Search

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests somewhat scattered optimization principles and designs empirically dependent prompt optimizers. Unfortunately, these endeavors lack a structural design, incurring high learning costs and it is not conducive to the iterative updating of prompts, especially for non-AI experts. Inspired by structured reusable programming languages, we propose LangGPT, a structural prompt design framework. Furthermore, we introduce Minstrel, a multi-generative agent system with reflection to automate the generation of structural prompts. Experiments and the case study illustrate that structural prompts generated by Minstrel or written manually significantly enhance the performance of LLMs. Furthermore, we analyze the ease of use of structural prompts through a user survey in our online community., Comment: arXiv admin note: text overlap with arXiv:2402.16929

Optically observing and monitoring moving objects, both natural and artificial, is important to human space security. Non-sidereal tracking can improve the system's limiting magnitude for moving objects, which benefits the surveillance. However, images with non-sidereal tracking include complex background, as well as objects with different brightness and moving mode, posing a significant challenge for accurate multi-object detection in such images, especially in wide field of view (WFOV) telescope images. To achieve a higher detection precision in a higher speed, we proposed a novel object detection method, which combines the source feature extraction and the neural network. First, our method extracts object features from optical images such as centroid, shape, and flux. Then it conducts a naive labeling based on those features to distinguish moving objects from stars. After balancing the labeled data, we employ it to train a neural network aimed at creating a classification model for point-like and streak-like objects. Ultimately, based on the neural network model's classification outcomes, moving objects whose motion modes consistent with the tracked objects are detected via track association, while objects with different motion modes are detected using morphological statistics. The validation, based on the space objects images captured in target tracking mode with the 1-meter telescope at Nanshan, Xinjiang Astronomical Observatory, demonstrates that our method achieves 94.72% detection accuracy with merely 5.02% false alarm rate, and a processing time of 0.66s per frame. Consequently, our method can rapidly and accurately detect objects with different motion modes from wide-field images with non-sidereal tracking.

Multi-hop Question Answering (QA) necessitates complex reasoning by integrating multiple pieces of information to resolve intricate questions. However, existing QA systems encounter challenges such as outdated information, context window length limitations, and an accuracy-quantity trade-off. To address these issues, we propose a novel framework, the Hierarchical Retrieval-Augmented Generation Model with Rethink (HiRAG), comprising Decomposer, Definer, Retriever, Filter, and Summarizer five key modules. We introduce a new hierarchical retrieval strategy that incorporates both sparse retrieval at the document level and dense retrieval at the chunk level, effectively integrating their strengths. Additionally, we propose a single-candidate retrieval method to mitigate the limitations of multi-candidate retrieval. We also construct two new corpora, Indexed Wikicorpus and Profile Wikicorpus, to address the issues of outdated and insufficient knowledge. Our experimental results on four datasets demonstrate that HiRAG outperforms state-of-the-art models across most metrics, and our Indexed Wikicorpus is effective. The code for HiRAG is available at https://github.com/2282588541a/HiRAG, Comment: undereview

Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer from heavy computational burden and slow inference due to the complex calculation of multi-head self-attention (MSA), seriously hindering their practical application and deployment. In this work, we present an efficient SR model to mitigate the dilemma between model efficiency and SR performance, which is dubbed Entropy Attention and Receptive Field Augmentation network (EARFA), and composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA). From the perspective of information theory, EA increases the entropy of intermediate features conditioned on a Gaussian distribution, providing more informative input for subsequent reasoning. On the other hand, SLKA extends the receptive field of SR models with the assistance of channel shifting, which also favors to boost the diversity of hierarchical features. Since the implementation of EA and SLKA does not involve complex computations (such as extensive matrix multiplications), the proposed method can achieve faster nonlinear inference than Transformer-based SR models while maintaining better SR performance. Extensive experiments show that the proposed model can significantly reduce the delay of model inference while achieving the SR performance comparable with other advanced models., Comment: Accepted to ACM MM 2024

We propose Diff-Shadow, a global-guided diffusion model for high-quality shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover images with obvious boundaries. In contrast, diffusion-based methods can generate better content but ignore global information, resulting in inconsistent illumination. In this work, we combine the advantages of diffusion models and global guidance to realize shadow-free restoration. Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images. A Reweight Cross Attention (RCA) module is designed to integrate global contextural information of non-shadow regions into the local branch. We further design a Global-guided Sampling Strategy (GSS) that mitigates patch boundary issues and ensures consistent illumination across shaded and unshaded regions in the recovered image. Comprehensive experiments on three publicly standard datasets ISTD, ISTD+, and SRD have demonstrated the effectiveness of Diff-Shadow. Compared to state-of-the-art methods, our method achieves a significant improvement in terms of PSNR, increasing from 32.33dB to 33.69dB on the SRD dataset. Codes will be released.

Efficient and lightweight single-image super-resolution (SISR) has achieved remarkable performance in recent years. One effective approach is the use of large kernel designs, which have been shown to improve the performance of SISR models while reducing their computational requirements. However, current state-of-the-art (SOTA) models still face problems such as high computational costs. To address these issues, we propose the Large Kernel Distillation Network (LKDN) in this paper. Our approach simplifies the model structure and introduces more efficient attention modules to reduce computational costs while also improving performance. Specifically, we employ the reparameterization technique to enhance model performance without adding extra cost. We also introduce a new optimizer from other tasks to SISR, which improves training speed and performance. Our experimental results demonstrate that LKDN outperforms existing lightweight SR methods and achieves SOTA performance., Comment: Accepted to CVPR workshop 2023

The early detection and precise diagnosis of liver tumors are tasks of critical clinical value, yet they pose significant challenges due to the high heterogeneity and variability of liver tumors. In this work, a precise LIver tumor DIAgnosis network on multi-phase contrast-enhance CT, named LIDIA, is proposed for real-world scenario. To fully utilize all available phases in contrast-enhanced CT, LIDIA first employs the iterative fusion module to aggregate variable numbers of image phases, thereby capturing the features of lesions at different phases for better tumor diagnosis. To effectively mitigate the high heterogeneity problem of liver tumors, LIDIA incorporates asymmetric contrastive learning to enhance the discriminability between different classes. To evaluate our method, we constructed a large-scale dataset comprising 1,921 patients and 8,138 lesions. LIDIA has achieved an average AUC of 93.6% across eight different types of lesions, demonstrating its effectiveness. Besides, LIDIA also demonstrated strong generalizability with an average AUC of 89.3% when tested on an external cohort of 828 patients., Comment: Accepted to MICCAI 2024

Esophageal varices (EV), a serious health concern resulting from portal hypertension, are traditionally diagnosed through invasive endoscopic procedures. Despite non-contrast computed tomography (NC-CT) imaging being a less expensive and non-invasive imaging modality, it has yet to gain full acceptance as a primary clinical diagnostic tool for EV evaluation. To overcome existing diagnostic challenges, we present the Multi-Organ-cOhesion-Network (MOON), a novel framework enhancing the analysis of critical organ features in NC-CT scans for effective assessment of EV. Drawing inspiration from the thorough assessment practices of radiologists, MOON establishes a cohesive multiorgan analysis model that unifies the imaging features of the related organs of EV, namely esophagus, liver, and spleen. This integration significantly increases the diagnostic accuracy for EV. We have compiled an extensive NC-CT dataset of 1,255 patients diagnosed with EV, spanning three grades of severity. Each case is corroborated by endoscopic diagnostic results. The efficacy of MOON has been substantiated through a validation process involving multi-fold cross-validation on 1,010 cases and an independent test on 245 cases, exhibiting superior diagnostic performance compared to methods focusing solely on the esophagus (for classifying severe grade: AUC of 0.864 versus 0.803, and for moderate to severe grades: AUC of 0.832 versus 0.793). To our knowledge, MOON is the first work to incorporate a synchronized multi-organ NC-CT analysis for EV assessment, providing a more acceptable and minimally invasive alternative for patients compared to traditional endoscopy., Comment: Early accepted to MICCAI 2024

Alkaline water electrolysis is considered a commercially viable option for large-scale hydrogen production. However, this process still faces challenges due to the high voltage (>1.65 V at 10 mA cm$^{-2}$) and its limited stability at higher current densities due to the inefficient electron transport kinetics. Herein, a novel cobalt based metallic heterostructure (Co$_3$Mo3N/Co$_4$N/Co/Co) is designed for application for water electrolysis. Operando Raman experiments reveal that the formation of Co$_3$Mo3N/Co$_4$N/Co heterointerface boosts the free water adsorption and dissociation, resulting in a surplus of protons available for subsequent hydrogen production. Furthermore, the altered electronic structure of Co$_3$Mo3N/Co$_4$N/Co heterointerface optimizes the {\Delta}GH of nitrogen atoms at the interface. This synergistic effect between interfacial nitrogen atoms and metal phase cobalt creates highly efficient hydrogen evolution reaction (HER) active sites, thereby enhancing the overall performance. Additionally, the heterostructure exhibits a rapid OH- adsorption rate, coupled with a strong adsorption strength, leading to improved oxygen evolution reaction (OER) performance. Crucially, the metallic heterojunction facilitates fast electron transport, expediting the aforementioned reaction steps and ultimately improving the overall efficiency of water splitting. The water electrolyzer with Co$_3$Mo3N/Co$_4$N/Co/Co as a catalyst exhibits outstanding performance, requiring an impressively low cell voltage of 1.58 V at 10 mA cm$^{-2}$ and maintaining approximately 100% retention over a remarkable 100 h duration at 200 mA cm$^{-2}$. This performance significantly exceeds that of the commercial Pt/C || RuO2 electrolyzer.

Multispectral photoacoustic tomography (PAT) is an imaging modality that utilizes the photoacoustic effect to achieve non-invasive and high-contrast imaging of internal tissues. However, the hardware cost and computational demand of a multispectral PAT system consisting of up to thousands of detectors are huge. To address this challenge, we propose an ultra-sparse spiral sampling strategy for multispectral PAT, which we named U3S-PAT. Our strategy employs a sparse ring-shaped transducer that, when switching excitation wavelengths, simultaneously rotates and translates. This creates a spiral scanning pattern with multispectral angle-interlaced sampling. To solve the highly ill-conditioned image reconstruction problem, we propose a self-supervised learning method that is able to introduce structural information shared during spiral scanning. We simulate the proposed U3S-PAT method on a commercial PAT system and conduct in vivo animal experiments to verify its performance. The results show that even with a sparse sampling rate as low as 1/30, our U3S-PAT strategy achieves similar reconstruction and spectral unmixing accuracy as non-spiral dense sampling. Given its ability to dramatically reduce the time required for three-dimensional multispectral scanning, our U3S-PAT strategy has the potential to perform volumetric molecular imaging of dynamic biological activities.

Existing benchmarks for fake news detection have significantly contributed to the advancement of models in assessing the authenticity of news content. However, these benchmarks typically focus solely on news pertaining to a single semantic topic or originating from a single platform, thereby failing to capture the diversity of multi-domain news in real scenarios. In order to understand fake news across various domains, the external knowledge and fine-grained annotations are indispensable to provide precise evidence and uncover the diverse underlying strategies for fabrication, which are also ignored by existing benchmarks. To address this gap, we introduce a novel multi-domain knowledge-enhanced benchmark with fine-grained annotations, named \textbf{FineFake}. FineFake encompasses 16,909 data samples spanning six semantic topics and eight platforms. Each news item is enriched with multi-modal content, potential social context, semi-manually verified common knowledge, and fine-grained annotations that surpass conventional binary labels. Furthermore, we formulate three challenging tasks based on FineFake and propose a knowledge-enhanced domain adaptation network. Extensive experiments are conducted on FineFake under various scenarios, providing accurate and reliable benchmarks for future endeavors. The entire FineFake project is publicly accessible as an open-source repository at \url{https://github.com/Accuser907/FineFake}.

In three dimensions, quasi-one-dimensional (Q1D) transport has traditionally been associated with systems featuring a Q1D chain structure. Here, based on first-principle calculations, we go beyond this understanding to show that the Q1D transport can also be realized in certain three-dimensional (3D) altermagnetic (AM) metals with a topological nodal net in momentum space but lacking Q1D chain structure in real space, including the existing compounds $\beta$-Fe$_2$(PO$_4$)O, Co$_2$(PO$_4$)O, and LiTi$_2$O$_4$. These materials exhibit an AM ground state and feature an ideal crossed $Z^3$ Weyl nodal line in each spin channel around Fermi level, formed by three straight and flat nodal lines traversing the entire Brillouin zone. These nodal lines eventually lead to an AM $Z^3$ nodal net. Surprisingly, the electronic conductivity $\sigma_{xx}$ in these topological nodal net metals is dozens of times larger than $\sigma_{yy}$ and $\sigma_{zz}$ in the up-spin channel, while $\sigma_{yy}$ dominates transport in the down-spin channel. This suggests a distinctive Q1D transport signature in each spin channel, and the principal moving directions for the two spin channels are orthogonal, resulting in Q1D direction-dependent spin transport. This novel phenomenon cannot be found in both conventional 3D bulk materials and Q1D chain materials. In particular, the Q1D spin transport gradually disappears as the Fermi energy moves away from the nodal net, further confirming its topological origin. Our work not only enhances the comprehension of topological physics in altermagnets but also opens a new direction for the exploration of topological spintronics.

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to instruct LLMs proficiently poses a challenge for non-AI experts. Existing research in prompt engineering suggests somewhat scattered optimization principles and designs empirically dependent prompt optimizers. Unfortunately, these endeavors lack a structured design template, incurring high learning costs and resulting in low reusability. In addition, it is not conducive to the iterative updating of prompts. Inspired by structured reusable programming languages, we propose LangGPT, a dual-layer prompt design framework as the programming language for LLMs. LangGPT has an easy-to-learn normative structure and provides an extended structure for migration and reuse. Experiments illustrate that LangGPT significantly enhances the performance of LLMs. Moreover, the case study shows that LangGPT leads LLMs to generate higher-quality responses. Furthermore, we analyzed the ease of use and reusability of LangGPT through a user survey in our online community.

Two-dimensional topological superconductor (TSC) represents an exotic quantum material with quasiparticle excitation manifesting in dispersive Majorana mode (DMM) at the boundaries. A domain-wall DMM can arise at the boundary between two TSC domains with opposite Chern numbers or with a $\pi$-phase shift in their pairing gap, which can only be tuned by magnetic field. Here we propose the concept of ferroelectric (FE) TSC, which not only enriches the domain-wall DMMs but also significantly makes them electrically tunable. The $\pi$-phase shift of the pairing gap is shown to be attained between two TSC domains of opposite FE polarization, and switchable by reversing FE polarizations. In combination with ferromagnetic (FM) polarization, the domain wall can host helical, doubled chiral, and fused DMMs, which can be transferred into each other by changing the direction of electrical and/or magnetic field. Furthermore, based on first-principles calculations, we demonstrate $\alpha$-In$_2$Se$_3$ to be a promising FE TSC candidate in proximity with a FM layer and a superconductor substrate. We envision that FE TSC will significantly ease the manipulation of DMM by electrical field to realize fault-tolerant quantum computation., Comment: 14 pages, 4 figures

Cognitive diagnosis is a crucial task in computational education, aimed at evaluating students' proficiency levels across various knowledge concepts through exercises. Current models, however, primarily rely on students' answered exercises, neglecting the complex and rich information contained in un-interacted exercises. While recent research has attempted to leverage the data within un-interacted exercises linked to interacted knowledge concepts, aiming to address the long-tail issue, these studies fail to fully explore the informative, un-interacted exercises related to broader knowledge concepts. This oversight results in diminished performance when these models are applied to comprehensive datasets. In response to this gap, we present the Collaborative-aware Mixed Exercise Sampling (CMES) framework, which can effectively exploit the information present in un-interacted exercises linked to un-interacted knowledge concepts. Specifically, we introduce a novel universal sampling module where the training samples comprise not merely raw data slices, but enhanced samples generated by combining weight-enhanced attention mixture techniques. Given the necessity of real response labels in cognitive diagnosis, we also propose a ranking-based pseudo feedback module to regulate students' responses on generated exercises. The versatility of the CMES framework bolsters existing models and improves their adaptability. Finally, we demonstrate the effectiveness and interpretability of our framework through comprehensive experiments on real-world datasets., Comment: 9 pages, 6 figures, accepted by AAAI-24 (AAAI 2024)

Photoacoustic tomography (PAT) is a promising imaging technique that can visualize the distribution of chromophores within biological tissue. However, the accuracy of PAT imaging is compromised by light fluence (LF), which hinders the quantification of light absorbers. Currently, model-based iterative methods are used for LF correction, but they require significant computational resources due to repeated LF estimation based on differential light transport models. To improve LF correction efficiency, we propose to use Fourier neural operator (FNO), a neural network specially designed for solving differential equations, to learn the forward projection of light transport in PAT. Trained using paired finite-element-based LF simulation data, our FNO model replaces the traditional computational heavy LF estimator during iterative correction, such that the correction procedure is significantly accelerated. Simulation and experimental results demonstrate that our method achieves comparable LF correction quality to traditional iterative methods while reducing the correction time by over 30 times.

High-resolution remote sensing (HRS) semantic segmentation extracts key objects from high-resolution coverage areas. However, objects of the same category within HRS images generally show significant differences in scale and shape across diverse geographical environments, making it difficult to fit the data distribution. Additionally, a complex background environment causes similar appearances of objects of different categories, which precipitates a substantial number of objects into misclassification as background. These issues make existing learning algorithms sub-optimal. In this work, we solve the above-mentioned problems by proposing a High-resolution remote sensing network (Hi-ResNet) with efficient network structure designs, which consists of a funnel module, a multi-branch module with stacks of information aggregation (IA) blocks, and a feature refinement module, sequentially, and Class-agnostic Edge Aware (CEA) loss. Specifically, we propose a funnel module to downsample, which reduces the computational cost, and extract high-resolution semantic information from the initial input image. Secondly, we downsample the processed feature images into multi-resolution branches incrementally to capture image features at different scales and apply IA blocks, which capture key latent information by leveraging attention mechanisms, for effective feature aggregation, distinguishing image features of the same class with variant scales and shapes. Finally, our feature refinement module integrate the CEA loss function, which disambiguates inter-class objects with similar shapes and increases the data distribution distance for correct predictions. With effective pre-training strategies, we demonstrated the superiority of Hi-ResNet over state-of-the-art methods on three HRS segmentation benchmarks.

The discovery of the topological states has become a key topic in condensed matter physics with the focus evolving from the Dirac or Weyl points to high-dimension topological states of the nodal lines and nodal surfaces. For a topological material to manifest its quantum properties and become useful in applications, the topological states need to be genuine and clean so that they lie close to the Fermi level without other trivial bands existing at the Fermi level. While a number of high-dimension topological materials are predicted, only a few of them have been synthesized and confirmed and the genuine and clean ones are especially scarce. Here we report the realization of the genuine clean multiple high-dimension topological states in NaAlSi. By performing high-resolution angle-resolved photoemission measurements and band structure calculations, we have observed two sets of nodal surfaces and the formation of two homocentric nodal ring states in NaAlSi. The observed nodal rings are distinct in that the inner one is a type-{\uppercase\expandafter{\romannumeral1}} nodal ring while the outer one is a type-{\uppercase\expandafter{\romannumeral1}} nodal ring embedded with four type-{\uppercase\expandafter{\romannumeral3}} nodal points. All the bands involved in the nodal rings lie very close to the Fermi level with no other trivial bands coexisting at the Fermi level. These observations make NaAlSi a desirable topological material to explore for novel quantum states and exotic properties.

The superconductor SnTaS$_{2}$ is theoretically predicted to be an intriguing topological nodal line semimetal without consideration of spin-orbit coupling. By carrying out angle-resolved photoemission (ARPES) and spin-resolved ARPES measurements combined with band structure calculations, we have provided a complete picture of the electronic structure and spin polarization property for the prominent surface states of SnTaS$_{2}$. The low-energy electronic states are dominated by surface states; two of them are from the S-terminated surface, while four of them are from the Sn-terminated surface. These give rise to interesting Fermi surface topology of SnTaS$_{2}$: three pockets located at $\bar\Gamma$, $\bar{M}$ and $\bar{K}$ for the S-terminated surface and two pockets surrounding $\bar\Gamma$ and $\bar{K}$ for the Sn-terminated surface. We further reveal that two surface states that cross the Fermi level are spin-polarized. Since SnTaS$_{2}$ is also a superconductor, our observations indicate that it may provide a new platform to explore topological superconductivity and other exotic properties.

Electrides are a unique class of electron-rich materials where excess electrons are localized in interstitial lattice sites as anions, leading to a range of unique properties and applications. While hundreds of electrides have been discovered in recent years, magnetic electrides have received limited attention, with few investigations into their fundamental physics and practical applications. In this work, 51 magnetic electrides (12 antiferromagnetic, 13 ferromagnetic, and 26 interstitial-magnetic) were identified using high-throughput computational screening methods and the latest Material Project database. Based on their compositions, these magnetic electrides can be classified as magnetic semiconductors, metals, or half-metals, each with unique topological states and excellent catalytic performance for N2 fixation due to their low work functions and excess electrons. The novel properties of magnetic electrides suggest potential applications in spintronics, topological electronics, electron emission, and as high-performance catalysts. This work marks the beginning of a new era in the identification, investigation, and practical applications of magnetic electrides.

Real Chern insulators have attracted great interest, but so far, their material realization is limited to nonmagnetic crystals and to systems without spin-orbit coupling. Here, we reveal magnetic real Chern insulator (MRCI) state in a recently synthesized metal-organic framework material Co3(HITP)2. Its ground state with in-plane ferromagnetic ordering hosts a nontrivial real Chern number, enabled by the C2zT symmetry and robust against spin-orbit coupling. Distinct from previous nonmagnetic examples, the topological corner zero-modes of MRCI are spin-polarized. Furthermore, under small tensile strains, the material undergoes a topological phase transition from MRCI to a magnetic double-Weyl semimetal phase, via a pseudospin-1 critical state. Similar physics can also be found in closely related materials Mn3(HITP)2 and Fe3(HITP)2, which are also existing. Possible experimental detections and implications of an emerging magnetic flat band in the system are discussed., Comment: 6 pages,5 figures

The elliptic azimuthal anisotropy coefficient ($v_{2}$) of the identified particles at midrapidity ($|\eta|<0.8$) was investigated in p--Pb collisions at $\sqrt{s_\mathrm{NN}}=$ 5.02 TeV using a multi-phase transport model (AMPT). The calculations of differential $v_{2}$ based on the advanced flow extraction method of light flavor hadrons (pions, kaons, protons, and $\Lambda$) in small collision systems were extended to a wider transverse momentum ($p_{\mathrm{T}}$) range of up to 8 GeV/$c$ for the first time. The string-melting version of the AMPT model provides a good description of the measured $p_{\mathrm{T}}$-differential $v_{2}$ of the mesons but exhibits a slight deviation from the baryon $v_{2}$. In addition, we observed the features of mass ordering at low $p_{\mathrm{T}}$ and the approximate number of constituent quarks (NCQ) scaled at intermediate $p_{\mathrm{T}}$. Moreover, we demonstrate that hadronic rescattering does not have a significant impact on $v_{2}$ in p--Pb collisions for different centrality selections, whereas partonic scattering dominates in generating the elliptic anisotropy of the final particles. This study provides further insight into the origin of collective-like behavior in small collision systems and has referential value for future measurements of azimuthal anisotropy., Comment: 9 pages, 9 figures

mRNA therapy is gaining worldwide attention as an emerging therapeutic approach. The widespread use of mRNA vaccines during the COVID-19 outbreak has demonstrated the potential of mRNA therapy. As mRNA-based drugs have expanded and their indications have broadened, more patents for mRNA innovations have emerged. The global patent landscape for mRNA therapy has not yet been analyzed, indicating a research gap in need of filling, from new technology to productization. This study uses social network analysis with the patent quality assessment to investigate the temporal trends, citation relationship, and significant litigation for 16,101 mRNA therapy patents and summarizes the hot topics and potential future directions for this industry. The information obtained in this study not only may be utilized as a tool of knowledge for researchers in a comprehensive and integrated way but can also provide inspiration for efficient production methods for mRNA drugs. This study shows that infectious diseases and cancer are currently the primary applications for mRNA drugs. Emerging patent activity and lawsuits in this field are demonstrating that delivery technology remains one of the key challenges in the field and that drug-targeting research in combination with vector technology will be one of the major directions for the industry going forward. With significant funding, new organizations have developed novel delivery technologies in an attempt to break into the patent thicket established by companies such as Arbutus. The global mRNA therapeutic landscape is undergoing a multifaceted development pattern, and the monopoly of giant companies is being challenged., Comment: I have received requests from co-authors and funding agencies to withdraw the manuscript

Multimodal summarization (MS) aims to generate a summary from multimodal input. Previous works mainly focus on textual semantic coverage metrics such as ROUGE, which considers the visual content as supplemental data. Therefore, the summary is ineffective to cover the semantics of different modalities. This paper proposes a multi-task cross-modality learning framework (CISum) to improve multimodal semantic coverage by learning the cross-modality interaction in the multimodal article. To obtain the visual semantics, we translate images into visual descriptions based on the correlation with text content. Then, the visual description and text content are fused to generate the textual summary to capture the semantics of the multimodal content, and the most relevant image is selected as the visual summary. Furthermore, we design an automatic multimodal semantics coverage metric to evaluate the performance. Experimental results show that CISum outperforms baselines in multimodal semantics coverage metrics while maintaining the excellent performance of ROUGE and BLEU., Comment: accepted by SIAM SDM2023

Topological states of matter and their corresponding properties are classical research topics in condensed matter physics. Quite recently, the application of materials that feature these states has been extended to the field of electrochemical catalysis and become an emerging research topic that is receiving increasing interest. In particular, several recent experimental studies performed on topological semimetals have already revealed high catalytic performance towards hydrogen evolution reaction (HER), strongly promoting acceptance of the fresh concept of the topological catalyst. This emerging concept has experienced rapid developments in the last few years, but these developments have been rarely summarized. Herein, we offer a comprehensive review on the state-of-the-art progress in developing topological catalysts for the HER process through topological semimetals such as Weyl semimetals, Dirac semimetals, nodal line semimetals, etc. The course of development, the general research routes, and the fundamental mechanisms in topological catalysts are also systematically analyzed in this review., Comment: 4 figures

Customized keyword spotting (KWS) has great potential to be deployed on edge devices to achieve hands-free user experience. However, in real applications, false alarm (FA) would be a serious problem for spotting dozens or even hundreds of keywords, which drastically affects user experience. To solve this problem, in this paper, we leverage the recent advances in transducer and transformer based acoustic models and propose a new multi-stage customized KWS framework named Cascaded Transducer-Transformer KWS (CaTT-KWS), which includes a transducer based keyword detector, a frame-level phone predictor based force alignment module and a transformer based decoder. Specifically, the streaming transducer module is used to spot keyword candidates in audio stream. Then force alignment is implemented using the phone posteriors predicted by the phone predictor to finish the first stage keyword verification and refine the time boundaries of keyword. Finally, the transformer decoder further verifies the triggered keyword. Our proposed CaTT-KWS framework reduces FA rate effectively without obviously hurting keyword recognition accuracy. Specifically, we can get impressively 0.13 FA per hour on a challenging dataset, with over 90% relative reduction on FA comparing to the transducer based detection model, while keyword recognition accuracy only drops less than 2%., Comment: Accepted by Interspeech 2022

Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain insufficiently studied. Besides, modern semi-supervised speech recognition algorithms either treat unlabeled data indiscriminately or filter out noisy samples with a confidence threshold. The dissimilarities among different unlabeled data are often ignored. In this paper, we propose Censer, a semi-supervised speech recognition algorithm based on self-supervised pre-training to maximize the utilization of unlabeled data. The pre-training stage of Censer adopts wav2vec2.0 and the fine-tuning stage employs an improved semi-supervised learning algorithm from slimIPL, which leverages unlabeled data progressively according to their pseudo labels' qualities. We also incorporate a temporal pseudo label pool and an exponential moving average to control the pseudo labels' update frequency and to avoid model divergence. Experimental results on Libri-Light and LibriSpeech datasets manifest our proposed method achieves better performance compared to existing approaches while being more unified.