Search

The reactions of p+$^{12}$C with triangular 3$\alpha$ structure and spherical structure with incident energies ranging from 5 to 200 MeV/nucleon are simulated by the in the extended-quantum-molecular-dynamics (EQMD) model together with the GEMINI decay process. This paper presents the incident energy dependence of the branching ratios of fragment production and multiplicity, as well as the associated event information entropy. The results indicate that the triangular 3$\alpha$ $^{12}$C has an extra branching ratio for the quasi-elastic reaction compared to the spherical $^{12}$C. This peculiarity of the branching ratios of the triangular 3$\alpha$ $^{12}$C appears as a small dent in the curves of the event information entropy (both the fragment information entropy and the multiplicity information entropy). Therefore, we propose that the event information entropy could be a probe for detecting the $\alpha$-cluster structure., Comment: 9 pages, 7 figures

Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvious, since it is unclear what experiences suit specific LLMs. Previous studies intended to automatically find useful experiences using LLMs, while it is difficult to ensure the effectiveness of the obtained experience. In this paper, we propose Stochastic Experience Optimization (SEO), an iterative approach that finds optimized model-specific experience without modifying model parameters through experience update in natural language. In SEO, we propose a stochastic validation method to ensure the update direction of experience, avoiding unavailing updates. Experimental results on three tasks for three LLMs demonstrate that experiences optimized by SEO can achieve consistently improved performance. Further analysis indicates that SEO-optimized experience can generalize to out-of-distribution data, boosting the performance of LLMs on similar tasks.

We study the $\lambda$-pure global dimension of a Grothendieck category $\cal A$, and provide two different applications about this dimension. We obtain that if the $\lambda$-pure global dimension $\plgldA<\infty$, then (1) The ordinary bounded derived category (where $\cal A$ has enough projective objects) and the bounded $\lambda$-pure one differ only by a homotopy category; (2) The $\lambda$-pure singularity category $\DlsgA =0$. At last, we explore the reason why the general construction of classic Buchweitz-Happel Theorem is not feasible for $\lambda$-pure one.

Like spoken languages, a single sign language expression could correspond to multiple valid textual interpretations. Hence, learning a rigid one-to-one mapping for sign language translation (SLT) models might be inadequate, particularly in the case of limited data. In this work, we introduce a Diverse Sign Language Translation (DivSLT) task, aiming to generate diverse yet accurate translations for sign language videos. Firstly, we employ large language models (LLM) to generate multiple references for the widely-used CSL-Daily and PHOENIX14T SLT datasets. Here, native speakers are only invited to touch up inaccurate references, thus significantly improving the annotation efficiency. Secondly, we provide a benchmark model to spur research in this task. Specifically, we investigate multi-reference training strategies to enable our DivSLT model to achieve diverse translations. Then, to enhance translation accuracy, we employ the max-reward-driven reinforcement learning objective that maximizes the reward of the translated result. Additionally, we utilize multiple metrics to assess the accuracy, diversity, and semantic precision of the DivSLT task. Experimental results on the enriched datasets demonstrate that our DivSLT method achieves not only better translation performance but also diverse translation results.

Molecular dynamics approaches use wave packets as nucleon wave functions to simulate the time evolution of nuclear reactions. It is crucial to activate the momentum fluctuation inherent in each wave packet so that it properly affects the time evolution. In the antisymmetrized molecular dynamics (AMD) model, this has traditionally been done by splitting the wave packets, i.e., by introducing a random fluctuation to the wave packet center of each particle. The present work proposes an improved approach to activate the fluctuation in both the one-body mean-field propagation and the two-nucleon collision processes, consistently based on the gradual or sudden change of the degree of isolation, which is derived from the fragment number function used for the zero-point energy subtraction. This new method is applied to the 12C + 12C and 12C + p reactions at about 100 MeV/nucleon, focusing on the momentum distribution of the 11B fragments produced by one-proton removal from the 12C projectile. The results show that, with the momentum fluctuation suitably activated, the method correctly accounts for the recoil from the removed nucleon to the residue and the 11B momentum distribution is significantly improved, while without activating the fluctuation the distribution is too narrow compared to the experimental data. Furthermore, the AMD results indicate that the momentum distribution consists of two components; one is the high $P_z$ component with a small shift from the beam velocity, resulting from the simple removal of a proton after an energetic collision with a target particle; the other is the low $P_z$ component with a larger peak shift resulting from the decay of an excited 12C nucleus in a longer time scale. The activation of momentum fluctuation mainly affects the high $P_z$ component to broaden it. The role of cluster correlations in this problem is also investigated., Comment: 15 pages, 16 figures, version accepted for publication in Physical Review C

Quantum-mechanics-based transport simulation is of importance for the design of ultra-short channel field-effect transistors (FETs) with its capability of understanding the physical mechanism, while facing the primary challenge of the high computational intensity. Traditional machine learning is expected to accelerate the optimization of FET design, yet its application in this field is limited by the lack of both high-fidelity datasets and the integration of physical knowledge. Here, we introduced a physics-integrated neural network framework to predict the transport curves of sub-5-nm gate-all-around (GAA) FETs using an in-house developed high-fidelity database. The transport curves in the database are collected from literature and our first-principles calculations. Beyond silicon, we included indium arsenide, indium phosphide, and selenium nanowires with different structural phases as the FET channel materials. Then, we built a physical-knowledge-integrated hyper vector neural network (PHVNN), in which five new physical features were added into the inputs for prediction transport characteristics, achieving a sufficiently low mean absolute error of 0.39. In particular, ~98% of the current prediction residuals are within one order of magnitude. Using PHVNN, we efficiently screened out the symmetric p-type GAA FETs that possess the same figures of merit with the n-type ones, which are crucial for the fabrication of homogeneous CMOS circuits. Finally, our automatic differentiation analysis provides interpretable insights into the PHVNN, which highlights the important contributions of our new input parameters and improves the reliability of PHVNN. Our approach provides an effective method for rapidly screening appropriate GAA FETs with the prospect of accelerating the design process of next-generation electronic devices., Comment: 13 pages, 4 figures

While computer vision has proven valuable for medical image segmentation, its application faces challenges such as limited dataset sizes and the complexity of effectively leveraging unlabeled images. To address these challenges, we present a novel semi-supervised, consistency-based approach termed the data-efficient medical segmenter (DEMS). The DEMS features an encoder-decoder architecture and incorporates the developed online automatic augmenter (OAA) and residual robustness enhancement (RRE) blocks. The OAA augments input data with various image transformations, thereby diversifying the dataset to improve the generalization ability. The RRE enriches feature diversity and introduces perturbations to create varied inputs for different decoders, thereby providing enhanced variability. Moreover, we introduce a sensitive loss to further enhance consistency across different decoders and stabilize the training process. Extensive experimental results on both our own and three public datasets affirm the effectiveness of DEMS. Under extreme data shortage scenarios, our DEMS achieves 16.85\% and 10.37\% improvement in dice score compared with the U-Net and top-performed state-of-the-art method, respectively. Given its superior data efficiency, DEMS could present significant advancements in medical segmentation under small data regimes. The project homepage can be accessed at https://github.com/NUS-Tim/DEMS., Comment: Neural Networks Accepted

Recently developed large language models (LLMs) such as ChatGPT, Claude, and Llama have demonstrated impressive abilities, and even surpass human-level performance in several tasks. Despite their success, the resource-intensive demands of these models, requiring significant computational power for both training and inference, limit their deployment to high-performance servers. Additionally, the extensive calculation requirements of the models often lead to increased latency in response times. With the increasing need for LLMs to operate efficiently on CPUs, research about lightweight models that are optimized for CPU inference has emerged. In this work, we introduce GEB-1.3B, a lightweight LLM trained on 550 billion tokens in both Chinese and English languages. We employ novel training techniques, including ROPE, Group-Query-Attention, and FlashAttention-2, to accelerate training while maintaining model performance. Additionally, we fine-tune the model using 10 million samples of instruction data to enhance alignment. GEB-1.3B exhibits outstanding performance on general benchmarks such as MMLU, C-Eval, and CMMLU, outperforming comparative models such as MindLLM-1.3B and TinyLLaMA-1.1B. Notably, the FP32 version of GEB-1.3B achieves commendable inference times on CPUs, with ongoing efforts to further enhance speed through advanced quantization techniques. The release of GEB-1.3B as an open-source model marks a significant contribution to the development of lightweight LLMs, promising to foster further research and innovation in the field., Comment: GEB-1.3B technical report

Few-mode multi-core fiber (FM-MCF) based Space-Division Multiplexing (SDM) systems possess the potential to maximize the number of multiplexed spatial channels per fiber by harnessing both the space (fiber cores) and mode (optical mode per core) dimensions. However, to date, no SDM transmissions over field-deployed FM-MCFs in realistic outdoor settings have been reported, which contrasts with SDM schemes demonstrated using single-mode multi-core fibers (SM-MCFs) installed in practical fiber cable ducts. In this paper, we present the successful demonstration of bidirectional SDM transmission over a 5-km field-deployed seven ring-core fiber (7-RCF) with a cladding diameter of 178 ${\mu}$m, achieving a Spectral Efficiency (SE) of 2$\times$201.6 bit/s/Hz. This work establishes a new record for the highest SE attained in SDM demonstrations utilizing field-deployed fiber cables, achieving an approximate 10x increase compared to the SE of reported field-deployed optical fiber cable transmission systems. Notably, these results are realized through the utilization of small-scale modular 4$\times$4 multiple-input multiple-output (MIMO) processing with a time-domain equalization (TDE) tap number not exceeding 15, maintaining a complexity per unit capacity comparable to that of MIMO equalization in SDM demonstrations employing weakly coupled SM-MCF cables. These results underscore the significant potential for achieving heightened SE and expanding capacity per individual fiber using SDM techniques in practical applications., Comment: 17 pages, 8 figures

In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and complex twisted structures has challenged traditional computational methods, both ab initio and machine-learning-based, due to their computationally intensive iterative processes. To address these scalability issues, here we introduce DeepRelax, a deep generative model capable of performing geometric crystal structure relaxation rapidly and without iterations. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. We demonstrate DeepRelax's reliability and robustness by applying it to five diverse databases, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high accuracy and efficiency, validated by density functional theory calculations. Finally, we enhance its trustworthiness by integrating uncertainty quantification. This work significantly accelerates computational workflows, offering a robust and trustworthy machine-learning method for material discovery and advancing the application of AI for science. Code for DeepRelax is available at https://github.com/Shen-Group/DeepRelax.

Two-dimensional (2D) multiferroic materials with coexisting ferroelectricity and ferromagnetism have garnered substantial attention for their intriguing physical properties and diverse promising applications in spintronics. For example, multiferroic materials with electronically controlled broken central symmetry provide a versatile platform for designing and manipulating topological skyrmions and diverse spintronic applications. Here, we investigate the complex magnetic properties of room-temerature multiferroic material MoPtGe2S6 and its electrical control of topological skyrmions using first-principles calculations and atomistic micromagnetic simulations. A sizable Dzyaloshinskii-Moriya interaction (DMI) (2.1 meV) is found in the multiferroic material MoPtGe2S6 with an electrically polarized ground state. The magnetic skyrmions can be stabilized in monolayer MoPtGe2S6 under zero magnetic field, and the chirality of skyrmions can be reversed with electric field-induced flipping of electrical polarization due to the reversed chirality of the DMI. Furthermore, an external magnetic fielc can reverse the magnetization direction and topological charge of the skyrmions as well as tune the size of skyrmions. These results demonstrate that the monolayer MoPtGe2S6 can enrich the 2D skyrmion community and pave the way for electronically controlled spintronic devices., Comment: 24 pages, 7 figures

This study ventures into the dynamic realm of ecosystem orchestration for industrial firms, emphasizing its significance in maintaining competitive advantage in the digital era. The fragmented research on this important subject poses challenges for firms aiming to navigate and capitalize on ecosystem orchestration. To bridge this knowledge gap, we conducted a comprehensive qualitative meta-analysis of 31 case studies and identified multifaceted orchestration practices employed by industrial firms. The core contribution of this research is the illumination of five interdependent but interrelated orchestration practices: strategic design, relational, resource integration, technological, and innovation. Together, these practices are synthesized into an integrative framework termed the "Stirring Model," which serves as a practical guide to the orchestration practices. Furthermore, the conceptual framework clarifies the synergy between the identified practices and highlights their collective impact. This study proposes theoretical and practical implications for ecosystem orchestration literature and suggests avenues for further research.

The rapid advancement of large language models has revolutionized various applications but also raised crucial concerns about their potential to perpetuate biases and unfairness when deployed in social media contexts. Evaluating LLMs' potential biases and fairness has become crucial, as existing methods rely on limited prompts focusing on just a few groups, lacking a comprehensive categorical perspective. In this paper, we propose evaluating LLM biases from a group fairness lens using a novel hierarchical schema characterizing diverse social groups. Specifically, we construct a dataset, GFair, encapsulating target-attribute combinations across multiple dimensions. In addition, we introduce statement organization, a new open-ended text generation task, to uncover complex biases in LLMs. Extensive evaluations of popular LLMs reveal inherent safety concerns. To mitigate the biases of LLM from a group fairness perspective, we pioneer a novel chain-of-thought method GF-Think to mitigate biases of LLMs from a group fairness perspective. Experimental results demonstrate its efficacy in mitigating bias in LLMs to achieve fairness., Comment: Work in progress

Most machine learning (ML) models in Materials Science are developed by global geometric features, often falling short in describing localized characteristics, like molecular adsorption on materials. In this study, we introduce a local environment framework that extracts local features from crystal structures to portray the environment surrounding specific adsorption sites. Upon OC20 database (~20,000 3D entries), we apply our local environment framework on several ML models, such as random forest, convolutional neural network, and graph neural network. It is found that our framework achieves remarkable prediction accuracy in predicting molecular adsorption energy, significantly outperforming other examined global-environment-based models. Moreover, the employment of this framework reduces data requirements and augments computational speed, specifically for deep learning algorithms. Finally, we directly apply our Local Environment ResNet (LERN) on a small 2DMatPedia database (~2,000 2D entries), which also achieves highly accurate prediction, demonstrating the model transferability and remarkable data efficiency. Overall, the prediction accuracy, data-utilization efficiency, and transferability of our local-environment-based ML framework hold a promising high applicability across a broad molecular adsorption field, such as catalysis and sensor technologies., Comment: 6 figures

In modern computational materials science, deep learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional simulations. However, existing models typically sacrifice either accuracy or efficiency. Moreover, lightweight models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs. Here, we introduce a lightweight equivariant interaction graph neural network (LEIGNN) that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals. Rather than relying on higher-order representations, LEIGNN employs a scalar-vector dual representation to encode equivariant features. By learning geometric symmetry information, our model remains lightweight while ensuring prediction accuracy and robustness through the equivariance. Our results show that LEIGNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets, which include catalysts, molecules, and organic isomers. Furthermore, we conduct molecular dynamics (MD) simulations using the LEIGNN force field across solid, liquid, and gas systems. It is found that LEIGNN can achieve the accuracy of \textit{ab initio} MD across all examined systems.

The technique of conventional ferromagnet/heavy-metal spin-orbit torque (SOT) offers significant potential for enhancing the efficiency of magnetic memories. However, it faces fundamental physical limitations, including hunting effects from the metallic layer, broken symmetry for enabling antidamping switching, spin scattering caused by interfacial defects, and sensitivity to stray magnetic fields. To address these issues, we here propose a van der Waals (vdW) field-free SOT antiferromagnetic memory using a vdW bilayer LaBr$_2$ (an antiferromagnet with perpendicular magnetic anisotropy) and a monolayer T$_d$ phase WTe$_2$ (a Weyl semimetal with broken inversion symmetry). By systematically employing density functional theory in conjunction with non-equilibrium Green's function methods and macrospin simulations, we demonstrate that the proposed vdW SOT devices exhibit remarkably low critical current density approximately 10 MA/cm$^2$ and rapid field-free magnetization switching in 250 ps. This facilitates excellent write performance with extremely low energy consumption. Furthermore, the device shows a significantly low read error rate, as evidenced by a high tunnel magnetoresistance ratio of up to 4250%. The superior write and read performance originates from the unique strong on-site (insulating phase) and off-site (magnetic phase) Coulomb interactions in electride LaBr$_2$, a large non-zero z-component polarization in WTe$_2$, and the proximity effect between them.

Palmprint recently shows great potential in recognition applications as it is a privacy-friendly and stable biometric. However, the lack of large-scale public palmprint datasets limits further research and development of palmprint recognition. In this paper, we propose a novel realistic pseudo-palmprint generation (RPG) model to synthesize palmprints with massive identities. We first introduce a conditional modulation generator to improve the intra-class diversity. Then an identity-aware loss is proposed to ensure identity consistency against unpaired training. We further improve the B\'ezier palm creases generation strategy to guarantee identity independence. Extensive experimental results demonstrate that synthetic pretraining significantly boosts the recognition model performance. For example, our model improves the state-of-the-art B\'ezierPalm by more than $5\%$ and $14\%$ in terms of TAR@FAR=1e-6 under the $1:1$ and $1:3$ Open-set protocol. When accessing only $10\%$ of the real training data, our method still outperforms ArcFace with $100\%$ real training data, indicating that we are closer to real-data-free palmprint recognition., Comment: 12 pages,8 figures

Data augmentation (DA) has been widely leveraged in computer vision to alleviate the data shortage, whereas the DA in medical image analysis (MIA) faces multiple challenges. The prevalent DA approaches in MIA encompass conventional DA, synthetic DA, and automatic DA. However, utilizing these approaches poses various challenges such as experience-driven design and intensive computation cost. Here, we propose an efficient and effective automatic DA method termed MedAugment. We propose a pixel augmentation space and spatial augmentation space and exclude the operations that can break medical details and features, such as severe color distortions or structural alterations that can compromise image diagnostic value. Besides, we propose a novel sampling strategy by sampling a limited number of operations from the two spaces. Moreover, we present a hyperparameter mapping relationship to produce a rational augmentation level and make the MedAugment fully controllable using a single hyperparameter. These configurations settle the differences between natural and medical images, such as high sensitivity to certain attributes such as brightness and posterize. Extensive experimental results on four classification and four segmentation datasets demonstrate the superiority of MedAugment. Compared with existing approaches, the proposed MedAugment serves as a more suitable yet general processing pipeline for medical images without producing color distortions or structural alterations and involving negligible computational overhead. We emphasize that our method can serve as a plugin for arbitrary projects without any extra training stage, thereby holding the potential to make a valuable contribution to the medical field, particularly for medical experts without a solid foundation in deep learning. Code is available at https://github.com/NUS-Tim/MedAugment., Comment: 29 pages, 8 figures

Empathy is a crucial factor in open-domain conversations, which naturally shows one's caring and understanding to others. Though several methods have been proposed to generate empathetic responses, existing works often lead to monotonous empathy that refers to generic and safe expressions. In this paper, we propose to use explicit control to guide the empathy expression and design a framework DiffusEmp based on conditional diffusion language model to unify the utilization of dialogue context and attribute-oriented control signals. Specifically, communication mechanism, intent, and semantic frame are imported as multi-grained signals that control the empathy realization from coarse to fine levels. We then design a specific masking strategy to reflect the relationship between multi-grained signals and response tokens, and integrate it into the diffusion model to influence the generative process. Experimental results on a benchmark dataset EmpatheticDialogue show that our framework outperforms competitive baselines in terms of controllability, informativeness, and diversity without the loss of context-relatedness., Comment: accepted by ACL 2023 main conference (Oral)

Cross-lingual transfer is important for developing high-quality chatbots in multiple languages due to the strongly imbalanced distribution of language resources. A typical approach is to leverage off-the-shelf machine translation (MT) systems to utilize either the training corpus or developed models from high-resource languages. In this work, we investigate whether it is helpful to utilize MT at all in this task. To do so, we simulate a low-resource scenario assuming access to limited Chinese dialog data in the movie domain and large amounts of English dialog data from multiple domains. Experiments show that leveraging English dialog corpora can indeed improve the naturalness, relevance and cross-domain transferability in Chinese. However, directly using English dialog corpora in its original form, surprisingly, is better than using its translated version. As the topics and wording habits in daily conversations are strongly culture-dependent, MT can reinforce the bias from high-resource languages, yielding unnatural generations in the target language. Considering the cost of translating large amounts of text and the strong effects of the translation quality, we suggest future research should rather focus on utilizing the original English data for cross-lingual transfer in dialog generation. We perform extensive human evaluations and ablation studies. The analysis results, together with the collected dataset, are presented to draw attention towards this area and benefit future research.

Large pre-trained code generation models, such as OpenAI Codex, can generate syntax- and function-correct code, making the coding of programmers more productive and our pursuit of artificial general intelligence closer. In this paper, we introduce CodeGeeX, a multilingual model with 13 billion parameters for code generation. CodeGeeX is pre-trained on 850 billion tokens of 23 programming languages as of June 2022. Our extensive experiments suggest that CodeGeeX outperforms multilingual code models of similar scale for both the tasks of code generation and translation on HumanEval-X. Building upon HumanEval (Python only), we develop the HumanEval-X benchmark for evaluating multilingual models by hand-writing the solutions in C++, Java, JavaScript, and Go. In addition, we build CodeGeeX-based extensions on Visual Studio Code, JetBrains, and Cloud Studio, generating 4.7 billion tokens for tens of thousands of active users per week. Our user study demonstrates that CodeGeeX can help to increase coding efficiency for 83.4% of its users. Finally, CodeGeeX is publicly accessible and in Sep. 2022, we open-sourced its code, model weights (the version of 850B tokens), API, extensions, and HumanEval-X at https://github.com/THUDM/CodeGeeX.

Recent studies demonstrate that novel 2D triphosphides semiconductors possess high carrier mobility and promising thermoelectric performance, while the carrier transport behaviors in 2D semimetal triphosphides have never been elucidated before. Herein, using the first-principles calculations and Boltzmann transport theory, we reveal that the electron-phonon coupling can be significant and thus greatly inhibits the electron and phonon transport in electron-doped BP3 and CP3. The intrinsic heat transport capacity of flexural acoustic phonon modes in the wrinkle structure is largely suppressed arising from the strong out-of-plane phonon scatterings, leading to the low phonon thermal conductivity of 1.36 and 5.33 W/(mK) for BP3 and CP3 at room temperature, and at high doping level, the enhanced scattering from electron diminishes the phonon thermal conductivity by 71% and 54% for BP3 and CP3, respectively. Instead, electron thermal conductivity shows nonmonotonic variations with the increase of doping concentration, stemming from the competition between electron-phonon scattering rates and electron group velocity. It is worth noting that the heavy-doping effect induced strong scattering from phonon largely suppresses the electron transport and reduces electron thermal conductivity to the magnitude of phonon thermal conductivity. This work sheds light on the electron and phonon transport properties in semimetal triphosphides monolayer and provides an efficient avenue for the modulation of carrier transport by doping-induced electron-phonon coupling effect.

In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to take advantage of both schemes remains a challenging problem. In this paper, we propose a novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods. Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps. TDE aligns the feature spaces of heatmap-based and regression-based models by introducing tokenization, while Simulated Heatmaps transfer explicit guidance (distribution and confidence) from teacher heatmaps into student models. Extensive experiments show that the proposed DistilPose can significantly improve the performance of the regression-based models while maintaining efficiency. Specifically, on the MSCOCO validation dataset, DistilPose-S obtains 71.6% mAP with 5.36M parameter, 2.38 GFLOPs and 40.2 FPS, which saves 12.95x, 7.16x computational cost and is 4.9x faster than its teacher model with only 0.9 points performance drop. Furthermore, DistilPose-L obtains 74.4% mAP on MSCOCO validation dataset, achieving a new state-of-the-art among predominant regression-based models., Comment: accepted by CVPR2023

The COVID-19 pandemic has resulted in hundreds of million cases and numerous deaths worldwide. Here, we develop a novel classification network CECT by controllable ensemble convolutional neural network and transformer to provide a timely and accurate COVID-19 diagnosis. The CECT is composed of a parallel convolutional encoder block, an aggregate transposed-convolutional decoder block, and a windowed attention classification block. Each block captures features at different scales from 28 $\times$ 28 to 224 $\times$ 224 from the input, composing enriched and comprehensive information. Different from existing methods, our CECT can capture features at both multi-local and global scales without any sophisticated module design. Moreover, the contribution of local features at different scales can be controlled with the proposed ensemble coefficients. We evaluate CECT on two public COVID-19 datasets and it reaches the highest accuracy of 98.1% in the intra-dataset evaluation, outperforming existing state-of-the-art methods. Moreover, the developed CECT achieves an accuracy of 90.9% on the unseen dataset in the inter-dataset evaluation, showing extraordinary generalization ability. With remarkable feature capture ability and generalization ability, we believe CECT can be extended to other medical scenarios as a powerful diagnosis tool. Code is available at https://github.com/NUS-Tim/CECT., Comment: Computers in Biology and Medicine Accepted

Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance while also protecting the privacy of sensitive data is a crucial challenge in NLP. To preserve privacy, Differential Privacy (DP), which can prevent reconstruction attacks and protect against potential side knowledge, is becoming a de facto technique for private data analysis. In recent years, NLP in DP models (DP-NLP) has been studied from different perspectives, which deserves a comprehensive review. In this paper, we provide the first systematic review of recent advances in DP deep learning models in NLP. In particular, we first discuss some differences and additional challenges of DP-NLP compared with the standard DP deep learning. Then, we investigate some existing work on DP-NLP and present its recent developments from three aspects: gradient perturbation based methods, embedding vector perturbation based methods, and ensemble model based methods. We also discuss some challenges and future directions.