Search

Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral choice scenarios in Chinese, derived from moral words. The decision-making process of the models in these scenarios reveals their moral principle preferences. By ranking these moral choices, we discern the varying moral beliefs held by different language models. Additionally, through moral debates, we investigate the firmness of these models to their moral choices. Our findings indicate that English language models, namely ChatGPT and Gemini, closely mirror moral decisions of the sample of Chinese university students, demonstrating strong adherence to their choices and a preference for individualistic moral beliefs. In contrast, Chinese models such as Ernie and ChatGLM lean towards collectivist moral beliefs, exhibiting ambiguity in their moral choices and debates. This study also uncovers gender bias embedded within the moral beliefs of all examined language models. Our methodology offers an innovative means to assess moral beliefs in both artificial and human intelligence, facilitating a comparison of moral values across different cultures.

This paper presents a novel approach to glass composition screening through a self-supervised learning framework, addressing the challenges posed by glass transition temperature (Tg) prediction. Given the critical role of Tg in determining glass performance across various applications, we reformulate the composition screening task as a classification problem, allowing for direct prediction of whether specific compositional samples fall within a designated Tg range. Our model leverages advanced self-supervised learning techniques to optimize for the area under the curve (AUC) metric, mitigating the adverse effects of noise and class imbalances in training data. We introduce a data augmentation method based on the law of large numbers to enhance sample size and improve noise robustness. Additionally, our DeepGlassNet backbone encoder captures intricate second-order and higher-order interactions among components, providing insights into their collective impact on glass properties. We validate our approach using data from the SciGlass database, demonstrating its capability to accurately predict Tg for compositions within the specified range, while also exploring extrapolation to untested samples. This work not only enhances the accuracy of glass composition screening but also offers scalable solutions applicable to material screening across various fields, thereby advancing the development of novel materials.

An extreme ultraviolet (EUV) close-up view of the Sun offers unprecedented detail of heating events in the solar corona. Enhanced temporal and spatial images obtained by the Solar Orbiter during its first science perihelion enabled us to identify clustered EUV bright tadpoles (CEBTs) occurring near the footpoints of coronal loops. Combining SDO/AIA observations, we determine the altitudes of six distinct CEBTs by stereoscopy, ranging from $\sim$1300 to 3300 km. We then notice a substantial presence of dark, cooler filamentary structures seemingly beneath the CEBTs, displaying periodic up-and-down motions lasting 3 to 5 minutes. This periodic behavior suggests an association of the majority of CEBTs with Type I spicules. Out of the ten selected CEBTs with fast downward velocity, six exhibit corrected velocities close to or exceeding 50 km $s^{-1}$. These velocities notably surpass the typical speeds of Type I spicules. We explore the generation of such velocities. It indicates that due to the previous limited observations of spicules in the EUV wavelengths, they may reveal novel observational features beyond our current understanding. Gaining insights into these features contributes to a better comprehension of small-scale coronal heating dynamics., Comment: 17 pages, 10 figures, accepted for publication in RAA

This work demonstrates a novel energy-efficient tunnel FET (TFET)-CMOS hybrid foundry platform for ultralow-power AIoT applications. By utilizing the proposed monolithic integration process, the novel complementary n and p-type Si TFET technology with dopant segregated source junction and self-aligned drain underlap design is successfully integrated into a 300mm CMOS baseline process without CMOS performance penalty and any new materials, experimentally demonstrating the large Ion and record high Ion/Ioff ratio of 10^7 among TFETs by industry-manufacturers. The device performance and variability are also co-optimized for high-volume production. Further circuit-level implementations are presented based on the calibrated compact model. The proposed TFET-CMOS hybrid logic and SRAM topologies show significant energy efficiency improvement with comparable operation speed compared with standard CMOS circuits, indicating its great potential for power-constraint AIoT applications.

Despite the remarkable advancements in Visual Question Answering (VQA), the challenge of mitigating the language bias introduced by textual information remains unresolved. Previous approaches capture language bias from a coarse-grained perspective. However, the finer-grained information within a sentence, such as context and keywords, can result in different biases. Due to the ignorance of fine-grained information, most existing methods fail to sufficiently capture language bias. In this paper, we propose a novel causal intervention training scheme named CIBi to eliminate language bias from a finer-grained perspective. Specifically, we divide the language bias into context bias and keyword bias. We employ causal intervention and contrastive learning to eliminate context bias and improve the multi-modal representation. Additionally, we design a new question-only branch based on counterfactual generation to distill and eliminate keyword bias. Experimental results illustrate that CIBi is applicable to various VQA models, yielding competitive performance.

The acceleration of the young solar wind is studied using the first 17 encounters of Parker Solar Probe. We identify wind intervals from different source regions: coronal hole (CH) interiors, streamers, and low Mach number boundary layers (LMBLs), i.e. the inner boundaries of coronal holes. We present their statistical trends in the acceleration process. Most of the observations can be reproduced by a two-fluid hydrodynamic model with realistic corona temperatures. In such a model, the solar wind is accelerated by the combined thermal pressures of protons and electrons,but it is mainly the difference in the proton pressure that leads to the difference in the solar wind speed. The proton pressure is the highest in the fastest CH wind, with a high initial proton temperature that decreases slowly. It is lower in the relatively slow LMBL wind, and the lowest in the slowest streamer wind. The proton temperature is quadratically correlated with the wind speed when scaled to the same distance. In contrast, the electron temperature shows no significant differences for different wind types or wind speeds, indicating more similar contributions from the electron pressure. The model gives reasonable locations for the sonic critical point, which is on average at 3.6-7.3 solar radii and can also extend to large distances when the proton temperature is extremely low, as in the LMBL wind. In addition to the thermal pressure, we raise the possibility that Alfv\'en waves may contribute to the solar wind acceleration, especially for the fast CH wind., Comment: Accepted for publication by ApJ Letters

High-speed ultra-broadband detectors play a crucial role in aerospace technology, and national security etc. The interfacial work function internal photoemission (IWIP) detector employs multiple absorption mechanism comprehensively across different wavelength band to achieve complete photon type detection, which makes it possible to realize high-speed and ultra-broadband simultaneously. We propose a ratchet heterojunction IWIP (HEIWIP) detector, which shows 3-165THz ultra-broadband coverage. The high-speed response is investigated in detail by both microwave rectification technology and high-speed modulated terahertz light. Up to 5.1GHz 3dB bandwidth is acquired in terms of microwave rectification measurement. And 4.255GHz inter-mode optical beat note signal was successfully detected.

In this paper, we present a method, VectorPD, for converting a given human face image into a vector portrait sketch. VectorPD supports different levels of abstraction by simply controlling the number of strokes. Since vector graphics are composed of different shape primitives, it is challenging for rendering complex faces to accurately express facial details and structure. To address this, VectorPD employs a novel two-round optimization mechanism. We first initialize the strokes with facial keypoints, and generate a basic portrait sketch by a CLIP-based Semantic Loss. Then we complete the face structure through VGG-based Structure Loss, and propose a novel Crop-based Shadow Loss to enrich the shadow details of the sketch, achieving a visually pleasing portrait sketch. Quantitative and qualitative evaluations both demonstrate that the portrait sketches generated by VectorPD can produce better visual effects than existing state-of-the-art methods, maintaining as much fidelity as possible at different levels of abstraction., Comment: 9 pages, 12 figures

Scene sketching is to convert a scene into a simplified, abstract representation that captures the essential elements and composition of the original scene. It requires semantic understanding of the scene and consideration of different regions within the scene. Since scenes often contain diverse visual information across various regions, such as foreground objects, background elements, and spatial divisions, dealing with these different regions poses unique difficulties. In this paper, we define a sketch as some sets of Bezier curves. We optimize the different regions of input scene in multiple rounds. In each round of optimization, strokes sampled from the next region can seamlessly be integrated into the sketch generated in the previous round of optimization. We propose additional stroke initialization method to ensure the integrity of the scene and the convergence of optimization. A novel CLIP-Based Semantic loss and a VGG-Based Feature loss are utilized to guide our multi-round optimization. Extensive experimental results on the quality and quantity of the generated sketches confirm the effectiveness of our method., Comment: 9 pages, 9 figures

Multi-view learning methods often focus on improving decision accuracy, while neglecting the decision uncertainty, limiting their suitability for safety-critical applications. To mitigate this, researchers propose trusted multi-view learning methods that estimate classification probabilities and uncertainty by learning the class distributions for each instance. However, these methods assume that the data from each view can effectively differentiate all categories, ignoring the semantic vagueness phenomenon in real-world multi-view data. Our findings demonstrate that this phenomenon significantly suppresses the learning of view-specific evidence in existing methods. We propose a Consistent and Complementary-aware trusted Multi-view Learning (CCML) method to solve this problem. We first construct view opinions using evidential deep neural networks, which consist of belief mass vectors and uncertainty estimates. Next, we dynamically decouple the consistent and complementary evidence. The consistent evidence is derived from the shared portions across all views, while the complementary evidence is obtained by averaging the differing portions across all views. We ensure that the opinion constructed from the consistent evidence strictly aligns with the ground-truth category. For the opinion constructed from the complementary evidence, we allow it for potential vagueness in the evidence. We compare CCML with state-of-the-art baselines on one synthetic and six real-world datasets. The results validate the effectiveness of the dynamic evidence decoupling strategy and show that CCML significantly outperforms baselines on accuracy and reliability. The code is released at https://github.com/Lihong-Liu/CCML.

NOAA Active Region (AR) 13664/8 produced the most intense geomagnetic effects since the ``Halloween'' event of 2003. The resulting extreme solar storm is believed to be the consequence of multiple interacting coronal mass ejections (CMEs). Notably, this AR exhibites an exceptionally rapid magnetic flux emergence. The eruptions we are focusing on all occurred along collisional polarity inversion lines (PILs) through ``collisional shearing'' during a three-day period of extraordinarily high flux emergence ($\sim$10$^{21}$ Mx hr$^{-1}$). Our key findings reveal how photospheric magnetic configurations in eruption sources influence solar superstorm formation and geomagnetic responses, and link exceptionally strong flux emergence to sequential homologous eruptions: (1) We identified the source regions of seven halo CMEs, distributed primarily along two distinct PILs, suggesting the presence of two groups of homologous CMEs. (2) The variations in magnetic flux emergence rates at the source regions correlate with CME intensities, potentially explaining the two contrasting cases of complex ejecta observed at Earth. (3) Calculations of magnetic field gradients around CME source regions show strong correlations with eruptions, providing crucial insights into solar eruption mechanisms and enhancing future prediction capabilities., Comment: 4 figures, accepted for publication in A&A

Mobile Artificial Intelligence-Generated Content (AIGC) networks enable massive users to obtain customized content generation services. However, users still need to download a large number of AIGC outputs from mobile AIGC service providers, which strains communication resources and increases the risk of transmission failures. Fortunately, Semantic Communication (SemCom) can improve transmission efficiency and reliability through semantic information processing. Moreover, recent advances in Generative Artificial Intelligence (GAI) further enhanced the effectiveness of SemCom through its powerful generative capabilities. However, how to strike a balance between high-quality content generation and the size of semantic information transmitted is a major challenge. In this paper, we propose a Generative Diffusion Model (GDM)-based multi-modal SemCom (GM-SemCom) framework. The framework improves the accuracy of information reconstruction by integrating GDMs and multi-modal semantic information and also adopts a controllable extraction module for efficient and controllable problems of unstable data recovery and slow decoding speed in GAI-enabled SemCom. Then, we introduce a novel metric called Age of Semantic Information (AoSI) based on the concept of Age of Information (AoI) to quantify the freshness of semantic information. To address the resource trading problem within the framework, we propose a Stackelberg game model, which integrates the AoSI with psychological factors to provide a comprehensive measure of user utility. Furthermore, we propose a GDM-based algorithm to solve the game under incomplete information. Compared with the traditional deep reinforcement learning algorithms, numerical results demonstrate that the proposed algorithm converges faster and is closer to the Stackelberg equilibrium.

We select and investigate six global solar extreme ultraviolet (EUV) wave events using data from the Solar Dynamics Observatory (SDO) and the Solar and Heliospheric Observatory (SOHO). These eruptions are all on the limb but recorded as halo coronal mass ejections (CMEs) because the CME-driven shocks have expanded laterally to the opposite side. With the limb observations avoiding the projection effect, we have measured the inclination and speed of the EUV wavefront from 1.05 to 1.25 $R_\odot$. We also investigate the coupling and connection of the EUV wavefront with the CME boundary and the CME-driven shock, respectively. The major findings in the six events are: (1) the forward inclination of the primary and coronal-hole transmitted EUV wavefronts is estimated, respectively, and the origins of these inclinations and their effects on the estimate of actual wavefront speed are investigated; (2) the wavefront speed can be elevated by loop systems near the coronal base, and the average speed in the low corona has no clear correlation with the lateral expansion of the CME-driven shock in the high corona; (3) the fast magnetosonic Mach number of the wavefront is larger than unity from the coronal base; (4) the EUV wavefront is coupled with the CME driver throughout the propagation in two events; (5) after the EUV wavefront vanishes, the CME-driven shock continues traveling on the opposite side and disconnects from the EUV wavefront in four events. These results and their implications are discussed, which provide insight into the properties of global EUV waves., Comment: 32 pages, 10 figures, 2 tables; accepted by ApJ; added necessary revisions according to proof

The largest geomagnetic storm in two decades occurred in 2024 May with a minimum $D_{\rm st}$ of $-412$ nT. We examine its solar and interplanetary origins by combining multipoint imaging and in situ observations. The source active region, NOAA AR 13664, exhibited extraordinary activity and produced successive halo eruptions, which were responsible for two complex ejecta observed at the Earth. In situ measurements from STEREO A, which was $12.6^{\circ}$ apart, allow us to compare the ``geo-effectiveness" at the Earth and STEREO A. We obtain key findings concerning the formation of solar superstorms and how mesoscale variations of coronal mass ejections affect geo-effectiveness: (1) the 2024 May storm supports the hypothesis that solar superstorms are ``perfect storms" in nature, i.e., a combination of circumstances resulting in an event of an unusual magnitude; (2) the first complex ejecta, which caused the geomagnetic superstorm, shows considerable differences in the magnetic field and associated ``geo-effectiveness" between the Earth and STEREO A, despite a mesoscale separation; and (3) two contrasting cases of complex ejecta are found in terms of the geo-effectiveness at the Earth, which is largely due to different magnetic field configurations within the same active region., Comment: Accepted for publication in ApJL

The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches., Comment: 10 pages, 12 figures

Two self-supervised pretrained transformer-based segmentation models (SMIT and Swin UNETR) fine-tuned on a dataset of ovarian cancer CT images provided reasonably accurate delineations of the tumors in an independent test dataset. Tumors in the adnexa were segmented more accurately by both transformers (SMIT and Swin UNETR) than the omental implants. AI-assisted labeling performed on 72 out of 245 omental implants resulted in smaller manual editing effort of 39.55 mm compared to full manual correction of partial labels of 106.49 mm and resulted in overall improved accuracy performance. Both SMIT and Swin UNETR did not generate any false detection of omental metastases in the urinary bladder and relatively few false detections in the small bowel, with 2.16 cc on average for SMIT and 7.37 cc for Swin UNETR respectively.

On 2022 March 28 two successive coronal mass ejections (CMEs) were observed by multiple spacecraft and resulted in a magnetic cloud (MC) at 1 AU. We investigate the propagation and interaction properties of the two CMEs correlated with the MC using coordinated multi-point remote sensing and in situ observations from Solar Orbiter, STEREO A, SOHO, and Wind. The first CME was triggered by a filament eruption with a high inclination angle. Roughly 9 hr later, the second CME originating from the same active region erupted with a smaller tilt angle and faster speed compared to the first one. The second CME overtook the preceding CME and formed a merged front at approximately 75 \rsun{}, which developed into a complex ejecta at 1 AU. The descending speed and low proton temperature inside the complex ejecta suggest that the two CMEs have fully merged before reaching 1 AU, leading them to begin expanding rather than compressing against each other. The complex ejecta appears to have the magnetic field and plasma signatures of an MC, although there is a discontinuity in the magnetic field implying previous interactions. The cross section of the complex ejecta, reconstructed from in situ data using a Grad-Shafranov technique, exhibits a right--handed flux rope structure. These results highlight that an MC--like complex ejecta lacking interaction features could arise from the complete merging of two CMEs.

Quantitative susceptibility mapping (QSM) is an MRI phase-based post-processing technique to extract the distribution of tissue susceptibilities, demonstrating significant potential in studying neurological diseases. However, the ill-conditioned nature of dipole inversion makes QSM reconstruction from the tissue field prone to noise and artifacts. In this work, we propose a novel deep learning-based IR2QSM method for QSM reconstruction. It is designed by iterating four times of a reverse concatenations and middle recurrent modules enhanced U-net, which could dramatically improve the efficiency of latent feature utilization. Simulated and in vivo experiments were conducted to compare IR2QSM with several traditional algorithms (MEDI and iLSQR) and state-of-the-art deep learning methods (U-net, xQSM, and LPCNN). The results indicated that IR2QSM was able to obtain QSM images with significantly increased accuracy and mitigated artifacts over other methods. Particularly, IR2QSM demonstrated on average the best NRMSE (27.59%) in simulated experiments, which is 15.48%, 7.86%, 17.24%, 9.26%, and 29.13% lower than iLSQR, MEDI, U-net, xQSM, LPCNN, respectively, and led to improved QSM results with fewer artifacts for the in vivo data., Comment: 10 pages, 9 figures

Predicting unseen relations that cannot be observed during the training phase is a challenging task in relation extraction. Previous works have made progress by matching the semantics between input instances and label descriptions. However, fine-grained matching often requires laborious manual annotation, and rich interactions between instances and label descriptions come with significant computational overhead. In this work, we propose an efficient multi-grained matching approach that uses virtual entity matching to reduce manual annotation cost, and fuses coarse-grained recall and fine-grained classification for rich interactions with guaranteed inference speed. Experimental results show that our approach outperforms the previous State Of The Art (SOTA) methods, and achieves a balance between inference efficiency and prediction accuracy in zero-shot relation extraction tasks. Our code is available at https://github.com/longls777/EMMA., Comment: Accepted to the main conference of NAACL2024

Whereas ferroelectricity may vanish in ultra-thin ferroelectric films, it is expected to emerge in ultra-thin anti-ferroelectric films, sparking people's interest in using antiferroelectric materials as an alternative to ferroelectric ones for high-density data storage applications. Lead Zirconate (PbZrO3) is considered the prototype material for antiferroelectricity, and indeed previous studies indicated that nanoscale PbZrO3 films exhibit ferroelectricity. The understanding of such phenomena from the microstructure aspect is crucial but still lacking. In this study, we fabricated a PbZrO3 film with thicknesses varying from 5 nm to 80 nm. Using Piezoresponse Force Microscopy, we discovered the film displayed a transition from antiferroelectric behaviour in the thicker areas to ferroelectric behaviour in the thinner ones, with a critical thickness between 10 and 15 nm. In this critical thickness range, a 12 nm PZO thin film was chosen for further study using aberration-corrected scanning transmission electron microscopy. The investigation showed that the film comprises both ferroelectric and ferrielectric phases. The ferroelectric phase is characterized by polarisation along the pseudocubic [011] projection direction. The positions of Pb, Zr, and O were determined using the integrated differential phase contrast method. This allowed us to ascertain that the ferroelectric PbZrO3 unit cell is half the size of that in the antiferroelectric phase on the ab plane. The observed unit cell is different from the electric field-induced ferroelectric rhombohedral phases. Additionally, we identified a ferrielectric phase with a unique up-up-zero-zero dipole configuration. The finding is crucial for understanding the performance of ultrathin antiferroelectric thin films and the subsequent design and development of antiferroelectric devices.

Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of diverse tasks in multitask speech models has positive influence on the performance of individual tasks. In this paper we present a multitask speech model -- PolySpeech, which supports speech recognition, speech synthesis, and two speech classification tasks. PolySpeech takes multi-modal language model as its core structure and uses semantic representations as speech inputs. We introduce semantic speech embedding tokenization and speech reconstruction methods to PolySpeech, enabling efficient generation of high-quality speech for any given speaker. PolySpeech shows competitiveness across various tasks compared to single-task models. In our experiments, multitask optimization achieves performance comparable to single-task optimization and is especially beneficial for specific tasks., Comment: 5 pages, 2 figures

While nationality is a pivotal demographic element that enhances the performance of language models, it has received far less scrutiny regarding inherent biases. This study investigates nationality bias in ChatGPT (GPT-3.5), a large language model (LLM) designed for text generation. The research covers 195 countries, 4 temperature settings, and 3 distinct prompt types, generating 4,680 discourses about nationality descriptions in Chinese and English. Automated metrics were used to analyze the nationality bias, and expert annotators alongside ChatGPT itself evaluated the perceived bias. The results show that ChatGPT's generated discourses are predominantly positive, especially compared to its predecessor, GPT-2. However, when prompted with negative inclinations, it occasionally produces negative content. Despite ChatGPT considering its generated text as neutral, it shows consistent self-awareness about nationality bias when subjected to the same pair-wise comparison annotation framework used by human annotators. In conclusion, while ChatGPT's generated texts seem friendly and positive, they reflect the inherent nationality biases in the real world. This bias may vary across different language versions of ChatGPT, indicating diverse cultural perspectives. The study highlights the subtle and pervasive nature of biases within LLMs, emphasizing the need for further scrutiny., Comment: Accepted by LREC-COLING 2024

Sequential recommender systems explore users' preferences and behavioral patterns from their historically generated data. Recently, researchers aim to improve sequential recommendation by utilizing massive user-generated multi-modal content, such as reviews, images, etc. This content often contains inevitable noise. Some studies attempt to reduce noise interference by suppressing cross-modal inconsistent information. However, they could potentially constrain the capturing of personalized user preferences. In addition, it is almost impossible to entirely eliminate noise in diverse user-generated multi-modal content. To solve these problems, we propose a trustworthy sequential recommendation method via noisy user-generated multi-modal content. Specifically, we explicitly capture the consistency and complementarity of user-generated multi-modal content to mitigate noise interference. We also achieve the modeling of the user's multi-modal sequential preferences. In addition, we design a trustworthy decision mechanism that integrates subjective user perspective and objective item perspective to dynamically evaluate the uncertainty of prediction results. Experimental evaluation on four widely-used datasets demonstrates the superior performance of our model compared to state-of-the-art methods. The code is released at https://github.com/FairyMeng/TrustSR.

Fundus diseases are major causes of visual impairment and blindness worldwide, especially in underdeveloped regions, where the shortage of ophthalmologists hinders timely diagnosis. AI-assisted fundus image analysis has several advantages, such as high accuracy, reduced workload, and improved accessibility, but it requires a large amount of expert-annotated data to build reliable models. To address this dilemma, we propose a general self-supervised machine learning framework that can handle diverse fundus diseases from unlabeled fundus images. Our method's AUC surpasses existing supervised approaches by 15.7%, and even exceeds performance of a single human expert. Furthermore, our model adapts well to various datasets from different regions, races, and heterogeneous image sources or qualities from multiple cameras or devices. Our method offers a label-free general framework to diagnose fundus diseases, which could potentially benefit telehealth programs for early screening of people at risk of vision loss.

Machine learning-based fundus image diagnosis technologies trigger worldwide interest owing to their benefits such as reducing medical resource power and providing objective evaluation results. However, current methods are commonly based on supervised methods, bringing in a heavy workload to biomedical staff and hence suffering in expanding effective databases. To address this issue, in this article, we established a label-free method, name 'SSVT',which can automatically analyze un-labeled fundus images and generate high evaluation accuracy of 97.0% of four main eye diseases based on six public datasets and two datasets collected by Beijing Tongren Hospital. The promising results showcased the effectiveness of the proposed unsupervised learning method, and the strong application potential in biomedical resource shortage regions to improve global eye health., Comment: ISBI 2024

The top-down synthesis of inherently ferroelectric semiconductors and their integration with traditional material platforms have the potential to enable new low power logic devices, and to harness the bulk photoelectric effect for more efficient photovoltaic cells. InSe is a layered van der Waals compound exhibiting multiple polytypes, with semiconducting gamma-InSe revealing a non-centrosymmetric space group and showing a high carrier mobility at room temperature. Here we report the growth of InSe films on close to lattice matched semi-insulating GaAs(111)B substrates by molecular beam epitaxy (MBE). Excellent nucleation behavior resulted in the growth of smooth, single phase InSe films. The dominant polytype determined from X-ray diffraction was the targeted gamma-InSe, however Raman spectroscopy revealed spatial variations in the overall low-intensity non-centrosymmetric vibration modes. Transmission electron microscopy uncovered the presence of the three bulk polytypes beta, gamma, and epsilon-InSe coexisting in the films arranging in nanosized domains. The different polytypes can be interpreted as sequences of stacking faults and rotational twin boundaries of gamma-InSe made from individual non-centrosymmetric Se-In-In-Se layers with P-6m2 symmetry. A second, centrosymmetric Se-In-In-Se layer polymorph was identified with P-3m symmetry, which is typically not present in InSe bulk phases. First principles calculations revealed small formation energy differences between the InSe polymorphs and polytypes, yet sizeable differences in their electronic properties. Nanoscale domain sizes of varying polytypes thus resulted in sizeable electronic disorder in the grown films that dominated the electronic transport properties. Our results indicate that bottom-up thin film synthesis is a viable synthesis route towards stabilization of InSe polytypes not present in the bulk.

This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field., Comment: NTIRE 2024 webpage: https://cvlai.net/ntire/2024. Code: https://github.com/zhengchen1999/NTIRE2024_ImageSR_x4

We identify and examine the solar wind intervals near the sonic critical point (i.e., $M_S \sim 1$) observed by the Parker Solar Probe (PSP). The near subsonic wind intervals show similar properties: a low density, an extremely low velocity, a low proton temperature, and essentially no magnetic field deflections compared with the surrounding solar wind. The extremely low velocity is the primary contributor to the near crossing of the sonic critical point rather than the sound speed, which is roughly constant in these intervals. Source tracing with a potential field source surface (PFSS) model suggests that the near subsonic intervals all connect to the boundaries inside coronal holes. Heliospheric current sheet (HCS) and partial HCS crossings around the near subsonic intervals indicate that the near subsonic wind is a transition layer between the slow and fast wind. The above scenario is consistent with the nature of the near subsonic wind as a low Mach-number boundary layer (LMBL), which facilitates the crossing of the sonic critical point at 15-20 $R_S$. Moreover, we find a dependence of the amplitude of switchbacks on the radial sonic Mach number. Magnetic field deflections essentially disappear near the sonic critical point, which suggests that switchbacks originate from above the sonic critical point., Comment: Accepted for publication in ApJ

Andreev reflection at a normal-superconductor interface may be accompanied with an anomalous spatial shift. The studies so far are limited to the top incidence configuration. Here, we investigate this effect in the side incidence configuration, with the interface parallel to the principal axis of superconductor. We find that the shift exhibits rich behaviors reflecting the character of pair potential. It has two contributions: one from the $k$-dependent phase of pair potential, and the other from the evanescent mode. For chiral $p$-wave pairing, the pairing phase contribution is proportional to the chirality of pairing and is independent of excitation energy, whereas the evanescent mode contribution is independent of chirality and is nonzero only for excitation energy below the gap. The two contributions also have opposite parity with respect to the incident angle. For $d_{x^{2}-y^{2}}$-wave pairing, only the evanescent mode contribution exists, and the shift exhibits suppressed zones in incident angles, manifesting the superconducting nodes. The dependence of the shift on other factors, such as the angle of incident plane and Fermi surface anisotropy, are discussed.

Automated hand gesture recognition has long been a focal point in the AI community. Traditionally, research in this field has predominantly focused on scenarios with access to a continuous flow of hand's images. This focus has been driven by the widespread use of cameras and the abundant availability of image data. However, there is an increasing demand for gesture recognition technologies that operate on low-power sensor devices. This is due to the rising concerns for data leakage and end-user privacy, as well as the limited battery capacity and the computing power in low-cost devices. Moreover, the challenge in data collection for individually designed hardware also hinders the generalisation of a gesture recognition model. In this study, we unveil a novel methodology for pattern recognition systems using adaptive and agile error correction, designed to enhance the performance of legacy gesture recognition models on devices with limited battery capacity and computing power. This system comprises a compact Support Vector Machine as the base model for live gesture recognition. Additionally, it features an adaptive agile error corrector that employs few-shot learning within the feature space induced by high-dimensional kernel mappings. The error corrector can be customised for each user, allowing for dynamic adjustments to the gesture prediction based on their movement patterns while maintaining the agile performance of its base model on a low-cost and low-power micro-controller. This proposed system is distinguished by its compact size, rapid processing speed, and low power consumption, making it ideal for a wide range of embedded systems.

The counterflow superfluidity (CSF) was predicted two decades ago. Counterintuitively, while both components in the CSF have fluidity, their correlated counterflow currents cancel out leading the overall system to an incompressible Mott insulator. However, realizing and identifying the CSF remain challenging due to the request on extreme experimental capabilities in a single setup. Here, we observe the CSF in a binary Bose mixture in optical lattices. We prepare a low-entropy spin-Mott state by conveying and merging two spin-1/2 bosonic atoms at every site and drive it adiabatically to the CSF at $\sim$ 1 nK. Antipair correlations of the CSF are probed though a site- and spin-resolved quantum gas microscope in both real and momentum spaces. These techniques and observations provide accessibility to the symmetry-protected topological quantum matters., Comment: 13 pages, 10 figures

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models are not fully explored, unlike their predecessors, such as BERT-like architectures. In this paper, we specifically investigate the bottom-up evolution of lexical semantics for a popular LLM, namely Llama2, by probing its hidden states at the end of each layer using a contextualized word identification task. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics. The conclusion is further supported by the monotonic increase in performance via the hidden states for the last meaningless symbols, such as punctuation, in the prompting strategy. Our codes are available at https://github.com/RyanLiut/LLM_LexSem., Comment: Accepted to Findings of ACL 2024