Search

Whether and how language models (LMs) acquire the syntax of natural languages has been widely evaluated under the minimal pair paradigm. However, a lack of wide-coverage benchmarks in languages other than English has constrained systematic investigations into the issue. Addressing it, we first introduce ZhoBLiMP, the most comprehensive benchmark of linguistic minimal pairs for Chinese to date, with 118 paradigms, covering 15 linguistic phenomena. We then train 20 LMs of different sizes (14M to 1.4B) on Chinese corpora of various volumes (100M to 3B tokens) and evaluate them along with 14 off-the-shelf LLMs on ZhoBLiMP. The overall results indicate that Chinese grammar can be mostly learned by models with around 500M parameters, trained on 1B tokens with one epoch, showing limited benefits for further scaling. Most (N=95) linguistic paradigms are of easy or medium difficulty for LMs, while there are still 13 paradigms that remain challenging even for models with up to 32B parameters. In regard to how LMs acquire Chinese grammar, we observe a U-shaped learning pattern in several phenomena, similar to those observed in child language acquisition.

We consider the neural representation to solve the Boltzmann-BGK equation, especially focusing on the application in microscopic flow problems. A new dimension reduction model of the BGK equation with the flexible auxiliary distribution functions is first deduced to reduce the problem dimension. Then, a network-based ansatz that can approximate the dimension-reduced distribution with extremely high efficiency is proposed. Precisely, fully connected neural networks are utilized to avoid discretization in space and time. A specially designed loss function is employed to deal with the complex Maxwell boundary in microscopic flow problems. Moreover, strategies such as multi-scale input and Maxwellian splitting are applied to enhance the approximation efficiency further. Several classical numerical experiments, including 1D Couette flow and Fourier flow problems and 2D duct flow and in-out flow problems are studied to demonstrate the effectiveness of this neural representation method.

LLM self-evaluation relies on the LLM's own ability to estimate response correctness, which can greatly improve its deployment reliability. In this research track, we propose the Chain-of-Embedding (CoE) in the latent space to enable LLMs to perform output-free self-evaluation. CoE consists of all progressive hidden states produced during the inference time, which can be treated as the latent thinking path of LLMs. We find that when LLMs respond correctly and incorrectly, their CoE features differ, these discrepancies assist us in estimating LLM response correctness. Experiments in four diverse domains and seven LLMs fully demonstrate the effectiveness of our method. Meanwhile, its label-free design intent without any training and millisecond-level computational cost ensure real-time feedback in large-scale scenarios. More importantly, we provide interesting insights into LLM response correctness from the perspective of hidden state changes inside LLMs., Comment: 33 pages, 18 figures, 12 tables

Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains. While large language models (LLMs) have demonstrated impressive general understanding and generation abilities, their potential in multi-domain MT is under-explored. We establish a comprehensive benchmark for multi-domain translation, featuring 25 German$\Leftrightarrow$English and 22 Chinese$\Leftrightarrow$English test sets respectively covering 15 domains. Our evaluation of prominent LLMs reveals a discernible performance gap against traditional MT systems, highlighting domain overfitting and catastrophic forgetting issues after fine-tuning on domain-limited corpora. To mitigate this, we propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance. This method inspires the LLM to perceive domain information from the source text, which then serves as a helpful hint to guide the translation process. Despite being trained on a small dataset of four domains, our CoT fine-tune approach achieves notable enhancements in translation accuracy and domain robustness than traditional fine-tuning, as evidenced by an average 1.53 BLEU score increase in over 20 German$\rightarrow$English distinct out-of-domain tests.

The significant discrepancy in the difference of squared nuclear charge radii $\Delta R^2$ of $^{3,4}$He obtained from electronic-atom or muonic-atom energy levels is a puzzle. In this paper, we show that the tension is resolved by including off-diagonal mixing effects due to the hyperfine interaction. Our findings indicate that the hyperfine mixing effect from the $n\,^3\!S$ and $n\,^1\!S$ states ($n>2$) of $^3$He leads to a $-1.37$ kHz adjustment in the isotope shift of the $2\,^1\!S-2\,^3\!S$ transition, surpassing the current uncertainty by a factor of $7$. This results in a change of $-0.0064~\rm{fm}^2$ in $\Delta R^2$, shifting from $1.0757(15)~\mathrm{fm}^2$ to $1.0693(15)~\mathrm{fm}^2$ as determined by Werf {\it et al.}, significantly reducing the discrepancy with the value of $1.0636(31)~\mathrm{fm}^2$ determined by $\mu\rm{He}^+$, and aligning with the result of $1.069(3)$ $\mathrm{fm}^2$ obtained from the $2\,^3\!S-2\,^3\!P$ transition. This adjustment will result in a noticeable change in the absolute nuclear charge radius of $^{3}$He by $-0.0017~\rm{fm}$, aligning the revised value of $1.9715(11)~\mathrm{fm}$ with the value of $1.97007(94)~\mathrm{fm}$ determined by $\mu^3\rm{He}^+$ within $1\sigma$. Our results offer crucial insights into resolving discrepancy in $\Delta R^2$ for $^{3,4}$He and determining the charge radius of $^3$He.

We investigate the phenomenon of magnomechanically induced grating (MMIG) within a cavity magnomechanical system, comprising magnons (spins in a ferromagnet, such as yttrium iron garnet), cavity microwave photons, and phonons [\textit{J. Li, S.-Y. Zhu, and G. S. Agarwal, Phys. Rev. Lett. \textbf{121}, 203601 (2018)}]. By applying an external standing wave control, we observe modifications in the transmission profile of a probe light beam, signifying the presence of MMIG. Through numerical analysis, we explore the diffraction intensities of the probe field, examining the impact of interactions between cavity magnons, magnon-phonon interactions, standing wave field strength, and interaction length. MMIG systems leverage the unique properties of magnons, and collective spin excitations with attributes like long coherence times and spin-wave propagation. These distinctive features can be harnessed in MMIG systems for innovative applications in information storage, retrieval, and quantum memories, offering various orders of diffraction grating., Comment: 12 pages, 8 figures

Mammals can generate autonomous behaviors in various complex environments through the coordination and interaction of activities at different levels of their central nervous system. In this paper, we propose a novel hierarchical learning control framework by mimicking the hierarchical structure of the central nervous system along with their coordination and interaction behaviors. The framework combines the active and passive control systems to improve both the flexibility and reliability of the control system as well as to achieve more diverse autonomous behaviors of robots. Specifically, the framework has a backbone of independent neural network controllers at different levels and takes a three-level dual descending pathway structure, inspired from the functionality of the cerebral cortex, cerebellum, and spinal cord. We comprehensively validated the proposed approach through the simulation as well as the experiment of a hexapod robot in various complex environments, including obstacle crossing and rapid recovery after partial damage. This study reveals the principle that governs the autonomous behavior in the central nervous system and demonstrates the effectiveness of the hierarchical control approach with the salient features of the hierarchical learning control architecture and combination of active and passive control systems.

Recognizing unauthorized Unmanned Aerial Vehicles (UAVs) within designated no-fly zones throughout the day and night is of paramount importance, where the unauthorized UAVs pose a substantial threat to both civil and military aviation safety. However, recognizing UAVs day and night with dual-vision cameras is nontrivial, since red-green-blue (RGB) images suffer from a low detection rate under an insufficient light condition, such as on cloudy or stormy days, while black-and-white infrared (IR) images struggle to capture UAVs that overlap with the background at night. In this paper, we propose a new optical flow-assisted graph-pooling residual network (OF-GPRN), which significantly enhances the UAV detection rate in day and night dual visions. The proposed OF-GPRN develops a new optical fusion to remove superfluous backgrounds, which improves RGB/IR imaging clarity. Furthermore, OF-GPRN extends optical fusion by incorporating a graph residual split attention network and a feature pyramid, which refines the perception of UAVs, leading to a higher success rate in UAV detection. A comprehensive performance evaluation is conducted using a benchmark UAV catch dataset. The results indicate that the proposed OF-GPRN elevates the UAV mean average precision (mAP) detection rate to 87.8%, marking a 17.9% advancement compared to the residual graph neural network (ResGCN)-based approach., Comment: The article is accepted at July 08, 2024 with 13 pages and 10 figures in the Journal of Engineering Applications of Artificial Intelligence, Elsevier

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face and ModelScope, and the supplementary materials including example code on GitHub. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors., Comment: 26 pages, 1 figure

Neuromorphic imaging is an emerging technique that imitates the human retina to sense variations in dynamic scenes. It responds to pixel-level brightness changes by asynchronous streaming events and boasts microsecond temporal precision over a high dynamic range, yielding blur-free recordings under extreme illumination. Nevertheless, this modality falls short in spatial resolution and leads to a low level of visual richness and clarity. Pursuing hardware upgrades is expensive and might cause compromised performance due to more burdens on computational requirements. Another option is to harness offline, plug-in-play super-resolution solutions. However, existing ones, which demand substantial sample volumes for lengthy training on massive computing resources, are largely restricted by real data availability owing to the current imperfect high-resolution devices, as well as the randomness and variability of motion. To tackle these challenges, we introduce the first self-supervised neuromorphic super-resolution prototype. It can be self-adaptive to per input source from any low-resolution camera to estimate an optimal, high-resolution counterpart of any scale, without the need of side knowledge and prior training. Evaluated on downstream tasks, such a simple yet effective method can obtain competitive results against the state-of-the-arts, significantly promoting flexibility but not sacrificing accuracy. It also delivers enhancements for inferior natural images and optical micrographs acquired under non-ideal imaging conditions, breaking through the limitations that are challenging to overcome with frame-based techniques. In the current landscape where the use of high-resolution cameras for event-based sensing remains an open debate, our solution is a cost-efficient and practical alternative, paving the way for more intelligent imaging systems., Comment: 13 pages, 13 figures, and 5 tables. Accepted by IEEE Transactions on Circuits and Systems for Video Technology

This paper introduces AnyTrans, an all-encompassing framework for the task-Translate AnyText in the Image (TATI), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, the advanced inpainting and editing abilities of diffusion models make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Additionally, our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the TATI task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs.

We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) computations in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define nearest-neighbor convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFMs training to tens of thousands of GPUs on datasets consisting of hundreds of millions of graphs. Our GFMs use multi-task learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as energy and atomic forces. Using over 154 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two state-of-the-art United States Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge Leadership Computing Facility. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2,000 GPUs on Perlmutter and 16,000 GPUs on Frontier., Comment: 51 pages, 32 figures

Real-world data deviating from the independent and identically distributed (i.i.d.) assumption of in-distribution training data poses security threats to deep networks, thus advancing out-of-distribution (OOD) detection algorithms. Detection methods in generative language models (GLMs) mainly focus on uncertainty estimation and embedding distance measurement, with the latter proven to be most effective in traditional linguistic tasks like summarization and translation. However, another complex generative scenario mathematical reasoning poses significant challenges to embedding-based methods due to its high-density feature of output spaces, but this feature causes larger discrepancies in the embedding shift trajectory between different samples in latent spaces. Hence, we propose a trajectory-based method TV score, which uses trajectory volatility for OOD detection in mathematical reasoning. Experiments show that our method outperforms all traditional algorithms on GLMs under mathematical reasoning scenarios and can be extended to more applications with high-density features in output spaces, such as multiple-choice questions., Comment: Accepted by NeurIPS 2024

The Shack-Hartmann wavefront sensor is widely employed in adaptive optics systems to measure optical aberrations. However, simultaneously achieving high sensitivity and large dynamic range is still challenging, limiting the performance of diagnosing fast-changing turbulence. To overcome this limitation, we propose neuromorphic Shack-Hartmann wave normal sensing (NeuroSH). NeuroSH is a unifying framework that harnesses the computational neuromorphic imaging paradigm to extract the high-dimensional wave normal from temporal diversity measurements. Both numerical analysis and experimental verification demonstrate the feasibility of NeuroSH. To the best of our knowledge, the proposed NeuroSH is the first scheme to surpass the optical dynamic range limitation under challenging dynamic scenarios, thereby advancing ultra-fast turbulence mitigation technology for cutting-edge imagers.

The optical Ramsey technique is used to obtain precise measurements of the hyperfine splittings in the $2\,^3\!S_1$ and $2\,^3\!P_J$ states of $^7$Li$^+$. Together with bound-state quantum electrodynamic theory, the Zemach radius and quadrupole moment of the $^7$Li nucleus are determined to be $3.35(1)$~fm and $-3.86(5)$~fm$^2$ respectively, with the quadrupole moment deviating from the recommended value of $-4.00(3)$~fm$^2$ by $1.75\sigma$. Furthermore, we determine the quadrupole moment ratio of $^6$Li to $^7$Li as $0.101(13)$, exhibiting a $6\sigma$ deviation from the previous measured value of $0.020161(13)$ by LiF molecular spectroscopy. The results taken together provide a sensitive test of nuclear structure models.

Cosmic rays travel throughout the Galaxy, leaving traces from radio to ultra-high-energy gamma rays due to interactions with the interstellar gas, radiation field and magnetic field. Therefore, it is necessary to utilize multi-wavelength investigations on the Galactic diffuse emission to shed light on the physics of CR production and propagation. In this work, we present a spatially dependent propagation scenario, taking account of a local source contribution, while making allowances for an additional CR component freshly accelerated near their sources. In this picture, after reproducing the particle measurements at the Solar system, we calculated the intensity and compared the spectral energy distribution to observations from Fermi-LAT and LHAASO-KM2A in the gamma-ray band, and from WMAP and Planck among other radio surveys at lower energies. Multi-band data considered in conjunction, the former comparison exhibits sufficiently good consistency in favor of our model, while the latter calls for improvement in data subtraction and processing. From this standpoint, there remains potential for advanced observations at energies from milli-eVs to MeVs towards the Galactic plane, in order to evaluate our model further and more comprehensively in the future., Comment: Accepted by ApJ

Late fusion multi-view clustering (LFMVC) has become a rapidly growing class of methods in the multi-view clustering (MVC) field, owing to its excellent computational speed and clustering performance. One bottleneck faced by existing late fusion methods is that they are usually aligned to the average kernel function, which makes the clustering performance highly dependent on the quality of datasets. Another problem is that they require subsequent k-means clustering after obtaining the consensus partition matrix to get the final discrete labels, and the resulting separation of the label learning and cluster structure optimization processes limits the integrity of these models. To address the above issues, we propose an integrated framework named One-Step Late Fusion Multi-view Clustering with Compressed Subspace (OS-LFMVC-CS). Specifically, we use the consensus subspace to align the partition matrix while optimizing the partition fusion, and utilize the fused partition matrix to guide the learning of discrete labels. A six-step iterative optimization approach with verified convergence is proposed. Sufficient experiments on multiple datasets validate the effectiveness and efficiency of our proposed method., Comment: Accepted by ICASSP2024

The development of intelligent robots requires control policies that can handle dynamic environments and evolving tasks. Pre-training reinforcement learning has emerged as an effective approach to address these demands by enabling robots to acquire reusable motor skills. However, they often rely on large datasets or expert-designed goal spaces, limiting adaptability. Additionally, these methods need help to generate dynamic and diverse skills in high-dimensional state spaces, reducing their effectiveness for downstream tasks. In this paper, we propose CMS-PRL, a pre-training reinforcement learning method inspired by the Central Motor System (CMS). First, we introduce a fusion reward mechanism that combines the basic motor reward with mutual information reward, promoting the discovery of dynamic skills during pre-training without reliance on external data. Second, we design a skill encoding method inspired by the motor program of the basal ganglia, providing rich and continuous skill instructions during pre-training. Finally, we propose a skill activity function to regulate motor skill activity, enabling the generation of skills with different activity levels, thereby enhancing the robot's flexibility in downstream tasks. We evaluate the model on four types of robots in a challenging set of sparse-reward tasks. Experimental results demonstrate that CMS-PRL generates diverse, reusable motor skills to solve various downstream tasks and outperforms baseline methods, particularly in high-degree-of-freedom robots and complex tasks., Comment: 12 pages; 9 figures

Transformer-based large language models have remarkable potential to accelerate design optimization for applications such as drug development and materials discovery. Self-supervised pretraining of transformer models requires large-scale datasets, which are often sparsely populated in topical areas such as polymer science. State-of-the-art approaches for polymers conduct data augmentation to generate additional samples but unavoidably incurs extra computational costs. In contrast, large-scale open-source datasets are available for small molecules and provide a potential solution to data scarcity through transfer learning. In this work, we show that using transformers pretrained on small molecules and fine-tuned on polymer properties achieve comparable accuracy to those trained on augmented polymer datasets for a series of benchmark prediction tasks.

Multi-view clustering has attracted growing attention owing to its capabilities of aggregating information from various sources and its promising horizons in public affairs. Up till now, many advanced approaches have been proposed in recent literature. However, there are several ongoing difficulties to be tackled. One common dilemma occurs while attempting to align the features of different views. {Moreover, due to the fact that many existing multi-view clustering algorithms stem from spectral clustering, this results to cubic time complexity w.r.t. the number of dataset. However, we propose Anchor-based Multi-view Subspace Clustering with Hierarchical Feature Descent(MVSC-HFD) to tackle the discrepancy among views through hierarchical feature descent and project to a common subspace( STAGE 1), which reveals dependency of different views. We further reduce the computational complexity to linear time cost through a unified sampling strategy in the common subspace( STAGE 2), followed by anchor-based subspace clustering to learn the bipartite graph collectively( STAGE 3). }Extensive experimental results on public benchmark datasets demonstrate that our proposed model consistently outperforms the state-of-the-art techniques.

In the upcoming decade, deep learning may revolutionize the natural sciences, enhancing our capacity to model and predict natural occurrences. This could herald a new era of scientific exploration, bringing significant advancements across sectors from drug development to renewable energy. To answer this call, we present DeepSpeed4Science initiative (deepspeed4science.ai) which aims to build unique capabilities through AI system technology innovations to help domain experts to unlock today's biggest science mysteries. By leveraging DeepSpeed's current technology pillars (training, inference and compression) as base technology enablers, DeepSpeed4Science will create a new set of AI system technologies tailored for accelerating scientific discoveries by addressing their unique complexity beyond the common technical approaches used for accelerating generic large language models (LLMs). In this paper, we showcase the early progress we made with DeepSpeed4Science in addressing two of the critical system challenges in structural biology research.

Bio-inspired neuromorphic cameras asynchronously record pixel brightness changes and generate sparse event streams. They can capture dynamic scenes with little motion blur and more details in extreme illumination conditions. Due to the multidimensional address-event structure, most existing vision algorithms cannot properly handle asynchronous event streams. While several event representations and processing methods have been developed to address such an issue, they are typically driven by a large number of events, leading to substantial overheads in runtime and memory. In this paper, we propose a new graph representation of the event data and couple it with a Graph Transformer to perform accurate neuromorphic classification. Extensive experiments show that our approach leads to better results and excels at the challenging realistic situations where only a small number of events and limited computational resources are available, paving the way for neuromorphic applications embedded into mobile facilities., Comment: 15 pages, 4 figures, and 7 tables. Accepted by Elsevier Neurocomputing

Neuromorphic imaging reacts to per-pixel brightness changes of a dynamic scene with high temporal precision and responds with asynchronous streaming events as a result. It also often supports a simultaneous output of an intensity image. Nevertheless, the raw events typically involve a large amount of noise due to the high sensitivity of the sensor, while capturing fast-moving objects at low frame rates results in blurry images. These deficiencies significantly degrade human observation and machine processing. Fortunately, the two information sources are inherently complementary -- events with microsecond-level temporal resolution, which are triggered by the edges of objects recorded in a latent sharp image, can supply rich motion details missing from the blurry one. In this work, we bring the two types of data together and introduce a simple yet effective unifying algorithm to jointly reconstruct blur-free images and noise-robust events in an iterative coarse-to-fine fashion. Specifically, an event-regularized prior offers precise high-frequency structures and dynamic features for blind deblurring, while image gradients serve as a kind of faithful supervision in regulating neuromorphic noise removal. Comprehensively evaluated on real and synthetic samples, such a synergy delivers superior reconstruction quality for both images with severe motion blur and raw event streams with a storm of noise, and also exhibits greater robustness to challenging realistic scenarios such as varying levels of illumination, contrast and motion magnitude. Meanwhile, it can be driven by much fewer events and holds a competitive edge at computational time overhead, rendering itself preferable as available computing resources are limited. Our solution gives impetus to the improvement of both sensing data and paves the way for highly accurate neuromorphic reasoning and analysis., Comment: 16 pages, 19 figures, and 3 tables. Accepted by IEEE Transactions on Image Processing

Graph anomaly detection (GAD) has attracted increasing attention in machine learning and data mining. Recent works have mainly focused on how to capture richer information to improve the quality of node embeddings for GAD. Despite their significant advances in detection performance, there is still a relative dearth of research on the properties of the task. GAD aims to discern the anomalies that deviate from most nodes. However, the model is prone to learn the pattern of normal samples which make up the majority of samples. Meanwhile, anomalies can be easily detected when their behaviors differ from normality. Therefore, the performance can be further improved by enhancing the ability to learn the normal pattern. To this end, we propose a normality learning-based GAD framework via multi-scale contrastive learning networks (NLGAD for abbreviation). Specifically, we first initialize the model with the contrastive networks on different scales. To provide sufficient and reliable normal nodes for normality learning, we design an effective hybrid strategy for normality selection. Finally, the model is refined with the only input of reliable normal nodes and learns a more accurate estimate of normality so that anomalous nodes can be more easily distinguished. Eventually, extensive experiments on six benchmark graph datasets demonstrate the effectiveness of our normality learning-based scheme on GAD. Notably, the proposed algorithm improves the detection performance (up to 5.89% AUC gain) compared with the state-of-the-art methods. The source code is released at https://github.com/FelixDJC/NLGAD., Comment: 10 pages, 7 figures, accepted by ACM MM 2023

Anchor-based multi-view graph clustering (AMVGC) has received abundant attention owing to its high efficiency and the capability to capture complementary structural information across multiple views. Intuitively, a high-quality anchor graph plays an essential role in the success of AMVGC. However, the existing AMVGC methods only consider single-structure information, i.e., local or global structure, which provides insufficient information for the learning task. To be specific, the over-scattered global structure leads to learned anchors failing to depict the cluster partition well. In contrast, the local structure with an improper similarity measure results in potentially inaccurate anchor assignment, ultimately leading to sub-optimal clustering performance. To tackle the issue, we propose a novel anchor-based multi-view graph clustering framework termed Efficient Multi-View Graph Clustering with Local and Global Structure Preservation (EMVGC-LG). Specifically, a unified framework with a theoretical guarantee is designed to capture local and global information. Besides, EMVGC-LG jointly optimizes anchor construction and graph learning to enhance the clustering quality. In addition, EMVGC-LG inherits the linear complexity of existing AMVGC methods respecting the sample number, which is time-economical and scales well with the data size. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method., Comment: arXiv admin note: text overlap with arXiv:2308.16541

Solute transport in fluid-particle systems is a fundamental process in numerous scientific and engineering disciplines. The simulation of it necessitates the consideration of solid particles with intricate shapes and sizes. To address this challenge, this study proposes the Random-Walk Metaball-Imaging Discrete Element Lattice Boltzmann Method (RW-MI-DELBM). In this model, we reconstruct particle geometries with the Metaball-Imaging algorithm, capture the particle behavior using the Discrete Element Method (DEM), simulate fluid behavior by the Lattice Boltzmann Method (LBM), and represent solute behavior through the Random Walk Method (RWM). Through the integration of these techniques with specially designed boundary conditions, we achieve to simulate the solute transport in fluid-particle systems comprising complex particle morphologies. Thorough validations, including analytical soluutions and experiments, are performed to assess the robustness and accuracy of this framework. The results demonstrate that the proposed framework can accurately capture the complex dynamics of solute transport under strict mass conservation. In particular, an investigation is carried out to assess the influence of particle morphologies on solute transport in a 3D oscillator, with a focus on identifying correlations between shape features and dispersion coefficients. Notably, all selected shape features exhibited strong correlations with the dispersion coefficient, indicating the significant influence of particle shapes on transport phenomena. However, due to the complexity of the relationship and the limited number of simulations, no clear patterns could be observed. Further comprehensive analyses incorporating a broader range of shape features and varying conditions are necessary to fully comprehend their collective influence on the dispersion coefficient., Comment: Pei Zhang, Stan Z. Li and S.A. Galindo-Torres are all cooresponding authors of this paper

Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions. However, the development of LLMs has been primarily focused on high-resource languages, such as English, thereby limiting their applicability and research in other languages. Consequently, we present PolyLM, a multilingual LLM trained on 640 billion (B) tokens, avaliable in two model sizes: 1.7B and 13B. To enhance its multilingual capabilities, we 1) integrate bilingual data into training data; and 2) adopt a curriculum learning strategy that increases the proportion of non-English data from 30% in the first stage to 60% in the final stage during pre-training. Further, we propose a multilingual self-instruct method which automatically generates 132.7K diverse multilingual instructions for model fine-tuning. To assess the model's performance, we collect several existing multilingual tasks, including multilingual understanding, question answering, generation, and translation. Extensive experiments show that PolyLM surpasses other open-source models such as LLaMA and BLOOM on multilingual tasks while maintaining comparable performance in English. Our models, alone with the instruction data and multilingual benchmark, are available at: \url{https://modelscope.cn/models/damo/nlp_polylm_13b_text_generation}.

The observations of the energy spectra of cosmic-ray have revealed complicated structures. Especially, spectral hardenings in the boron-to-carbon and boron-to-oxygen ratios above $\sim 200$ GV has been revealed by AMS-02 and DAMPE experiments. One scenario to account for the hardenings of secondary-to-primary ratios is the nuclear fragmentation of freshly accelerated particles around sources. In this work, we further study this scenario based on new observations of Galactic diffuse gamma rays by LHAASO and neutrinos by IceCube. We find that the spectra of cosmic ray nuclei, the diffuse ultra-high-energy gamma rays, and the Galactic component of neutrinos can be simultaneously explained, given an average confinement and interaction time of $\sim 0.25$ Myr around sources. These multi-messenger data thus provide evidence of non-negligible grammage of Galactic cosmic rays surrounding sources besides the traditional one during the propagation., Comment: 10 papes, 5 pages

Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like Python and SQL. Those methods require that reasoning tasks be convertible into programs, which cater to the computer execution mindset and deviate from human reasoning habits. To broaden symbolic methods' applicability and adaptability in the real world, we propose the Meta-Reasoning from a linguistic perspective. This method empowers LLMs to deconstruct reasoning-independent semantic information into generic symbolic representations, thereby efficiently capturing more generalized reasoning knowledge. We conduct extensive experiments on more than ten datasets encompassing conventional reasoning tasks like arithmetic, symbolic, and logical reasoning, and the more complex interactive reasoning tasks like theory-of-mind reasoning. Experimental results demonstrate that Meta-Reasoning significantly enhances in-context reasoning accuracy, learning efficiency, out-of-domain generalization, and output stability compared to the Chain-of-Thought technique. Code and data are publicly available at \url{https://github.com/Alsace08/Meta-Reasoning}., Comment: Accepted by ACL 2024 Findings

Quantum incompatibility is referred as the phenomenon that some quantum measurements cannot be performed simultaneously, and is also used in various quantum information tasks. However, it is still a challenge to certify whether a given set of multiple high-dimensional measurements respects a specific structure of incompatibility. To address this problem, we propose a modified quantum state discrimination protocol that decomposes complex compatibility structures into pair-wise ones and employs noise robustness to witness incompatibility structures. Our method is capable of detecting genuine $n$-wise incompatibility and some specific general compatibility structures, as demonstrated by our experimental verification of incompatibility structures of $4$ mutually unbiased bases in a qutrit system. The experimental results show that our approach is able to witness incompatibility structures, i.e., the hierarchy of quantum incompatibility resources., Comment: 7 pages, 4 figures

Bio-inspired neuromorphic cameras sense illumination changes on a per-pixel basis and generate spatiotemporal streaming events within microseconds in response, offering visual information with high temporal resolution over a high dynamic range. Such devices often serve in surveillance systems due to their applicability and robustness in environments with high dynamics and harsh lighting, where they can still supply clearer recordings than traditional imaging. In other words, when it comes to privacy-relevant cases, neuromorphic cameras also expose more sensitive data and pose serious security threats. Therefore, asynchronous event streams necessitate careful encryption before transmission and usage. This work discusses several potential attack scenarios and approaches event encryption from the perspective of neuromorphic noise removal, in which we inversely introduce well-crafted noise into raw events until they are obfuscated. Our evaluations show that the encrypted events can effectively protect information from attacks of low-level visual reconstruction and high-level neuromorphic reasoning, and thus feature dependable privacy-preserving competence. The proposed solution gives impetus to the security of event data and paves the way to a highly encrypted technique for privacy-protective neuromorphic imaging., Comment: 6 pages, 6 figures, and 2 tables. Accepted by IOP Neuromorphic Computing and Engineering