Searcharxiv⌕ Search

arXiv subjects

Jing Hu

Publications and source records attributed to Jing Hu.

At least 55 records · Page 3Linked to original sources
arXiv2024

Bidirectional skip-frame prediction for video anomaly detection with intra-domain disparity-driven attention

With the widespread deployment of video surveillance devices and the demand for intelligent system development, video anomaly detection (VAD) has become an important part of constructing intelligent surveillance systems. Expanding the discriminative boundary between normal and abnormal events to enhance performance is the common goal and challenge of VAD. To address this problem, we propose a Bidirectional Skip-frame Prediction (BiSP) network based on a dual-stream autoencoder, from the perspective of learning the intra-domain disparity between different features. The BiSP skips frames in the training phase to achieve the forward and backward frame prediction respectively, and in the testing phase, it utilizes bidirectional consecutive frames to co-predict the same intermediate frames, thus expanding the degree of disparity between normal and abnormal events. The BiSP designs the variance channel attention and context spatial attention from the perspectives of movement patterns and object scales, respectively, thus ensuring the maximization of the disparity between normal and abnormal in the feature extraction and delivery with different dimensions. Extensive experiments from four benchmark datasets demonstrate the effectiveness of the proposed BiSP, which substantially outperforms state-of-the-art competing methods.

cs.CV↗
arXiv2024

Three-dimensional non-reciprocal transport in photonic topological heterostructure of arbitrary shape

Electromagnetic wave propagation in three-dimensional space typically suffers omnidirectional scattering when encountering obstacles. In this study, we employed Chern vectors to construct a topological heterostructure, where large-volume non-reciprocal topological transport in three-dimension is achieved. The shape of the cross-section in the heterostructure can be arbitrary designed, and we experimentally observed the distinctive cross-shaped field pattern transport, non-reciprocal energy harvesting, and most importantly, the remarkable ability of electromagnetic wave to traverse obstacles and abrupt structure changes without encountering reflections in 3D space.

physics.optics↗
arXiv2024

HelixFold-Multimer: Elevating Protein Complex Structure Prediction to New Heights

While monomer protein structure prediction tools boast impressive accuracy, the prediction of protein complex structures remains a daunting challenge in the field. This challenge is particularly pronounced in scenarios involving complexes with protein chains from different species, such as antigen-antibody interactions, where accuracy often falls short. Limited by the accuracy of complex prediction, tasks based on precise protein-protein interaction analysis also face obstacles. In this report, we highlight the ongoing advancements of our protein complex structure prediction model, HelixFold-Multimer, underscoring its enhanced performance. HelixFold-Multimer provides precise predictions for diverse protein complex structures, especially in therapeutic protein interactions. Notably, HelixFold-Multimer achieves remarkable success in antigen-antibody and peptide-protein structure prediction, greatly surpassing AlphaFold 3. HelixFold-Multimer is now available for public use on the PaddleHelix platform, offering both a general version and an antigen-antibody version. Researchers can conveniently access and utilize this service for their development needs.

q-bio.BM↗
arXiv2024

In-context Autoencoder for Context Compression in a Large Language Model

We propose the In-context Autoencoder (ICAE), leveraging the power of a large language model (LLM) to compress a long context into short compact memory slots that can be directly conditioned on by the LLM for various purposes. ICAE is first pretrained using both autoencoding and language modeling objectives on massive text data, enabling it to generate memory slots that accurately and comprehensively represent the original context. Then, it is fine-tuned on instruction data for producing desirable responses to various prompts. Experiments demonstrate that our lightweight ICAE, introducing about 1% additional parameters, effectively achieves $4\times$ context compression based on Llama, offering advantages in both improved latency and GPU memory cost during inference, and showing an interesting insight in memorization as well as potential for scalability. These promising results imply a novel perspective on the connection between working memory in cognitive science and representation learning in LLMs, revealing ICAE's significant implications in addressing the long context problem and suggesting further research in LLM context management. Our data, code and models are available at https://github.com/getao/icae.

cs.CL↗
arXiv2024

MetaSD: A Unified Framework for Scalable Downscaling of Meteorological Variables in Diverse Situations

Addressing complex meteorological processes at a fine spatial resolution requires substantial computational resources. To accelerate meteorological simulations, researchers have utilized neural networks to downscale meteorological variables from low-resolution simulations. Despite notable advancements, contemporary cutting-edge downscaling algorithms tailored to specific variables. Addressing meteorological variables in isolation overlooks their interconnectedness, leading to an incomplete understanding of atmospheric dynamics. Additionally, the laborious processes of data collection, annotation, and computational resources required for individual variable downscaling are significant hurdles. Given the limited versatility of existing models across different meteorological variables and their failure to account for inter-variable relationships, this paper proposes a unified downscaling approach leveraging meta-learning. This framework aims to facilitate the downscaling of diverse meteorological variables derived from various numerical models and spatiotemporal scales. Trained at variables consisted of temperature, wind, surface pressure and total precipitation from ERA5 and GFS, the proposed method can be extended to downscale convective precipitation, potential energy, height, humidity and ozone from CFS, S2S and CMIP6 at different spatiotemporal scales, which demonstrating its capability to capture the interconnections among diverse variables. Our approach represents the initial effort to create a generalized downscaling model. Experimental evidence demonstrates that the proposed model outperforms existing top downscaling methods in both quantitative and qualitative assessments.

physics.ao-ph↗
arXiv2024

Spin-resolved counting statistics as a sensitive probe of spin correlation in transport through a quantum dot spin valve

We investigate the noise in spin transport through a single quantum dot (QD) tunnel coupled to ferromagnetic electrodes with noncollinear magnetizations. Based on a spin-resolved quantum master equation, auto- and cross-correlations of spin-resolved currents are analyzed to reveal the underlying spin transport dynamics and characteristics for various polarizations. We find the currents of majority and minority spins could be strongly autocorrelated despite uncorrelated charge transfer. The interplay between tunnel coupling and the Coulomb interaction gives rise to an exchange magnetic field, leading to the precession of the accumulated spin in the QD. It strongly suppresses the bunching of spin tunneling events and results in a unique double-peak structure in the noise of the net spin current. The spin autocorrelation is found to be susceptible to magnetization alignments, which may serve as a sensitive tool to measure the magnetization directions between the ferromagnetic electrodes.

cond-mat.mes-hall↗
arXiv2024

UMedNeRF: Uncertainty-aware Single View Volumetric Rendering for Medical Neural Radiance Fields

In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies. Compared with X-ray images, CT images can provide more information, including multi-planar slices and three-dimensional structures for clinical diagnosis. However, CT imaging requires patients to be exposed to large doses of ionizing radiation for a long time, which may cause irreversible physical harm. In this paper, we propose an Uncertainty-aware MedNeRF (UMedNeRF) network based on generated radiation fields. The network can learn a continuous representation of CT projections from 2D X-ray images by obtaining the internal structure and depth information and using adaptive loss weights to ensure the quality of the generated images. Our model is trained on publicly available knee and chest datasets, and we show the results of CT projection rendering with a single X-ray and compare our method with other methods based on generated radiation fields.

eess.IV↗
arXiv2024

Efficient Image Super-Resolution via Symmetric Visual Attention Network

An important development direction in the Single-Image Super-Resolution (SISR) algorithms is to improve the efficiency of the algorithms. Recently, efficient Super-Resolution (SR) research focuses on reducing model complexity and improving efficiency through improved deep small kernel convolution, leading to a small receptive field. The large receptive field obtained by large kernel convolution can significantly improve image quality, but the computational cost is too high. To improve the reconstruction details of efficient super-resolution reconstruction, we propose a Symmetric Visual Attention Network (SVAN) by applying large receptive fields. The SVAN decomposes a large kernel convolution into three different combinations of convolution operations and combines them with an attention mechanism to form a Symmetric Large Kernel Attention Block (SLKAB), which forms a symmetric attention block with a bottleneck structure by the size of the receptive field in the convolution combination to extract depth features effectively as the basic component of the SVAN. Our network gets a large receptive field while minimizing the number of parameters and improving the perceptual ability of the model. The experimental results show that the proposed SVAN can obtain high-quality super-resolution reconstruction results using only about 30% of the parameters of existing SOTA methods.

cs.CV↗
arXiv2023

Extensible Prompts for Language Models on Zero-shot Language Style Customization

We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL). X-Prompt instructs an LLM with not only NL but also an extensible vocabulary of imaginary words. Registering new imaginary words allows us to instruct the LLM to comprehend concepts that are difficult to describe with NL words, thereby making a prompt more descriptive. Also, these imaginary words are designed to be out-of-distribution (OOD) robust so that they can be (re)used like NL words in various prompts, distinguishing X-Prompt from soft prompt that is for fitting in-distribution data. We propose context-augmented learning (CAL) to learn imaginary words for general usability, enabling them to work properly in OOD (unseen) prompts. We experiment X-Prompt for zero-shot language style customization as a case study. The promising results of X-Prompt demonstrate its potential to facilitate advanced interaction beyond the natural language interface, bridging the communication gap between humans and LLMs.

cs.CL↗
arXiv2023

KDE-Based Coarse-graining of Semicrystalline Systems with Correlated Three-body Intramolecular Interaction

We present an extension to the iterative Boltzmann inversion method to generate coarse-grained models with three-body intramolecular potentials that can reproduce correlations in structural distribution functions. The coarse-grained structural distribution functions are computed using kernel density estimates to produce analytically differentiable distribution functions with controllable smoothening via the kernel bandwidth parameters. Bicubic interpolation is used to accurately interpolate the three-body potentials trained by the method. To demonstrate this new approach, a coarse-grained model of polyethylene is constructed in which each bead represents an ethylene monomer. The resulting model reproduces the radial density function as well as the joint probability distribution of bond-length and bond-angles sampled from target atomistic simulations with only a 10% increase in the computational cost compared to models with independent bond-length and bond-angle potentials. Analysis of the predicted crystallization kinetics of the model developed by the new approach reveals that the bandwidth parameters can be tuned to accelerate the modeling of polymer crystallization. Specifically, computing target RDF with larger bandwidth slows down the secondary crystallization, and increasing the bandwidth in $θ$-direction of bond-length and bond-angle distribution reduces the primary crystallization rate.

physics.comp-ph↗
arXiv2023

Controlling Neural Style Transfer with Deep Reinforcement Learning

Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters. In this paper, we propose the first deep Reinforcement Learning (RL) based architecture that splits one-step style transfer into a step-wise process for the NST task. Our RL-based method tends to preserve more details and structures of the content image in early steps, and synthesize more style patterns in later steps. It is a user-easily-controlled style-transfer method. Additionally, as our RL-based model performs the stylization progressively, it is lightweight and has lower computational complexity than existing one-step Deep Learning (DL) based models. Experimental results demonstrate the effectiveness and robustness of our method.

cs.CV↗
arXiv2023

Investigating full-heavy tetraquarks composed of $cc\bar{c}\bar{b}$ and $bb\bar{b}\bar{c}$

The full-heavy tetraquarks $cc\bar{c}\bar{b}$ and $bb\bar{b}\bar{c}$ are systematically investigated within the chiral quark model. The meson-meson structure, diquark-antidiquark structure and K-structure are considered in this work. There is no bound state for $cc\bar{c}\bar{b}$ and $bb\bar{b}\bar{c}$ systems in $ IJ^{P}=00^{+},01^{+}$ and $ 02^{+}$ channels. However, for $cc\bar{c}\bar{b}$ system, three possible resonance states with energy of $ 10079~{\rm MeV} $, $ 10081~{\rm MeV} $ and $ 10177~{\rm MeV} $ are found in $ IJ^{P}=00^{+},01^{+}$ and $ 02^{+}$, respectively, and their decay width $ Γ$ are $6.7-8.4~{\rm MeV} $, $1.4-7.2~{\rm MeV} $ and $9.1-11.1~{\rm MeV} $. For $bb\bar{b}\bar{c}$ system, there also exist three possible resonance states with energy of $ 16474~{\rm MeV} $, $ 16474~{\rm MeV} $ and $ 16541~{\rm MeV} $ in $ IJ^{P}=00^{+},01^{+}$ and $ 02^{+}$, respectively, and the decay widths $ Γ$ of them are $2.2-6.1~{\rm MeV} $, $2.2-6.9~{\rm MeV} $ and $5.3-8.5~{\rm MeV} $. $bc\bar{c}\bar{c}$ and $cb\bar{b}\bar{b}$ systems will have the same results as $cc\bar{c}\bar{b}$ and $bb\bar{b}\bar{c}$, respectively. These full-heavy resonance states are worthy to be searched in the future experiments.

hep-ph↗
arXiv2023

Computing the Rate-Distortion Function of Gray-Wyner System

In this paper, the rate-distortion theory of the Gray-Wyner lossy source coding system is investigated. For the case of jointly Gaussian distributed sources, we establish an expression for the rate-distortion function under the constraint of quadratic distortion. Using the proposed rate-distortion function, any corner point on the rate-distortion region can be conveniently calculated. We take Wyner's common information as an example and provide a general and simple method to solve this problem. Through the analysis of the rate-distortion function, the rate on each layer and covariance matrix of auxiliary random variables and the sources are also presented in this paper.

cs.IT↗
arXiv2023

Linking Unserved Energy to Weather Regimes

The integration of renewable energy sources into power systems is expected to increase significantly in the coming decades. This can result in critical situations related to the strong variability in space and time of weather patterns. During these critical situations the power system experiences a structural shortage of energy across multiple time steps and regions, leading to Energy Not Served (ENS) events. Our research explores the relationship between six weather regimes that describe the large scale atmospheric flow and ENS events in Europe by simulating future power systems. Our results indicate that most regions have a specific weather regime that leads to the highest number of ENS events. However, ENS events can still occur during any weather regime, but with a lower probability. In particular, our findings show that ENS events in western and central European countries often coincide with either the positive Scandinavian Blocking (SB+), characterised by cold air penetrating Europe under calm weather conditions from north-eastern regions, or North Atlantic Oscillation (NAO+) weather regime, characterised by westerly flow and cold air in the southern half of Europe. Additionally, we found that the relative impact of one of these regimes reaches a peak 10 days before ENS events in these countries. In Scandinavian and Baltic countries, on the other hand, our results indicate that the relative prevalence of the negative Atlantic Ridge (AR-) weather regime is higher during and leading up to the ENS event.

physics.soc-ph↗
arXiv2023

DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design

Thermal issue is a major concern in 3D integrated circuit (IC) design. Thermal optimization of 3D IC often requires massive expensive PDE simulations. Neural network-based thermal prediction models can perform real-time prediction for many unseen new designs. However, existing works either solve 2D temperature fields only or do not generalize well to new designs with unseen design configurations (e.g., heat sources and boundary conditions). In this paper, for the first time, we propose DeepOHeat, a physics-aware operator learning framework to predict the temperature field of a family of heat equations with multiple parametric or non-parametric design configurations. This framework learns a functional map from the function space of multiple key PDE configurations (e.g., boundary conditions, power maps, heat transfer coefficients) to the function space of the corresponding solution (i.e., temperature fields), enabling fast thermal analysis and optimization by changing key design configurations (rather than just some parameters). We test DeepOHeat on some industrial design cases and compare it against Celsius 3D from Cadence Design Systems. Our results show that, for the unseen testing cases, a well-trained DeepOHeat can produce accurate results with $1000\times$ to $300000\times$ speedup.

cs.LG↗
arXiv2023

Dynamic Combination of Heterogeneous Models for Hierarchical Time Series

We introduce a framework to dynamically combine heterogeneous models called \texttt{DYCHEM}, which forecasts a set of time series that are related through an aggregation hierarchy. Different types of forecasting models can be employed as individual ``experts'' so that each model is tailored to the nature of the corresponding time series. \texttt{DYCHEM} learns hierarchical structures during the training stage to help generalize better across all the time series being modeled and also mitigates coherency issues that arise due to constraints imposed by the hierarchy. To improve the reliability of forecasts, we construct quantile estimations based on the point forecasts obtained from combined heterogeneous models. The resulting quantile forecasts are coherent and independent of the choice of forecasting models. We conduct a comprehensive evaluation of both point and quantile forecasts for hierarchical time series (HTS), including public data and user records from a large financial software company. In general, our method is robust, adaptive to datasets with different properties, and highly configurable and efficient for large-scale forecasting pipelines.

cs.LG↗
arXiv2022

Intrinsic triple degeneracy point bounded by nodal surfaces in chiral photonic crystal

In periodic systems, band degeneracies are usually protected and classified by spatial symmetries. However, the Gamma point at zero-frequency of a photonic system is an intrinsic degeneracy due to the polarization degree of freedom of electromagnetic waves. We show here that in chiral photonic crystals, such an intrinsic degeneracy node carries +(-)2 chiral topological charge and the topological characters is the same as a spin-1 Weyl point manifested as a triple degeneracy of two linear propagating bands intersecting a flat band representing the electrostatic solution. Such an intrinsic triple degeneracy point (TDP) at Gamma is usually buried in bulk band projections and the topological charge at photonic zero-frequency has never been observed. Here, by imposing space-group screw symmetry to the chiral photonic crystal, the Brillouin zone boundary is transformed into an oppositely charged nodal surface enclosing the Gamma point. The emergent Fermi-arcs on sample surface are then forced to connect the bulk band projections of these topological singularities, revealing the embedded non-trivial topology.

cond-mat.mes-hall↗
arXiv2022

Experimental realization of chiral Landau levels in two-dimensional Dirac cone systems with inhomogeneous effective mass

Chiral zeroth Landau levels are topologically protected bulk states that give rise to chiral anomaly. Previous discussions on such chiral Landau levels are based on three-dimensional Weyl degeneracies. Their realizations using two-dimensional Dirac point systems, being more promising for future applications, were never reported before. Here we propose a theoretical and experimental scheme for realizing chiral Landau levels in a photonic system. By introducing an inhomogeneous effective mass through breaking local parity inversion symmetries, the zeroth-order chiral Landau levels with one-way propagation characteristics are experimentally observed. In addition, the robust transport of the chiral zeroth mode against defects in the system is experimentally tested. Our system provides a new pathway for the realization of chiral Landau levels in two-dimensional Dirac systems, and may potentially be applied in device designs utilizing the transport robustness.

cond-mat.mtrl-sci↗