Searcharxiv⌕ Search

arXiv subjects

Lei Shen

Publications and source records attributed to Lei Shen.

At least 73 records · Page 4Linked to original sources

CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X

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.

cs.LG↗

GEB-1.3B: Open Lightweight Large Language Model

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.

cs.CL↗

High Spectral-Efficiency, Ultra-low MIMO SDM Transmission over a Field-Deployed Multi-Core OAM Fiber

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 $μ$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.

cs.NI↗

CECT: Controllable Ensemble CNN and Transformer for COVID-19 Image Classification

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.

eess.IV↗

Topological skyrmions in monolayer multiferroic MoPtGe2S6

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.

cond-mat.mtrl-sci↗

Ecosystem orchestration practices for industrial firms: A qualitative meta-analysis, framework development and research agenda

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.

econ.GN↗

Local environment-based machine learning for molecular adsorption energy prediction

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.

cond-mat.mtrl-sci↗

Differentially Private Natural Language Models: Recent Advances and Future Directions

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.

cs.CL↗

GSDA: Generative Adversarial Network-based Semi-Supervised Data Augmentation for Ultrasound Image Classification

Medical Ultrasound (US) is one of the most widely used imaging modalities in clinical practice, but its usage presents unique challenges such as variable imaging quality. Deep Learning (DL) models can serve as advanced medical US image analysis tools, but their performance is greatly limited by the scarcity of large datasets. To solve the common data shortage, we develop GSDA, a Generative Adversarial Network (GAN)-based semi-supervised data augmentation method. GSDA consists of the GAN and Convolutional Neural Network (CNN). The GAN synthesizes and pseudo-labels high-resolution, high-quality US images, and both real and synthesized images are then leveraged to train the CNN. To address the training challenges of both GAN and CNN with limited data, we employ transfer learning techniques during their training. We also introduce a novel evaluation standard that balances classification accuracy with computational time. We evaluate our method on the BUSI dataset and GSDA outperforms existing state-of-the-art methods. With the high-resolution and high-quality images synthesized, GSDA achieves a 97.9% accuracy using merely 780 images. Given these promising results, we believe that GSDA holds potential as an auxiliary tool for medical US analysis.

eess.IV↗

Van der Waals Spin-Orbit Torque Antiferromagnetic Memory

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.

cond-mat.mtrl-sci↗

RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition

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 Bézier 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 BézierPalm 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.

cs.CV↗

Recent Progress in Transformer-based Medical Image Analysis

The transformer is primarily used in the field of natural language processing. Recently, it has been adopted and shows promise in the computer vision (CV) field. Medical image analysis (MIA), as a critical branch of CV, also greatly benefits from this state-of-the-art technique. In this review, we first recap the core component of the transformer, the attention mechanism, and the detailed structures of the transformer. After that, we depict the recent progress of the transformer in the field of MIA. We organize the applications in a sequence of different tasks, including classification, segmentation, captioning, registration, detection, enhancement, localization, and synthesis. The mainstream classification and segmentation tasks are further divided into eleven medical image modalities. A large number of experiments studied in this review illustrate that the transformer-based method outperforms existing methods through comparisons with multiple evaluation metrics. Finally, we discuss the open challenges and future opportunities in this field. This task-modality review with the latest contents, detailed information, and comprehensive comparison may greatly benefit the broad MIA community.

eess.IV↗

DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation

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.

cs.CL↗

Is Translation Helpful? An Empirical Analysis of Cross-Lingual Transfer in Low-Resource Dialog Generation

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.

cs.CL↗

DistilPose: Tokenized Pose Regression with Heatmap Distillation

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.

cs.CV↗

Large modulation of thermal transport in 2D semimetal triphosphides by doping-induced electron-phonon coupling

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.

cond-mat.mtrl-sci↗

Coordinating Cross-modal Distillation for Molecular Property Prediction

In recent years, molecular graph representation learning (GRL) has drawn much more attention in molecular property prediction (MPP) problems. The existing graph methods have demonstrated that 3D geometric information is significant for better performance in MPP. However, accurate 3D structures are often costly and time-consuming to obtain, limiting the large-scale application of GRL. It is an intuitive solution to train with 3D to 2D knowledge distillation and predict with only 2D inputs. But some challenging problems remain open for 3D to 2D distillation. One is that the 3D view is quite distinct from the 2D view, and the other is that the gradient magnitudes of atoms in distillation are discrepant and unstable due to the variable molecular size. To address these challenging problems, we exclusively propose a distillation framework that contains global molecular distillation and local atom distillation. We also provide a theoretical insight to justify how to coordinate atom and molecular information, which tackles the drawback of variable molecular size for atom information distillation. Experimental results on two popular molecular datasets demonstrate that our proposed model achieves superior performance over other methods. Specifically, on the largest MPP dataset PCQM4Mv2 served as an "ImageNet Large Scale Visual Recognition Challenge" in the field of graph ML, the proposed method achieved a 6.9% improvement compared with the best works. And we obtained fourth place with the MAE of 0.0734 on the test-challenge set for OGB-LSC 2022 Graph Regression Task. We will release the code soon.

cs.LG↗

MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding

Multimodal named entity recognition (MNER) is a critical step in information extraction, which aims to detect entity spans and classify them to corresponding entity types given a sentence-image pair. Existing methods either (1) obtain named entities with coarse-grained visual clues from attention mechanisms, or (2) first detect fine-grained visual regions with toolkits and then recognize named entities. However, they suffer from improper alignment between entity types and visual regions or error propagation in the two-stage manner, which finally imports irrelevant visual information into texts. In this paper, we propose a novel end-to-end framework named MNER-QG that can simultaneously perform MRC-based multimodal named entity recognition and query grounding. Specifically, with the assistance of queries, MNER-QG can provide prior knowledge of entity types and visual regions, and further enhance representations of both texts and images. To conduct the query grounding task, we provide manual annotations and weak supervisions that are obtained via training a highly flexible visual grounding model with transfer learning. We conduct extensive experiments on two public MNER datasets, Twitter2015 and Twitter2017. Experimental results show that MNER-QG outperforms the current state-of-the-art models on the MNER task, and also improves the query grounding performance.

cs.CV↗