Searcharxiv⌕ Search

arXiv subjects

Jun Yin

Publications and source records attributed to Jun Yin.

At least 91 records · Page 5Linked to original sources
arXiv2024

Lite-SAM Is Actually What You Need for Segment Everything

This paper introduces Lite-SAM, an efficient end-to-end solution for the SegEvery task designed to reduce computational costs and redundancy. Lite-SAM is composed of four main components: a streamlined CNN-Transformer hybrid encoder (LiteViT), an automated prompt proposal network (AutoPPN), a traditional prompt encoder, and a mask decoder. All these components are integrated within the SAM framework. Our LiteViT, a high-performance lightweight backbone network, has only 1.16M parameters, which is a 23% reduction compared to the lightest existing backbone network Shufflenet. We also introduce AutoPPN, an innovative end-to-end method for prompt boxes and points generation. This is an improvement over traditional grid search sampling methods, and its unique design allows for easy integration into any SAM series algorithm, extending its usability. we have thoroughly benchmarked Lite-SAM across a plethora of both public and private datasets. The evaluation encompassed a broad spectrum of universal metrics, including the number of parameters, SegEvery execution time, and accuracy. The findings reveal that Lite-SAM, operating with a lean 4.2M parameters, significantly outpaces its counterparts, demonstrating performance improvements of 43x, 31x, 20x, 21x, and 1.6x over SAM, MobileSAM, Edge-SAM, EfficientViT-SAM, and MobileSAM-v2 respectively, all the while maintaining competitive accuracy. This underscores Lite-SAM's prowess in achieving an optimal equilibrium between performance and precision, thereby setting a new state-of-the-art(SOTA) benchmark in the domain.

cs.CV↗
arXiv2024

ACCO: Automated Causal CNN Scheduling Optimizer for Real-Time Edge Accelerators

Spatio-Temporal Convolutional Neural Networks (ST-CNN) allow extending CNN capabilities from image processing to consecutive temporal-pattern recognition. Generally, state-of-the-art (SotA) ST-CNNs inflate the feature maps and weights from well-known CNN backbones to represent the additional time dimension. However, edge computing applications would suffer tremendously from such large computation or memory overhead. Fortunately, the overlapping nature of ST-CNN enables various optimizations, such as the dilated causal convolution structure and Depth-First (DF) layer fusion to reuse the computation between time steps and CNN sliding windows, respectively. Yet, no hardware-aware approach has been proposed that jointly explores the optimal strategy from a scheduling as well as a hardware point of view. To this end, we present ACCO, an automated optimizer that explores efficient Causal CNN transformation and DF scheduling for ST-CNNs on edge hardware accelerators. By cost-modeling the computation and data movement on the accelerator architecture, ACCO automatically selects the best scheduling strategy for the given hardware-algorithm target. Compared to the fixed dilated causal structure, ST-CNNs with ACCO reach an ~8.4x better Energy-Delay-Product. Meanwhile, ACCO improves ~20% in layer-fusion optimals compared to the SotA DF exploration toolchain. When jointly optimizing ST-CNN on the temporal and spatial dimension, ACCO's scheduling outcomes are on average 19x faster and 37x more energy-efficient than spatial DF schemes.

eess.SP↗
arXiv2024

DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities

Vulnerability detection is a critical problem in software security and attracts growing attention both from academia and industry. Traditionally, software security is safeguarded by designated rule-based detectors that heavily rely on empirical expertise, requiring tremendous effort from software experts to generate rule repositories for large code corpus. Recent advances in deep learning, especially Graph Neural Networks (GNN), have uncovered the feasibility of automatic detection of a wide range of software vulnerabilities. However, prior learning-based works only break programs down into a sequence of word tokens for extracting contextual features of codes, or apply GNN largely on homogeneous graph representation (e.g., AST) without discerning complex types of underlying program entities (e.g., methods, variables). In this work, we are one of the first to explore heterogeneous graph representation in the form of Code Property Graph and adapt a well-known heterogeneous graph network with a dual-supervisor structure for the corresponding graph learning task. Using the prototype built, we have conducted extensive experiments on both synthetic datasets and real-world projects. Compared with the state-of-the-art baselines, the results demonstrate promising effectiveness in this research direction in terms of vulnerability detection performance (average F1 improvements over 10\% in real-world projects) and transferability from C/C++ to other programming languages (average F1 improvements over 11%).

cs.SE↗
arXiv2024

Strength and Sensitivity of Land-Atmosphere Interaction

The land-atmosphere coupling strength has been defined as the percentage of precipitation variability explained by the variation of soil moisture in the Global Land-Atmosphere Coupling Experiment (GLACE). While it is useful to identify global hotspots of land-atmosphere interaction, this coupling strength is different from coupling sensitivity, which directly quantifies how precipitation generation responds to the perturbation of soil moisture and is essential for our understanding of the global water cycle. To disentangle these two quantities, here we theoretically explore the relationships among coupling strength, sensitivity, and soil moisture variances. We use climate model outputs to show that the largest soil moisture variances are located in the transitional climate zones and the variations of soil moisture largely account for the geographical patterns of coupling hotspots. The coupling sensitivity is not necessarily low in non-hotspot regions, which could impose great impacts on the development of extreme climate events. We therefore call for more research attention on coupling sensitivity to improve our understanding of the climate system.

physics.ao-ph↗
arXiv2024

An Artificial Intelligence (AI) workflow for catalyst design and optimization

In the pursuit of novel catalyst development to address pressing environmental concerns and energy demand, conventional design and optimization methods often fall short due to the complexity and vastness of the catalyst parameter space. The advent of Machine Learning (ML) has ushered in a new era in the field of catalyst optimization, offering potential solutions to the shortcomings of traditional techniques. However, existing methods fail to effectively harness the wealth of information contained within the burgeoning body of scientific literature on catalyst synthesis. To address this gap, this study proposes an innovative Artificial Intelligence (AI) workflow that integrates Large Language Models (LLMs), Bayesian optimization, and an active learning loop to expedite and enhance catalyst optimization. Our methodology combines advanced language understanding with robust optimization strategies, effectively translating knowledge extracted from diverse literature into actionable parameters for practical experimentation and optimization. In this article, we demonstrate the application of this AI workflow in the optimization of catalyst synthesis for ammonia production. The results underscore the workflow's ability to streamline the catalyst development process, offering a swift, resource-efficient, and high-precision alternative to conventional methods.

physics.chem-ph↗
arXiv2024

Chirality tuning and reversing with resonant phase-change metasurfaces

Dynamic control of circular dichroism in photonic structures is critically important for compact spectrometers, stereoscopic displays, and information processing exploiting multiple degrees of freedom. Metasurfaces can help miniaturize chiral devices but only produce static and limited chiral responses. While external stimuli are able to tune resonances, their modulations are often weak, and reversing continuously the sign of circular dichroism is extremely challenging. Here, we demonstrate dynamically tunable chiral response of resonant metasurfaces supporting chiral bound states in the continuum combining them with phase-change materials. Phase transition between amorphous and crystalline phases allows to control chiral response and vary chirality rapidly from -0.947 to +0.958 backward and forward via chirality continuum. Our demonstrations underpin the rapid development of chiral photonics and its applications.

physics.optics↗
arXiv2023

Band Gap Renormalization at Different Symmetry Points in Perovskites

Using ultrafast broad-band transient absorption (TA) spectroscopy of photo-excited MAPbBr3 thin films with probe continua in the visible and the mid-to-deep-UV ranges, we capture the ultrafast gap renormalization at the fundamental gap situated at the R symmetry point of the Brillouin Zone (BZ) and a higher energy gap at the M point. Global Lifetime analysis, Lifetime density distribution and spectral trace fitting analysis are applied to extract quantitative information. Our work confirms the similarity of the energy gap renormalization at both symmetry points, which rises within the instrument response function (IRF, ~250 fs) and decays in ~400-600 fs times, and an energy red-shift of ~90-150 meV. The ability to monitor different high symmetry points in photoexcited perovskites opens exciting prospects into the characterization of materials, which can be extended to a larger class of materials.

cond-mat.mtrl-sci↗
arXiv2023

The Clumpy Structure Of Five Star-bursting Dwarf Galaxies In The MaNGA Survey

The star-forming clumps in star-bursting dwarf galaxies provide valuable insights into the understanding of the evolution of dwarf galaxies. In this paper, we focus on five star-bursting dwarf galaxies featuring off-centered clumps in the Mapping Nearby Galaxies at Apache Point Observatory (MaNGA) survey. Using the stellar population synthesis software FADO, we obtain the spatially-resolved distribution of the star formation history, which allows us to construct the $g$-band images of the five galaxies at different ages. These images can help us to probe the evolution of the morphological structures of these galaxies. While images of stellar population older than 1 Gyr are typically smooth, images of stellar population younger than 1 Gyr reveal significant clumps, including multiple clumps which appear at different locations and even different ages. To study the evolutionary connections of these five galaxies to other dwarf galaxies before their star-forming clumps appear, we construct the images of the stellar populations older than three age nodes, and define them to be the images of the "host" galaxies. We find that the properties such as the central surface brightness and the effective radii of the hosts of the five galaxies are in between those of dwarf ellipticals (dEs) and dwarf irregulars (dIrrs), with two clearly more similar to dEs and one more similar to dIrrs. Among the five galaxies, 8257-3704 is particularly interesting, as it shows a previous starburst event that is not quite visible from its $gri$ image, but only visible from images of the stellar population at a few hundred million years. The star-forming clump associated with this event may have appeared at around 600 Myr and disappeared at around 40 Myr.

astro-ph.GA↗
arXiv2023

Detecting subtle macroscopic changes in a finite temperature classical scalar field with machine learning

The ability to detect macroscopic changes is important for probing the behaviors of experimental many-body systems from the classical to the quantum realm. Although abrupt changes near phase boundaries can easily be detected, subtle macroscopic changes are much more difficult to detect as the changes can be obscured by noise. In this study, as a toy model for detecting subtle macroscopic changes in many-body systems, we try to differentiate scalar field samples at varying temperatures. We compare different methods for making such differentiations, from physics method, statistics method, to AI method. Our finding suggests that the AI method outperforms both the statistical method and the physics method in its sensitivity. Our result provides a proof-of-concept that AI can potentially detect macroscopic changes in many-body systems that elude physical measures.

cond-mat.stat-mech↗
arXiv2023

Bulk universality and quantum unique ergodicity for random band matrices in high dimensions

We consider Hermitian random band matrices $H=(h_{xy})$ on the $d$-dimensional lattice $(\mathbb Z/L \mathbb Z)^d$, where the entries $h_{xy}=\overline h_{yx}$ are independent centered complex Gaussian random variables with variances $s_{xy}=\mathbb E|h_{xy}|^2$. The variance matrix $S=(s_{xy})$ has a banded profile so that $s_{xy}$ is negligible if $|x-y|$ exceeds the band width $W$. For dimensions $d\ge 7$, we prove the bulk eigenvalue universality of $H$ under the condition $W \gg L^{95/(d+95)}$. Assuming that $W\geq L^ε$ for a small constant $ε>0$, we also prove the quantum unique ergodicity for the bulk eigenvectors of $H$ and a sharp local law for the Green's function $G(z)=(H-z)^{-1}$ up to ${\mathrm{Im}} \, z \gg W^{-5}L^{5-d}$. The local law implies that the bulk eigenvector entries of $H$ are of order ${\mathrm{O}}(W^{-5/2}L^{-d/2+5/2})$ with high probability.

math.PR↗
arXiv2023

Linking the Metallicity Enrichment History to the Star Formation History: An SFH-regulated Chemical Evolution Model and Its Implications for the Gas Cycling Process

The metallicity enrichment history (MEH) of a galaxy is determined by its star formation history (SFH) and the gas cycling process. In this paper, we construct a chemical evolution model that is regulated by the SFH of the system. In this SFH-regulated model, the evolution of all other variables, including the MEH, can be determined by the SFH. We test this model on six locally isolated dwarf galaxies covering three dwarf types that were observed by the Local Cosmology from Isolated Dwarfs (LCID) project. The SFHs and MEHs of these LCID galaxies have been measured from the deep color-magnitude diagrams that are down to the main sequence turn-offs stars. With simple assumptions of the star formation law and the mass-dependent outflows, our SFH-regulated model successfully reproduces the MEHs of all six LCID galaxies from their SFHs, with only one free parameter, the wind efficiency $η\sim 1.0$, for all six galaxies. This model provides a physically motivated link that directly connects the SFH and MEH of a galaxy, which will be useful to accommodate into the state-of-the-art stellar population synthesis models to help relieve the nuisance of the heavy degeneracy between the ages and metallicities of the stellar populations.

astro-ph.GA↗
arXiv2023

Exploiting Spatial-temporal Data for Sleep Stage Classification via Hypergraph Learning

Sleep stage classification is crucial for detecting patients' health conditions. Existing models, which mainly use Convolutional Neural Networks (CNN) for modelling Euclidean data and Graph Convolution Networks (GNN) for modelling non-Euclidean data, are unable to consider the heterogeneity and interactivity of multimodal data as well as the spatial-temporal correlation simultaneously, which hinders a further improvement of classification performance. In this paper, we propose a dynamic learning framework STHL, which introduces hypergraph to encode spatial-temporal data for sleep stage classification. Hypergraphs can construct multi-modal/multi-type data instead of using simple pairwise between two subjects. STHL creates spatial and temporal hyperedges separately to build node correlations, then it conducts type-specific hypergraph learning process to encode the attributes into the embedding space. Extensive experiments show that our proposed STHL outperforms the state-of-the-art models in sleep stage classification tasks.

cs.LG↗
arXiv2023

Few Shot Rationale Generation using Self-Training with Dual Teachers

Self-rationalizing models that also generate a free-text explanation for their predicted labels are an important tool to build trustworthy AI applications. Since generating explanations for annotated labels is a laborious and costly pro cess, recent models rely on large pretrained language models (PLMs) as their backbone and few-shot learning. In this work we explore a self-training approach leveraging both labeled and unlabeled data to further improve few-shot models, under the assumption that neither human written rationales nor annotated task labels are available at scale. We introduce a novel dual-teacher learning framework, which learns two specialized teacher models for task prediction and rationalization using self-training and distills their knowledge into a multi-tasking student model that can jointly generate the task label and rationale. Furthermore, we formulate a new loss function, Masked Label Regularization (MLR) which promotes explanations to be strongly conditioned on predicted labels. Evaluation on three public datasets demonstrate that the proposed methods are effective in modeling task labels and generating faithful rationales.

cs.CL↗
arXiv2023

Nonlinearities of Penman and Penman-Monteith Equations across Multiple Timescales

The nonlinear Penman and Penman-Monteith equations, widely used for estimating surface evapotranspiration at regional and global scales, were derived from turbulent transport of heat fluxes and thus apply to subhourly scale. However, these equations have been directly applied with hydrometeorological variables averaged at longer time intervals, leading to biases due to their nonlinearities. To address this problem, we used global eddy covariance flux data and Taylor expanded Penman and Penman-Monteith equations to explore their nonlinear components and the biases associated with the timescales mismatch. We found relatively small biases when applying Penman equation at longer timescale, in which the biases in equilibrium evapotranspiration mainly stem from the temperature-radiation covariance, whereas the biases in evapotranspiration due to drying power of air primarily come from the higher-order terms. Most of these biases can be corrected by linear regressions of first-order approximations. For Penman-Monteith equations, the corresponding biases are relatively larger but can be significantly reduced when daytime median stomatal conductance is used along with the first-order approximation of Penman-Monteith equation, suggesting the importance of diurnal variation of latent heat fluxes. The nonlinearity explored here serves as a reminder of the mismatched timescales for applying Penman and Penman-Monteith equations.

physics.geo-ph↗
arXiv2023

Adaptive Graph Convolutional Subspace Clustering

Spectral-type subspace clustering algorithms have shown excellent performance in many subspace clustering applications. The existing spectral-type subspace clustering algorithms either focus on designing constraints for the reconstruction coefficient matrix or feature extraction methods for finding latent features of original data samples. In this paper, inspired by graph convolutional networks, we use the graph convolution technique to develop a feature extraction method and a coefficient matrix constraint simultaneously. And the graph-convolutional operator is updated iteratively and adaptively in our proposed algorithm. Hence, we call the proposed method adaptive graph convolutional subspace clustering (AGCSC). We claim that by using AGCSC, the aggregated feature representation of original data samples is suitable for subspace clustering, and the coefficient matrix could reveal the subspace structure of the original data set more faithfully. Finally, plenty of subspace clustering experiments prove our conclusions and show that AGCSC outperforms some related methods as well as some deep models.

cs.LG↗
arXiv2023

Nonequilibrium fluctuations of global warming

While the warming trends of the Earth's mean temperature are evident at climatological scales, the local temperature at shorter timescales are highly fluctuating. In this letter we show that the probabilities of such fluctuations are characterized by a special symmetry typical of systems out of equilibrium. Their nearly universal properties are linked to the fluctuation theorem and reveal that the progressive warming is accompanied by growing asymmetry of temperature distributions. These statistics allow us to project the global temperature variability in the near future, in line with predictions from climate models, providing valuable information about future extremes.

physics.geo-ph↗
arXiv2023

Eigenstate Thermalization Hypothesis for Generalized Wigner Matrices

In this paper, we extend results of Eigenvector Thermalization to the case of generalized Wigner matrices. Analytically, the central quantity of interest here are multiresolvent traces, such as $Λ_A:= \frac{1}{N} \text{Tr }{ GAGA}$. In the case of Wigner matrices, as in \cite{cipolloni-erdos-schroder-2021}, one can form a self-consistent equation for a single $Λ_A$. There are multiple difficulties extending this logic to the case of general covariances. The correlation structure prevents us from deriving a self-consistent equation for a single matrix $A$; this is due to the introduction of new terms that are quite distinct from the form of $Λ_A$. We find a way around this by carefully splitting these new terms and writing them as sums of $Λ_B$, for matrices $B$ obtained by modifying $A$ using the covariance matrix. The result is a system of self-consistent equations relating families of deterministic matrices. Our main effort in this work is to derive and analyze this system of self-consistent equations.

math.PR↗