Search

Text ranking has witnessed significant advancements, attributed to the utilization of dual-encoder enhanced by Pre-trained Language Models (PLMs). Given the proliferation of available PLMs, selecting the most effective one for a given dataset has become a non-trivial challenge. As a promising alternative to human intuition and brute-force fine-tuning, Transferability Estimation (TE) has emerged as an effective approach to model selection. However, current TE methods are primarily designed for classification tasks, and their estimated transferability may not align well with the objectives of text ranking. To address this challenge, we propose to compute the expected rank as transferability, explicitly reflecting the model's ranking capability. Furthermore, to mitigate anisotropy and incorporate training dynamics, we adaptively scale isotropic sentence embeddings to yield an accurate expected rank score. Our resulting method, Adaptive Ranking Transferability (AiRTran), can effectively capture subtle differences between models. On challenging model selection scenarios across various text ranking datasets, it demonstrates significant improvements over previous classification-oriented TE methods, human intuition, and ChatGPT with minor time consumption., Comment: Accepted by EMNLP 2024 main conference

Per- and polyfluoroalkyl substances (PFAS) are persistent environmental pollutants with known toxicity and bioaccumulation issues. Their widespread industrial use and resistance to degradation have led to global environmental contamination and significant health concerns. While a minority of PFAS have been extensively studied, the toxicity of many PFAS remains poorly understood due to limited direct toxicological data. This study advances the predictive modeling of PFAS toxicity by combining semi-supervised graph convolutional networks (GCNs) with molecular descriptors and fingerprints. We propose a novel approach to enhance the prediction of PFAS binding affinities by isolating molecular fingerprints to construct graphs where then descriptors are set as the node features. This approach specifically captures the structural, physicochemical, and topological features of PFAS without overfitting due to an abundance of features. Unsupervised clustering then identifies representative compounds for detailed binding studies. Our results provide a more accurate ability to estimate PFAS hepatotoxicity to provide guidance in chemical discovery of new PFAS and the development of new safety regulations., Comment: 8 pages, 9 figures, submitted to IEEE BIBM 2024

Generating peptides with desired properties is crucial for drug discovery and biotechnology. Traditional sequence-based and structure-based methods often require extensive datasets, which limits their effectiveness. In this study, we proposed a novel method that utilized autoencoder shaped models to explore the protein embedding space, and generate novel peptide analogs by leveraging protein language models. The proposed method requires only a single sequence of interest, avoiding the need for large datasets. Our results show significant improvements over baseline models in similarity indicators of peptide structures, descriptors and bioactivities. The proposed method validated through Molecular Dynamics simulations on TIGIT inhibitors, demonstrates that our method produces peptide analogs with similar yet distinct properties, highlighting its potential to enhance peptide screening processes.

Material defects (MD) represent a primary challenge affecting product performance and giving rise to safety issues in related products. The rapid and accurate identification and localization of MD constitute crucial research endeavours in addressing contemporary challenges associated with MD. Although conventional non-destructive testing methods such as ultrasonic and X-ray approaches have mitigated issues related to low efficiency in manual inspections, they struggle to meet the diverse requirements of high precision, real-time speed, automation, and intelligence. In recent years, propelled by the swift advancement of machine learning (ML) technologies, particularly exemplified by deep learning, ML has swiftly emerged as the core technology and a prominent research direction for material defect detection (MDD). Through a comprehensive review of the latest literature, we systematically survey the ML techniques applied in MDD into five categories: unsupervised learning, supervised learning, semi-supervised learning, reinforcement learning, and generative learning. We provide a detailed analysis of the main principles and techniques used, together with the advantages and potential challenges associated with these techniques. Furthermore, the survey focuses on the techniques for defect detection in composite materials, which are important types of materials enjoying increasingly wide application in various industries such as aerospace, automotive, construction, and renewable energy. Finally, the survey explores potential future directions in MDD utilizing ML technologies. This comprehensive survey not only consolidates existing literature on ML-based MDD technologies but also serves as a foundational reference for future researchers and industrial practitioners, providing valuable insights and guidance in developing advanced and efficient MDD systems.

We report on the results of a search for radio pulsars in five supernova remnants (SNRs) with FAST. The observations were made using the 19-beam receiver in the Snapshot mode. The integration time for each pointing is 10 min. We discovered a new pulsar PSR J1845$-$0306 which has a spin period of 983.6 ms and a dispersion measure of 444.6$\pm$2.0 cm$^{-3}$ pc in observations of SNR G29.6+0.1. To judge the association between the pulsar and the SNR, further verification is needed. We also re-detected some known pulsars in the data from SNRs G29.6+0.1 and G29.7$-$0.3. No pulsars were detected in observations of other three SNRs., Comment: 6 pages, 2 figures, 2 tables published in CPL

Breast cancer continues to be a significant cause of mortality among women globally. Timely identification and precise diagnosis of breast abnormalities are critical for enhancing patient prognosis. In this study, we focus on improving the early detection and accurate diagnosis of breast abnormalities, which is crucial for improving patient outcomes and reducing the mortality rate of breast cancer. To address the limitations of traditional screening methods, a novel unsupervised feature correlation network was developed to predict maps indicating breast abnormal variations using longitudinal 2D mammograms. The proposed model utilizes the reconstruction process of current year and prior year mammograms to extract tissue from different areas and analyze the differences between them to identify abnormal variations that may indicate the presence of cancer. The model is equipped with a feature correlation module, an attention suppression gate, and a breast abnormality detection module that work together to improve the accuracy of the prediction. The proposed model not only provides breast abnormal variation maps, but also distinguishes between normal and cancer mammograms, making it more advanced compared to the state-of the-art baseline models. The results of the study show that the proposed model outperforms the baseline models in terms of Accuracy, Sensitivity, Specificity, Dice score, and cancer detection rate.

Transferability estimation has been attached to great attention in the computer vision fields. Researchers try to estimate with low computational cost the performance of a model when transferred from a source task to a given target task. Considering the effectiveness of such estimations, the communities of natural language processing also began to study similar problems for the selection of pre-trained language models. However, there is a lack of a comprehensive comparison between these estimation methods yet. Also, the differences between vision and language scenarios make it doubtful whether previous conclusions can be established across fields. In this paper, we first conduct a thorough survey of existing transferability estimation methods being able to find the most suitable model, then we conduct a detailed empirical study for the surveyed methods based on the GLUE benchmark. From qualitative and quantitative analyses, we demonstrate the strengths and weaknesses of existing methods and show that H-Score generally performs well with superiorities in effectiveness and efficiency. We also outline the difficulties of consideration of training details, applicability to text generation, and consistency to certain metrics which shed light on future directions., Comment: Accepted by Findings of EMNLP 2023

We report the radio observations of the eclipsing black widow pulsar J1720-0534, a 3.26 ms pulsar in orbit with a low mass companion of mass 0.029 to 0.034 M$_{\odot}$. We obtain the phase-connected timing ephemeris and polarization profile of this millisecond pulsar (MSP) using the Five-hundred-meter Aperture Spherical Radio Telescope (FAST), the Green Bank Telescope (GBT), and the Parkes Telescope. For the first time from such a system, an oscillatory polarisation angle change was observed from a particular eclipse egress with partial depolarization, indicating 10-milliGauss-level reciprocating magnetic fields oscillating in a length scale of 5000 km (assuming an orbital inclination angle of 90 degrees) outside the companion's magnetosphere. The dispersion measure variation observed during the ingresses and egresses shows the rapid raising of the electron density in the shock boundary between the companion's magnetosphere and the surrounding pulsar wind. We suggest that the observed oscillatory magnetic fields originate from the pulsar wind outside the companion's magnetosphere., Comment: 15 pages, 8 figures, 1 table, accepted by RAA

The linear constraint of secret key rate capacity is overcome by the tiwn-field quantum key distribution (QKD). However, the complex phase-locking and phase-tracking technique requirements throttle the real-life applications of twin-field protocol. The asynchronous measurement-device-independent (AMDI) QKD or called mode-pairing QKD protocol can relax the technical requirements and keep the similar performance of twin-field protocol. Here, we propose an AMDI-QKD protocol with a nonclassical light source by changing the phase-randomized weak coherent state to a phase-randomized coherent-state superposition in the signal state time window. Simulation results show that our proposed hybrid source protocol significantly enhances the key rate of the AMDI-QKD protocol, while exhibiting robustness to imperfect modulation of nonclassical light sources., Comment: 9 pages, 4 figures

The new variant of measurement-device-independent quantum key distribution (MDI-QKD), called asynchronous MDI-QKD or mode-pairing MDI-QKD, offers similar repeater-like rate-loss scaling but has the advantage of simple technology implementation by exploiting an innovative post-measurement pairing technique. We herein present an evaluation of the practical aspects of decoy-state asynchronous MDI-QKD. To determine its effectiveness, we analyze the optimal method of decoy-state calculation and examine the impact of asymmetrical channels and multi-user networks. Our simulations show that, under realistic conditions, aynchronous MDI-QKD can furnish the highest key rate with MDI security as compared to other QKD protocols over distances ranging from 50 km to 480 km. At fiber distances of 50 km and 100 km, the key rates attain 6.02 Mbps and 2.29 Mbps respectively, which are sufficient to facilitate real-time one-time-pad video encryption. Our findings indicate that experimental implementation of asynchronous MDI-QKD in intercity networks can be both practical and efficient., Comment: 15 pages, 4 figures

Prostate cancer is the most common cancer in men worldwide and the second leading cause of cancer death in the United States. One of the prognostic features in prostate cancer is the Gleason grading of histopathology images. The Gleason grade is assigned based on tumor architecture on Hematoxylin and Eosin (H&E) stained whole slide images (WSI) by the pathologists. This process is time-consuming and has known interobserver variability. In the past few years, deep learning algorithms have been used to analyze histopathology images, delivering promising results for grading prostate cancer. However, most of the algorithms rely on the fully annotated datasets which are expensive to generate. In this work, we proposed a novel weakly-supervised algorithm to classify prostate cancer grades. The proposed algorithm consists of three steps: (1) extracting discriminative areas in a histopathology image by employing the Multiple Instance Learning (MIL) algorithm based on Transformers, (2) representing the image by constructing a graph using the discriminative patches, and (3) classifying the image into its Gleason grades by developing a Graph Convolutional Neural Network (GCN) based on the gated attention mechanism. We evaluated our algorithm using publicly available datasets, including TCGAPRAD, PANDA, and Gleason 2019 challenge datasets. We also cross validated the algorithm on an independent dataset. Results show that the proposed model achieved state-of-the-art performance in the Gleason grading task in terms of accuracy, F1 score, and cohen-kappa. The code is available at https://github.com/NabaviLab/Prostate-Cancer.

Variational autoencoders (VAEs) are one of the powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound (ELBo), which consists of a conditional likelihood for generation and a negative Kullback-Leibler (KL) divergence for regularization. In practice, optimizing ELBo often leads the posterior distribution of all samples converge to the same degenerated local optimum, namely posterior collapse or KL vanishing. There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and hole problem, i.e., mismatch between the aggregated posterior distribution and the prior distribution. To this end, we introduce new training objectives to tackle both two problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution. Through experiments on language modeling, latent space visualization and interpolation, we show that our proposed method can solve both problems effectively and thus outperforms the existing methods in latent-directed generation. To the best of our knowledge, we are the first to jointly solve the hole problem and the posterior collapse., Comment: Accepted to NeurIPS 2022

Dual-Encoders is a promising mechanism for answer retrieval in question answering (QA) systems. Currently most conventional Dual-Encoders learn the semantic representations of questions and answers merely through matching score. Researchers proposed to introduce the QA interaction features in scoring function but at the cost of low efficiency in inference stage. To keep independent encoding of questions and answers during inference stage, variational auto-encoder is further introduced to reconstruct answers (questions) from question (answer) embeddings as an auxiliary task to enhance QA interaction in representation learning in training stage. However, the needs of text generation and answer retrieval are different, which leads to hardness in training. In this work, we propose a framework to enhance the Dual-Encoders model with question answer cross-embeddings and a novel Geometry Alignment Mechanism (GAM) to align the geometry of embeddings from Dual-Encoders with that from Cross-Encoders. Extensive experimental results show that our framework significantly improves Dual-Encoders model and outperforms the state-of-the-art method on multiple answer retrieval datasets., Comment: Findings of EMNLP 2021(10 pages)

Numerical methods are widely used to calculate the secure key rate of many quantum key distribution protocols in practice, but they consume many computing resources and are too time-consuming. In this work, we take the homodyne detection discrete-modulated continuous-variable quantum key distribution (CV-QKD) as an example, and construct a neural network that can quickly predict the secure key rate based on the experimental parameters and experimental results. Compared to traditional numerical methods, the speed of the neural network is improved by several orders of magnitude. Importantly, the predicted key rates are not only highly accurate but also highly likely to be secure. This allows the secure key rate of discrete-modulated CV-QKD to be extracted in real time on a low-power platform. Furthermore, our method is versatile and can be extended to quickly calculate the complex secure key rates of various other unstructured quantum key distribution protocols., Comment: 12 pages, 5 figures, 2 tables

Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very difficult to obtain both coherent and accurate labeling results. For this challenging task, we propose a novel deep model with convolutional neural networks (CNNs), i.e., an end-to-end self-cascaded network (ScasNet). Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation. Technically, multi-scale contexts are captured on the output of a CNN encoder, and then they are successively aggregated in a self-cascaded manner. Meanwhile, for fine-structured objects, ScasNet boosts the labeling accuracy with a coarse-to-fine refinement strategy. It progressively refines the target objects using the low-level features learned by CNN's shallow layers. In addition, to correct the latent fitting residual caused by multi-feature fusion inside ScasNet, a dedicated residual correction scheme is proposed. It greatly improves the effectiveness of ScasNet. Extensive experimental results on three public datasets, including two challenging benchmarks, show that ScasNet achieves the state-of-the-art performance., Comment: accepted by ISPRS Journal of Photogrammetry and Remote Senseing 2017

We propose some nonlinear Schr\"{o}dinger equations by adding some higher order terms to the Lagrangian density of Schr\"{o}dinger field, and obtain the Gross-Pitaevskii (GP) equation and the logarithmic form equation naturally. In addition, we prove the coefficient of nonlinear term is very small, i.e., the nonlinearity of Schr\"{o}dinger equation is weak.

We have analyzed the $D\rightarrow \pi K, KK$ decay with the naive factorization (NF), QCD factorization (QCDF)and QCD factorization including soft-gluon exchanges (QCDF+SGE). In these decay channels, the soft-gluon effects are firstly calculated with light cone QCD sum rules. Comparing the three kind approaches, we can find the calculation results have made much more improved QCD factorization (QCDF) than the naive factorization (NF), and the calculation results have also made improved QCD factorization including soft-gluon exchanges (QCDF+SGE) than the QCD factorization (QCDF) in the color-suppressed decay channels. In addition, we find the soft-gluon effects are larger than the leading order contributions, and the calculation results are close to the experimental data for the color-suppressed decay channels. In color-allowed decay channel $D^{0}\rightarrow \pi^{+} K^{-}$, the soft-gluon effects are small and we should consider other power terms, such as final state interaction and annihilation effects.

At present, the theory of light diffraction only has the simple wave-optical approach. In this paper, we study light diffraction with the approach of relativistic quantum theory. We find that the slit length, slit width, slit thickness and wave-length of light have affected to the diffraction intensity and form of diffraction pattern. However, the effect of slit thickness on the diffraction pattern can not be explained by wave-optical approach, and it can be explained in quantum theory. We compare the theoretical results with single and multiple slits experiment data, and find the theoretical results are accordance with the experiment data. Otherwise, we give some theory prediction. We think all the new prediction will be tested by the light diffraction experiment., Comment: 10 pages

In the paper, we present a new kind of function photonic crystals, which refractive index is a function of space position. Unlike conventional PCs, which structure grow from two materials, A and B, with different dielectric constants $\epsilon_{A}$ and $\epsilon_{B}$. By Fermat principle, we give the motion equations of light in one-dimensional, two-dimensional and three-dimensional function photonic crystals. For one-dimensional function photonic crystals, we study the dispersion relation, band gap structure and transmissivity, and compare them with conventional photonic crystals. By choosing various refractive index distribution function $n(z)$, we can obtain more width or more narrow band gap structure than conventional photonic crystals., Comment: 15 pages, 8 figures. arXiv admin note: text overlap with arXiv:1001.3793 by other authors; and text overlap with arXiv:1003.3524, arXiv:physics/0104088 by other authors without attribution

In this paper, we study the laser cooling mechanisms with a new quantum theory approach by applying a new Schrodinger equation, which can describe a particle in conservative and non-conservative force field. With the new theory, we prove the atom in laser field can be cooled, and give the atom cooling temperature, which is accordance with experiment result. Otherwise, we give new prediction that the atom cooling temperature is directly proportional to the atom vibration frequency. By calculation, we find they are: $T=0.4334\omega$., Comment: arXiv admin note: text overlap with arXiv:physics/0601097, arXiv:0710.5078, arXiv:0707.2280 by other authors without attribution

We know Schr\"{o}dinger equation describes the dynamics of quantum systems, which don't include temperature. In this paper, we propose finite temperature Schr\"{o}dinger equation, which can describe the quantum systems in an arbitrary temperature. When the temperature T=0, it become Shr\"{o}dinger equation., Comment: 8 pages

As well known, an electron will produce radiative reaction force when the electron emits electromagnetism radiation. The electron radiative effect had not been considered in Schr\"{o}dinger wave equation. In this paper, we give the nonlinear quantum wave equations for the radiative electron and some dissipative systems., Comment: 7 pages

We provide a quantum approach description of neutron single and double-slit diffraction, with specific attention to the cold neutron diffraction ($\lambda \approx 20$\AA) carried out by Zeilinger et al. in 1988. We find the theoretical results are good agreement with experimental data., Comment: 10 pages

It is well known that Schr\"{o}dinger's equation is only suitable for the particle in conservative force field. In atomic and molecular field, a particle can suffer the action of non-conservative force. In this paper, a new quantum wave equation is proposed, which can describe the particle in non-conservative force field. We think the new quantum wave equation can be used in many fields., Comment: 10 pages. arXiv admin note: substantial text overlap with arXiv:0909.3189; and text overlap with arXiv:0711.3544 by other authors without attribution

Experiments done with single photon in the early 1990's produced a surprising result: that single photon pass through a photon tunnel barrier with a group velocity faster than the vacuum speed of light. Recently, a series of experiments revealed that electromagnetic wave was able to travel at a group velocity faster than $c$. These phenomena have been observed in dispersive media. We think all particles can be divided into three kinds in nature: The first kind of particle is its velocity in the range of $0\leq v < c$, e.g. electron, atom and so on. The second kind of particle is its velocity in the range of $0\leq v < c_{m}$, e.g. photon. The third kind of particle is its velocity in the range of $c\leq v < c_{m}$ ($c_{m}$ is the maximum velocity in universe), e.g. tachyon. The first kind of particle is described by the special relativity. In this paper, we give some new kinematic and dynamic equations to describe the second and third kinds particles., Comment: 16 pages

The phenomena of electron, neutron, atomic and molecular diffraction have been studied by many experiments, and these experiments are explained by some theoretical works. In this paper, we study electronic double-slit diffraction with quantum mechanical approach. We can obtain the results: (1) When the slit width $a$ is in the range of $3\lambda\sim 50\lambda$ we can obtain the obvious diffraction patterns. (2) when the ratio of $\frac{d+a}{a}=n (n=1, 2, 3,\cdot\cdot\cdot)$, order $2n, 3n, 4n,\cdot\cdot\cdot$ are missing in diffraction pattern. (3)When the ratio of $\frac{d+a}{a}\neq n (n=1, 2, 3,\cdot\cdot\cdot)$, there isn't missing order in diffraction pattern. (4) We also find a new quantum mechanics effect that the slit thickness $c$ has a large affect to the electronic diffraction patterns. We think all the predictions in our work can be tested by the electronic double-slit diffraction experiment., Comment: 9pages, 14figures