github.com/JoyeZLearning/MaDiNet}.

eess.IV↗

arXiv2024

UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection

Occlusion is a longstanding difficulty that challenges the UAV-based object detection. Many works address this problem by adapting the detection model. However, few of them exploit that the UAV could fundamentally improve detection performance by changing its viewpoint. Active Object Detection (AOD) offers an effective way to achieve this purpose. Through Deep Reinforcement Learning (DRL), AOD endows the UAV with the ability of autonomous path planning to search for the observation that is more conducive to target identification. Unfortunately, there exists no available dataset for developing the UAV AOD method. To fill this gap, we released a UAV's eye view active vision dataset named UEVAVD and hope it can facilitate research on the UAV AOD problem. Additionally, we improve the existing DRL-based AOD method by incorporating the inductive bias when learning the state representation. First, due to the partial observability, we use the gated recurrent unit to extract state representations from the observation sequence instead of the single-view observation. Second, we pre-decompose the scene with the Segment Anything Model (SAM) and filter out the irrelevant information with the derived masks. With these practices, the agent could learn an active viewing policy with better generalization capability. The effectiveness of our innovations is validated by the experiments on the UEVAVD dataset. Our dataset will soon be available at https://github.com/Leo000ooo/UEVAVD_dataset.

cs.CV↗

arXiv2024

HRRPGraphNet: Make HRRPs to Be Graphs for Efficient Target Recognition

High Resolution Range Profiles (HRRP) have become a key area of focus in the domain of Radar Automatic Target Recognition (RATR). Despite the success of deep learning based HRRP recognition, these methods needs a large amount of training samples to generate good performance, which could be a severe challenge under non-cooperative circumstances. Currently, deep learning based models treat HRRP as sequences, which may lead to ignorance of the internal relationship of range cells. This letter introduces HRRPGraphNet, whose pivotal innovation is the transformation of HRRP data into a novel graph structure, utilizing a range cell amplitude(hyphen)based node vector and a range(hyphen)relative adjacency matrix. This graph(hyphen)based approach facilitates both local feature extraction via one(hyphen)dimensional convolution layers, global feature extraction through a graph convolution layer and a attention module. Experiments on the aircraft electromagnetic simulation dataset confirmed HRRPGraphNet superior accuracy and robustness, particularly in limited training sample environments, underscoring the potential of graph(hyphen)driven innovations in HRRP(hyphen)based RATR.

eess.SP↗

arXiv2024

Modeling groundwater levels in California's Central Valley by hierarchical Gaussian process and neural network regression

Modeling groundwater levels continuously across California's Central Valley (CV) hydrological system is challenging due to low-quality well data which is sparsely and noisily sampled across time and space. The lack of consistent well data makes it difficult to evaluate the impact of 2017 and 2019 wet years on CV groundwater following a severe drought during 2012-2015. A novel machine learning method is formulated for modeling groundwater levels by learning from a 3D lithological texture model of the CV aquifer. The proposed formulation performs multivariate regression by combining Gaussian processes (GP) and deep neural networks (DNN). The hierarchical modeling approach constitutes training the DNN to learn a lithologically informed latent space where non-parametric regression with GP is performed. We demonstrate the efficacy of GP-DNN regression for modeling non-stationary features in the well data with fast and reliable uncertainty quantification, as validated to be statistically consistent with the empirical data distribution from 90 blind wells across CV. We show how the model predictions may be used to supplement hydrological understanding of aquifer responses in basins with irregular well data. Our results indicate that on average the 2017 and 2019 wet years in California were largely ineffective in replenishing the groundwater loss caused during previous drought years.

physics.geo-ph↗

arXiv2024

A Survey on Time-Series Pre-Trained Models

Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications. Deep learning models that rely on massive labeled data have been utilized for TSM successfully. However, constructing a large-scale well-labeled dataset is difficult due to data annotation costs. Recently, pre-trained models have gradually attracted attention in the time series domain due to their remarkable performance in computer vision and natural language processing. In this survey, we provide a comprehensive review of Time-Series Pre-Trained Models (TS-PTMs), aiming to guide the understanding, applying, and studying TS-PTMs. Specifically, we first briefly introduce the typical deep learning models employed in TSM. Then, we give an overview of TS-PTMs according to the pre-training techniques. The main categories we explore include supervised, unsupervised, and self-supervised TS-PTMs. Further, extensive experiments involving 27 methods, 434 datasets, and 679 transfer learning scenarios are conducted to analyze the advantages and disadvantages of transfer learning strategies, Transformer-based models, and representative TS-PTMs. Finally, we point out some potential directions of TS-PTMs for future work.

cs.LG↗

arXiv2024

A Light QCD Axion with Hilltop Misalignment

We study the cosmological evolution of a light QCD axion and identify the parameter space to obtain the correct relic dark matter abundance. The axion potential is flattened at the origin, corresponding to the only minimum, while it is unsuppressed at $π$. These potential features arise by assuming a mirror sector with the strong CP phase $\barθ$ shifted by $π$ compared to the SM sector, which allows the mirror axion potential to be tuned against the usual QCD axion potential. Before the QCD phase transition, assuming the mirror sector is decoupled and much colder than the SM thermal bath, the mirror sector potential dominates, causing the axion to initially roll to a temporary minimum at $π$. However, after the QCD phase transition, the potential minimum changes, and the axion relaxes from the newly created "hilltop" near $π$ to the CP-conserving minimum at the origin. As the axion adiabatically tracks this shift in the potential minimum through the QCD phase transition, with non-adiabatic evolution near $π$ and 0, it alters the usual prediction of the dark matter abundance. Consequently, this "hilltop" misalignment mechanism opens new regions of axion parameter space, with the correct relic abundance while still solving the strong CP problem, that could be explored in future experiments.

hep-ph↗

arXiv2024

Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture

The growing Synthetic Aperture Radar (SAR) data has the potential to build a foundation model through Self-Supervised Learning (SSL) methods, which can achieve various SAR Automatic Target Recognition (ATR) tasks with pre-training in large-scale unlabeled data and fine-tuning in small labeled samples. SSL aims to construct supervision signals directly from the data, which minimizes the need for expensive expert annotation and maximizes the use of the expanding data pool for a foundational model. This study investigates an effective SSL method for SAR ATR, which can pave the way for a foundation model in SAR ATR. The primary obstacles faced in SSL for SAR ATR are the small targets in remote sensing and speckle noise in SAR images, corresponding to the SSL approach and signals. To overcome these challenges, we present a novel Joint-Embedding Predictive Architecture for SAR ATR (SAR-JEPA), which leverages local masked patches to predict the multi-scale SAR gradient representations of unseen context. The key aspect of SAR-JEPA is integrating SAR domain features to ensure high-quality self-supervised signals as target features. Besides, we employ local masks and multi-scale features to accommodate the various small targets in remote sensing. By fine-tuning and evaluating our framework on three target recognition datasets (vehicle, ship, and aircraft) with four other datasets as pre-training, we demonstrate its outperformance over other SSL methods and its effectiveness with increasing SAR data. This study showcases the potential of SSL for SAR target recognition across diverse targets, scenes, and sensors.Our codes and weights are available in \url{https://github.com/waterdisappear/SAR-JEPA.

cs.CV↗

arXiv2024

PuzzleAvatar: Assembling 3D Avatars from Personal Albums

Generating personalized 3D avatars is crucial for AR/VR. However, recent text-to-3D methods that generate avatars for celebrities or fictional characters, struggle with everyday people. Methods for faithful reconstruction typically require full-body images in controlled settings. What if a user could just upload their personal "OOTD" (Outfit Of The Day) photo collection and get a faithful avatar in return? The challenge is that such casual photo collections contain diverse poses, challenging viewpoints, cropped views, and occlusion (albeit with a consistent outfit, accessories and hairstyle). We address this novel "Album2Human" task by developing PuzzleAvatar, a novel model that generates a faithful 3D avatar (in a canonical pose) from a personal OOTD album, while bypassing the challenging estimation of body and camera pose. To this end, we fine-tune a foundational vision-language model (VLM) on such photos, encoding the appearance, identity, garments, hairstyles, and accessories of a person into (separate) learned tokens and instilling these cues into the VLM. In effect, we exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar. Importantly, we can customize avatars by simply inter-changing tokens. As a benchmark for this new task, we collect a new dataset, called PuzzleIOI, with 41 subjects in a total of nearly 1K OOTD configurations, in challenging partial photos with paired ground-truth 3D bodies. Evaluation shows that PuzzleAvatar not only has high reconstruction accuracy, outperforming TeCH and MVDreamBooth, but also a unique scalability to album photos, and strong robustness. Our code and data are publicly available for research purpose at https://puzzleavatar.is.tue.mpg.de/

cs.CV↗

arXiv2024

The mutual pulling force of human muscle fibers can treat mild cancer and rhinitis

Muscles can store a large amount of genetic information, and in order to transform humans into computers, we need to start by increasing muscle tension. When people with cancer go on happy trips, some cancers often heal without treatment; Rhinitis can cause blockage of the nostrils, but after running, the nostrils naturally ventilate. Both are related to exercise, and the mystery behind them can treat both conditions. Cancer belongs to systemic diseases, and the eradication method for systemic diseases should start from the entire body system, treat the symptoms and prevent recurrence. This article uses special exercise methods and detailed methods to treat diseases, and finds that treating diseases from the perspective of the human system is indeed effective. This article adopts a comparative experimental method to compare the changes in the body before and after. Through this article, it is concluded that exercise and certain methods can cure mild rhinitis and promote rapid ventilation; Explaining from the perspective of muscle pulling force that older individuals are more prone to developing cellular variant cancer; Enhancing muscle tension in the human body can promote the cure of some cancers

cs.OH↗

arXiv2024

The Philosopher's Stone: Trojaning Plugins of Large Language Models

Open-source Large Language Models (LLMs) have recently gained popularity because of their comparable performance to proprietary LLMs. To efficiently fulfill domain-specialized tasks, open-source LLMs can be refined, without expensive accelerators, using low-rank adapters. However, it is still unknown whether low-rank adapters can be exploited to control LLMs. To address this gap, we demonstrate that an infected adapter can induce, on specific triggers,an LLM to output content defined by an adversary and to even maliciously use tools. To train a Trojan adapter, we propose two novel attacks, POLISHED and FUSION, that improve over prior approaches. POLISHED uses a superior LLM to align naïvely poisoned data based on our insight that it can better inject poisoning knowledge during training. In contrast, FUSION leverages a novel over-poisoning procedure to transform a benign adapter into a malicious one by magnifying the attention between trigger and target in model weights. In our experiments, we first conduct two case studies to demonstrate that a compromised LLM agent can use malware to control the system (e.g., a LLM-driven robot) or to launch a spear-phishing attack. Then, in terms of targeted misinformation, we show that our attacks provide higher attack effectiveness than the existing baseline and, for the purpose of attracting downloads, preserve or improve the adapter's utility. Finally, we designed and evaluated three potential defenses. However, none proved entirely effective in safeguarding against our attacks, highlighting the need for more robust defenses supporting a secure LLM supply chain.

cs.CR↗

arXiv2024

Large Language Models Synergize with Automated Machine Learning

Recently, program synthesis driven by large language models (LLMs) has become increasingly popular. However, program synthesis for machine learning (ML) tasks still poses significant challenges. This paper explores a novel form of program synthesis, targeting ML programs, by combining LLMs and automated machine learning (autoML). Specifically, our goal is to fully automate the generation and optimization of the code of the entire ML workflow, from data preparation to modeling and post-processing, utilizing only textual descriptions of the ML tasks. To manage the length and diversity of ML programs, we propose to break each ML program into smaller, manageable parts. Each part is generated separately by the LLM, with careful consideration of their compatibilities. To ensure compatibilities, we design a testing technique for ML programs. Unlike traditional program synthesis, which typically relies on binary evaluations (i.e., correct or incorrect), evaluating ML programs necessitates more than just binary judgments. Our approach automates the numerical evaluation and optimization of these programs, selecting the best candidates through autoML techniques. In experiments across various ML tasks, our method outperforms existing methods in 10 out of 12 tasks for generating ML programs. In addition, autoML significantly improves the performance of the generated ML programs. In experiments, given the textual task description, our method, Text-to-ML, generates the complete and optimized ML program in a fully autonomous process. The implementation of our method is available at https://github.com/JLX0/llm-automl.

cs.SE↗

arXiv2024

Searching for axions with kaon decay at rest

We describe a novel search strategy for axions (or hadronically coupled axion-like particles) in the mass range of $m_a \lesssim 350\,{\rm MeV}$. The search relies on kaon decay at rest, which produces a mono-energetic signal in a large volume detector (e.g.\ a tank of liquid scintillator) from axion decays $a\rightarrow γγ$ or $a\rightarrow e^+e^-$. The decay modes $K^+\to π^+ a$ and $a \to γγ$ are induced by the axion's coupling to gluons, which is generic to any model which addresses the strong CP problem. We recast a recent search from MicroBooNE for $e^+e^-$ pairs, and study prospects at JSNS$^2$ and other near-term facilities. We find that JSNS$^2$ will have world-leading sensitivity to hadronically coupled axions in the mass range of $40\,\mathrm{MeV} \lesssim m_a \lesssim 350\,\mathrm{MeV}$.

hep-ph↗