Search

Unveiling atomic structures is significant for the relationship construction between microscopic configurations and macroscopic properties of materials. However, we still lack a rapid, accurate, and robust approach to automatically resolve complex patterns in atomic-resolution microscopy. Here, we present a Trident strategy-enhanced disentangled representation learning method (a generative model), which utilizes a few unlabeled experimental images with abundant low-cost simulated images to generate a large corpus of annotated simulation data that closely resembles experimental conditions, realizing simultaneous achievement of high quality and large volumes of the training dataset. A structural inference model is then trained via a residual neural network which can directly deduce the interlayer slip and rotation of diversified and complicated stacking patterns at van der Waals (vdWs) interfaces with picometer-scale accuracy across various materials (ReS2, ReSe2, and MoS2) with different layer numbers (bilayer and trilayers) and demonstrates robustness to defects, imaging quality, and surface contaminations. The framework can also identify pattern transition interfaces, quantify subtle motif variations, and discriminate moir\'e patterns that are undistinguishable in frequency domains. The high-throughput processing ability of our method helps discover a novel vdW epitaxy where various thermodynamically favorable slip stackings can coexist, demonstrating the machine learning contribution to the new knowledge emergence., Comment: 25 pages,5 figures

Scientific literature understanding is crucial for extracting targeted information and garnering insights, thereby significantly advancing scientific discovery. Despite the remarkable success of Large Language Models (LLMs), they face challenges in scientific literature understanding, primarily due to (1) a lack of scientific knowledge and (2) unfamiliarity with specialized scientific tasks. To develop an LLM specialized in scientific literature understanding, we propose a hybrid strategy that integrates continual pre-training (CPT) and supervised fine-tuning (SFT), to simultaneously infuse scientific domain knowledge and enhance instruction-following capabilities for domain-specific tasks.cIn this process, we identify two key challenges: (1) constructing high-quality CPT corpora, and (2) generating diverse SFT instructions. We address these challenges through a meticulous pipeline, including PDF text extraction, parsing content error correction, quality filtering, and synthetic instruction creation. Applying this strategy, we present a suite of LLMs: SciLitLLM, specialized in scientific literature understanding. These models demonstrate promising performance on scientific literature understanding benchmarks. Our contributions are threefold: (1) We present an effective framework that integrates CPT and SFT to adapt LLMs to scientific literature understanding, which can also be easily adapted to other domains. (2) We propose an LLM-based synthesis method to generate diverse and high-quality scientific instructions, resulting in a new instruction set -- SciLitIns -- for supervised fine-tuning in less-represented scientific domains. (3) SciLitLLM achieves promising performance improvements on scientific literature understanding benchmarks.

The study of structure-spectrum relationships is essential for spectral interpretation, impacting structural elucidation and material design. Predicting spectra from molecular structures is challenging due to their complex relationships. Herein, we introduce NMRNet, a deep learning framework using the SE(3) Transformer for atomic environment modeling, following a pre-training and fine-tuning paradigm. To support the evaluation of NMR chemical shift prediction models, we have established a comprehensive benchmark based on previous research and databases, covering diverse chemical systems. Applying NMRNet to these benchmark datasets, we achieve state-of-the-art performance in both liquid-state and solid-state NMR datasets, demonstrating its robustness and practical utility in real-world scenarios. This marks the first integration of solid and liquid state NMR within a unified model architecture, highlighting the need for domainspecific handling of different atomic environments. Our work sets a new standard for NMR prediction, advancing deep learning applications in analytical and structural chemistry., Comment: 23 pages, 6 figures

Developing an efficient method to accelerate the speed of molecular dynamics is a central theme in the field of molecular simulation. One category among the methods are collective-variable-based methods, which rely on predefined collective variables (CVs). The difficulty of selecting a few important CVs hinders the methods to be applied to large systems easily. Here we present a CV-based enhanced sampling method RiD-kit, which could handle a large number of CVs and perform efficient sampling. The method could be applied to various kinds of systems, including biomolecules, chemical reactions and materials. In this protocol, we guide the users through all phases of the RiD-kit workflow, from preparing the input files, setting the simulation parameters and analyzing the results. The RiD-kit workflow provides an efficient and user-friendly command line tool which could submit jobs to various kinds of platforms including the high-performance computers (HPC), cloud server and local machines., Comment: 43 pages,4 figures

Dataset Distillation (DD) aims to synthesize a small dataset capable of performing comparably to the original dataset. Despite the success of numerous DD methods, theoretical exploration of this area remains unaddressed. In this paper, we take an initial step towards understanding various matching-based DD methods from the perspective of sample difficulty. We begin by empirically examining sample difficulty, measured by gradient norm, and observe that different matching-based methods roughly correspond to specific difficulty tendencies. We then extend the neural scaling laws of data pruning to DD to theoretically explain these matching-based methods. Our findings suggest that prioritizing the synthesis of easier samples from the original dataset can enhance the quality of distilled datasets, especially in low IPC (image-per-class) settings. Based on our empirical observations and theoretical analysis, we introduce the Sample Difficulty Correction (SDC) approach, designed to predominantly generate easier samples to achieve higher dataset quality. Our SDC can be seamlessly integrated into existing methods as a plugin with minimal code adjustments. Experimental results demonstrate that adding SDC generates higher-quality distilled datasets across 7 distillation methods and 6 datasets.

Solid-water interfaces are crucial to many physical and chemical processes and are extensively studied using surface-specific sum-frequency generation (SFG) spectroscopy. To establish clear correlations between specific spectral signatures and distinct interfacial water structures, theoretical calculations using molecular dynamics (MD) simulations are required. These MD simulations typically need relatively long trajectories (a few nanoseconds) to achieve reliable SFG response function calculations via the dipole-polarizability time correlation function. However, the requirement for long trajectories limits the use of computationally expensive techniques such as ab initio MD (AIMD) simulations, particularly for complex solid-water interfaces. In this work, we present a pathway for calculating vibrational spectra (IR, Raman, SFG) of solid-water interfaces using machine learning (ML)-accelerated methods. We employ both the dipole moment-polarizability correlation function and the surface-specific velocity-velocity correlation function approaches to calculate SFG spectra. Our results demonstrate the successful acceleration of AIMD simulations and the calculation of SFG spectra using ML methods. This advancement provides an opportunity to calculate SFG spectra for the complicated solid-water systems more rapidly and at a lower computational cost with the aid of ML., Comment: 34 pages, 11 figures

Advancements in lithium battery technology heavily rely on the design and engineering of electrolytes. However, current schemes for molecular design and recipe optimization of electrolytes lack an effective computational-experimental closed loop and often fall short in accurately predicting diverse electrolyte formulation properties. In this work, we introduce Uni-ELF, a novel multi-level representation learning framework to advance electrolyte design. Our approach involves two-stage pretraining: reconstructing three-dimensional molecular structures at the molecular level using the Uni-Mol model, and predicting statistical structural properties (e.g., radial distribution functions) from molecular dynamics simulations at the mixture level. Through this comprehensive pretraining, Uni-ELF is able to capture intricate molecular and mixture-level information, which significantly enhances its predictive capability. As a result, Uni-ELF substantially outperforms state-of-the-art methods in predicting both molecular properties (e.g., melting point, boiling point, synthesizability) and formulation properties (e.g., conductivity, Coulombic efficiency). Moreover, Uni-ELF can be seamlessly integrated into an automatic experimental design workflow. We believe this innovative framework will pave the way for automated AI-based electrolyte design and engineering.

Predicting quantum operator matrices such as Hamiltonian, overlap, and density matrices in the density functional theory (DFT) framework is crucial for understanding material properties. Current methods often focus on individual operators and struggle with efficiency and scalability for large systems. Here we introduce a novel deep learning model, SLEM (strictly localized equivariant message-passing) for predicting multiple quantum operators, that achieves state-of-the-art accuracy while dramatically improving computational efficiency. SLEM's key innovation is its strict locality-based design, constructing local, equivariant representations for quantum tensors while preserving physical symmetries. This enables complex many-body dependence without expanding the effective receptive field, leading to superior data efficiency and transferability. Using an innovative SO(2) convolution technique, SLEM reduces the computational complexity of high-order tensor products and is therefore capable of handling systems requiring the $f$ and $g$ orbitals in their basis sets. We demonstrate SLEM's capabilities across diverse 2D and 3D materials, achieving high accuracy even with limited training data. SLEM's design facilitates efficient parallelization, potentially extending DFT simulations to systems with device-level sizes, opening new possibilities for large-scale quantum simulations and high-throughput materials discovery., Comment: 11 pages, 5 figures and 5 tables

Solid electrolytes with fast ion transport are one of the key challenges for solid state lithium metal batteries. To improve ion conductivity, chemical doping has been the most effective strategy, and atomistic simulation with machine-learning potential helps find optimized doping by predicting ion conductivity for arbitrary composition. Yet most existing machine-learning models are trained on narrow chemistry, and new model has to be trained for each system, wasting transferable knowledge and incurring significant cost. Here, we propose a pre-trained deep potential model purpose-built for sulfide electrolytes with attention mechanism, known as DPA-SSE. The training set encompasses 15 elements and consists of both equilibrium and extensive out-of-equilibrium configurations. DPA-SSE achieves a high energy resolution of less than 2 meV/atom for dynamical trajectories up to 1150 K, and reproduces experimental ion conductivity of sulfide electrolytes with remarkable accuracy. DPA-SSE exhibits good transferability, covering a range of complex electrolytes with mixes of cation and anion atoms. Highly efficient dynamical simulation with DPA-SSE can be realized by model distillation which generates a faster model for given systems. DPA-SSE also serves as a platform for continuous learning, and the model fine-tune requires only a portion of downstream data. These results demonstrate the possibility of a new pathway for AI-driven development of solid electrolytes with exceptional performance.

In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, graph level, and geometry structure level. Along with this, we systematically investigate the scaling law within molecular pretraining models, characterizing the power-law correlations between validation loss and model size, dataset size, and computational resources. Consequently, we successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date. Extensive experiments show consistent improvement in the downstream tasks as the model size grows. The Uni-Mol2 with 1.1B parameters also outperforms existing methods, achieving an average 27% improvement on the QM9 and 14% on COMPAS-1D dataset.

Molecular simulations are essential tools in computational chemistry, enabling the prediction and understanding of molecular interactions and thermodynamic properties of biomolecules. However, traditional force fields face significant challenges in accurately representing novel molecules and complex chemical environments due to the labor-intensive process of manually setting optimization parameters and the high computational cost of quantum mechanical calculations. To overcome these difficulties, we fine-tuned a high-accuracy DPA-2 pre-trained model and applied it to optimize force field parameters on-the-fly, significantly reducing computational costs. Our method combines this fine-tuned DPA-2 model with a node-embedding-based similarity metric, allowing seamless augmentation to new chemical species without manual intervention. We applied this process to the TYK2 inhibitor and PTP1B systems and demonstrated its effectiveness through the improvement of free energy perturbation calculation results. This advancement contributes valuable insights and tools for the computational chemistry community.

Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to self-attention's quadratic complexity. We propose DiTFastAttn, a novel post-training compression method to alleviate DiT's computational bottleneck. We identify three key redundancies in the attention computation during DiT inference: 1. spatial redundancy, where many attention heads focus on local information; 2. temporal redundancy, with high similarity between neighboring steps' attention outputs; 3. conditional redundancy, where conditional and unconditional inferences exhibit significant similarity. To tackle these redundancies, we propose three techniques: 1. Window Attention with Residual Caching to reduce spatial redundancy; 2. Temporal Similarity Reduction to exploit the similarity between steps; 3. Conditional Redundancy Elimination to skip redundant computations during conditional generation. To demonstrate the effectiveness of DiTFastAttn, we apply it to DiT, PixArt-Sigma for image generation tasks, and OpenSora for video generation tasks. Evaluation results show that for image generation, our method reduces up to 88\% of the FLOPs and achieves up to 1.6x speedup at high resolution generation.

In recent years, machine learning (ML) methods have emerged as promising alternatives for molecular docking, offering the potential for high accuracy without incurring prohibitive computational costs. However, recent studies have indicated that these ML models may overfit to quantitative metrics while neglecting the physical constraints inherent in the problem. In this work, we present Uni-Mol Docking V2, which demonstrates a remarkable improvement in performance, accurately predicting the binding poses of 77+% of ligands in the PoseBusters benchmark with an RMSD value of less than 2.0 {\AA}, and 75+% passing all quality checks. This represents a significant increase from the 62% achieved by the previous Uni-Mol Docking model. Notably, our Uni-Mol Docking approach generates chemically accurate predictions, circumventing issues such as chirality inversions and steric clashes that have plagued previous ML models. Furthermore, we observe enhanced performance in terms of high-quality predictions (RMSD values of less than 1.0 {\AA} and 1.5 {\AA}) and physical soundness when Uni-Mol Docking is combined with more physics-based methods like Uni-Dock. Our results represent a significant advancement in the application of artificial intelligence for scientific research, adopting a holistic approach to ligand docking that is well-suited for industrial applications in virtual screening and drug design. The code, data and service for Uni-Mol Docking are publicly available for use and further development in https://github.com/dptech-corp/Uni-Mol.

In the AI-for-science era, scientific computing scenarios such as concurrent learning and high-throughput computing demand a new generation of infrastructure that supports scalable computing resources and automated workflow management on both cloud and high-performance supercomputers. Here we introduce Dflow, an open-source Python toolkit designed for scientists to construct workflows with simple programming interfaces. It enables complex process control and task scheduling across a distributed, heterogeneous infrastructure, leveraging containers and Kubernetes for flexibility. Dflow is highly observable and can scale to thousands of concurrent nodes per workflow, enhancing the efficiency of complex scientific computing tasks. The basic unit in Dflow, known as an Operation (OP), is reusable and independent of the underlying infrastructure or context. Dozens of workflow projects have been developed based on Dflow, spanning a wide range of projects. We anticipate that the reusability of Dflow and its components will encourage more scientists to publish their workflows and OP components. These components, in turn, can be adapted and reused in various contexts, fostering greater collaboration and innovation in the scientific community.

The ability to rapidly evaluate materials properties through atomistic simulation approaches is the foundation of many new artificial intelligence-based approaches to materials identification and design. This depends on the availability of accurate descriptions of atomic bonding through various forms of interatomic potentials. We present an efficient, robust platform for calculating materials properties, i.e., APEX, the Alloy Property Explorer. APEX enables the rapid evolution of interatomic potential development and optimization, which is of particular importance in fine-tuning new classes of general AI-based foundation models to forms that are readily applicable to impacting materials development. APEX is an open-source, extendable, and cloud-native platform for material property calculations using a range of atomistic simulation methodologies that effectively manages diverse computational resources and is built upon user-friendly features including automatic results visualization, web-based platforms and NoSQL database client. It is designed for expert and non-specialist users, lowers the barrier to entry for interdisciplinary research within the "AI for Materials" framework. We describe the foundation and use of APEX, as well as provide an example of its application to properties of titanium for a wide-range of bonding descriptions.

In scientific research and its application, scientific literature analysis is crucial as it allows researchers to build on the work of others. However, the fast growth of scientific knowledge has led to a massive increase in scholarly articles, making in-depth literature analysis increasingly challenging and time-consuming. The emergence of Large Language Models (LLMs) has offered a new way to address this challenge. Known for their strong abilities in summarizing texts, LLMs are seen as a potential tool to improve the analysis of scientific literature. However, existing LLMs have their own limits. Scientific literature often includes a wide range of multimodal elements, such as tables, charts, and molecule, which are hard for text-focused LLMs to understand and analyze. This issue points to the urgent need for new solutions that can fully understand and analyze multimodal content in scientific literature. To answer this demand, we present \textbf{Uni-SMART} (Universal Science Multimodal Analysis and Research Transformer), an innovative model designed for in-depth understanding of multimodal scientific literature. Through rigorous quantitative evaluation across several domains, Uni-SMART demonstrates superior performance over other text-focused LLMs. Furthermore, our exploration extends to practical applications, including patent infringement detection and nuanced analysis of charts. These applications not only highlight Uni-SMART's adaptability but also its potential to revolutionize how we interact with scientific literature.

Recent breakthroughs in Large Language Models (LLMs) have revolutionized natural language understanding and generation, sparking significant interest in applying them to scientific literature analysis. However, existing benchmarks fail to adequately evaluate the proficiency of LLMs in this domain, particularly in scenarios requiring higher-level abilities beyond mere memorization and the handling of multimodal data. In response to this gap, we introduce SciAssess, a benchmark specifically designed for the comprehensive evaluation of LLMs in scientific literature analysis. SciAssess aims to thoroughly assess the efficacy of LLMs by focusing on their capabilities in Memorization (L1), Comprehension (L2), and Analysis \& Reasoning (L3). It encompasses a variety of tasks drawn from diverse scientific fields, including fundamental science, alloy materials, biomedicine, drug discovery, and organic materials. To ensure the reliability of SciAssess, rigorous quality control measures have been implemented, ensuring accuracy, anonymization, and compliance with copyright standards. SciAssess evaluates 11 LLMs, including GPT, Claude, and Gemini, highlighting their strengths and areas for improvement. This evaluation supports the ongoing development of LLM applications in the analysis of scientific literature. SciAssess and its resources are available at \url{https://sci-assess.github.io/}.

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

Rapid advancements in machine-learning methods have led to the emergence of machine-learning-based interatomic potentials as a new cutting-edge tool for simulating large systems with ab initio accuracy. Still, the community awaits universal inter-atomic models that can be applied to a wide range of materials without tuning neural network parameters. We develop a unified deep-learning inter-atomic potential (the DPA-Semi model) for 19 semiconductors ranging from group IIB to VIA, including Si, Ge, SiC, BAs, BN, AlN, AlP, AlAs, InP, InAs, InSb, GaN, GaP, GaAs, CdTe, InTe, CdSe, ZnS, and CdS. In addition, independent deep potential models for each semiconductor are prepared for detailed comparison. The training data are obtained by performing density functional theory calculations with numerical atomic orbitals basis sets to reduce the computational costs. We systematically compare various properties of the solid and liquid phases of semiconductors between different machine-learning models. We conclude that the DPA-Semi model achieves GGA exchange-correlation functional quality accuracy and can be regarded as a pre-trained model towards a universal model to study group IIB to VIA semiconductors.

With their celebrated structural and chemical flexibility, perovskite oxides have served as a highly adaptable material platform for exploring emergent phenomena arising from the interplay between different degrees of freedom. Molecular dynamics (MD) simulations leveraging classical force fields, commonly depicted as parameterized analytical functions, have made significant contributions in elucidating the atomistic dynamics and structural properties of crystalline solids including perovskite oxides. However, the force fields currently available for solids are rather specific and offer limited transferability, making it time-consuming to use MD to study new materials systems since a new force field must be parameterized and tested first. The lack of a generalized force field applicable to a broad spectrum of solid materials hinders the facile deployment of MD in computer-aided materials discovery (CAMD). Here, by utilizing a deep-neural network with a self-attention scheme, we have developed a unified force field that enables MD simulations of perovskite oxides involving 14 metal elements and conceivably their solid solutions with arbitrary compositions. Notably, isobaric-isothermal ensemble MD simulations with this model potential accurately predict the experimental phase transition sequences for several markedly different ferroelectric oxides, including a 6-element ternary solid solution, Pb(In$_{1/2}$Nb$_{1/2}$)O$_3$--Pb(Mg$_{1/3}$Nb$_{2/3}$)O$_3$--PbTiO$_3$. We believe the universal interatomic potential along with the training database, proposed regression tests, and the auto-testing workflow, all released publicly, will pave the way for a systematic improvement and extension of a unified force field for solids, potentially heralding a new era in CAMD., Comment: 18 pages, 4 figures

In the current market practice, many cyber insurance products offer a coverage bundle for losses arising from various types of incidents, such as data breaches and ransomware attacks, and the coverage for each incident type comes with a separate limit and deductible. Although this gives prospective cyber insurance buyers more flexibility in customizing the coverage and better manages the risk exposures of sellers, it complicates the decision-making process in determining the optimal amount of risks to retain and transfer for both parties. This paper aims to build an economic foundation for these incident-specific cyber insurance products with a focus on how incident-specific indemnities should be designed for achieving Pareto optimality for both the insurance seller and buyer. Real data on cyber incidents is used to illustrate the feasibility of this approach. Several implementation improvement methods for practicality are also discussed.

Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a challenge for their application to resource-constrained vehicles. One reason for this high resource consumption is the presence of a large number of redundant background points in Lidar point clouds, resulting in spatial redundancy in both 3D voxel and dense BEV map representations. To address this issue, we propose an adaptive inference framework called Ada3D, which focuses on exploiting the input-level spatial redundancy. Ada3D adaptively filters the redundant input, guided by a lightweight importance predictor and the unique properties of the Lidar point cloud. Additionally, we utilize the BEV features' intrinsic sparsity by introducing the Sparsity Preserving Batch Normalization. With Ada3D, we achieve 40% reduction for 3D voxels and decrease the density of 2D BEV feature maps from 100% to 20% without sacrificing accuracy. Ada3D reduces the model computational and memory cost by 5x, and achieves 1.52x/1.45x end-to-end GPU latency and 1.5x/4.5x GPU peak memory optimization for the 3D and 2D backbone respectively., Comment: Accepted at ICCV2023

The spin-dependent Berry force is a genuine effect of Berry curvature in molecular dynamics, which can dramatically result in spatial spin separation and change of reaction pathways. However, the way to probe the effect of Berry force remains challenging, because the time-reversal (TR) symmetry required for opposite Berry forces conflicts with TR symmetry breaking spin alignment needed to observe the effect, and the net effect could be transient for a molecular wave packet. We demonstrate that in molecular photodissociation, the dissociation rates can be different for molecules with opposite initial spin directions due to Berry force. We showcase that the spatially separated spin density, which is transiently induced by Berry force as the molecular wave packet passes through conical intersection, can be reconstructed from the circular dichroism (CD) of ultrafast non-resonant magnetic x-ray scattering using free electron lasers.

Simulating electronic behavior in materials and devices with realistic large system sizes remains a formidable task within the $ab$ $initio$ framework. We propose DeePTB, an efficient deep learning-based tight-binding (TB) approach with $ab$ $initio$ accuracy to address this issue. By training with $ab$ $initio$ eigenvalues, our method can efficiently predict TB Hamiltonians for unseen structures. This capability facilitates efficient simulation of large-size systems under external perturbations like strain, which are vital for semiconductor band gap engineering. Moreover, DeePTB, combined with molecular dynamics, can be used to perform efficient and accurate finite temperature simulations of both atomic and electronic behavior simultaneously. This is demonstrated by computing the temperature-dependent properties of a GaP system with $10^6$ atoms., Comment: 14 pages, 12 figures

Accurate prediction for the electronic structure properties of halide perovskites plays a significant role in the design of highly efficient and stable solar cells. While density functional theory (DFT) within the generalized gradient approximation (GGA) offers reliable prediction in terms of lattice constants and potential energy surface for halide perovskites, it severely underestimates the band gap due to the lack of non-local exact exchange term, which exists in computationally expensive hybrid functionals. In this work, a universal Deep Kohn-Sham (DeePKS) model based on neural network is trained so as to enable electronic structure calculations with the accuracy of hybrid functional HSE06 and the efficiency comparable to GGA functional, for a plethora of halide perovskites, i.e., ABX$_3$ (A=FA, MA, Cs; B=Sn, Pb; X=Cl, Br, I). Forces, band gaps, and density of states (DOS) predicted by our DeePKS model for all aforementioned perovskites are in good agreement with the HSE06 results, with significantly improved efficiency. In addition, even though the spin-orbit coupling (SOC) effect has not been taken into consideration during the training process, DeePKS+SOC offers highly consistent band gap and DOS as compared to HSE06+SOC for Pb-containing systems. We believe such DeePKS model can be readily applied for an accurate yet efficient prediction of various properties for the family of halide perovskites.

The excellent performance of deep neural networks is usually accompanied by a large number of parameters and computations, which have limited their usage on the resource-limited edge devices. To address this issue, abundant methods such as pruning, quantization and knowledge distillation have been proposed to compress neural networks and achieved significant breakthroughs. However, most of these compression methods focus on the architecture or the training method of neural networks but ignore the influence from data augmentation. In this paper, we revisit the usage of data augmentation in model compression and give a comprehensive study on the relation between model sizes and their optimal data augmentation policy. To sum up, we mainly have the following three observations: (A) Models in different sizes prefer data augmentation with different magnitudes. Hence, in iterative pruning, data augmentation with varying magnitudes leads to better performance than data augmentation with a consistent magnitude. (B) Data augmentation with a high magnitude may significantly improve the performance of large models but harm the performance of small models. Fortunately, small models can still benefit from strong data augmentations by firstly learning them with "additional parameters" and then discard these "additional parameters" during inference. (C) The prediction of a pre-trained large model can be utilized to measure the difficulty of data augmentation. Thus it can be utilized as a criterion to design better data augmentation policies. We hope this paper may promote more research on the usage of data augmentation in model compression., Comment: 10 pages, 7 figures, accepted to IJCNN2023

Measuring the thermal conductivity ($\kappa$) of water at extreme conditions is a challenging task and few experimental data are available. We predict $\kappa$ for temperatures and pressures relevant to the conditions of the Earth mantle, between 1,000 and 2,000 K and up to 22 GPa. We employ close to equilibrium molecular dynamics simulations and a deep neural network potential fitted to density functional theory data. We then interpret our results by computing the equation of state of water on a fine grid of points and using a simple model for $\kappa$. We find that the thermal conductivity is weakly dependent on temperature and monotonically increases with pressure with an approximate square-root behavior. In addition we show how the increase of $\kappa$ at high pressure, relative to ambient conditions, is related to the corresponding increase in the sound velocity. Although the relationships between the thermal conductivity, pressure and sound velocity established here are not rigorous, they are sufficiently accurate to allow for a robust estimate of the thermal conductivity of water in a broad range of temperatures and pressures, where experiments are still difficult to perform.

Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data examples; (2) the relational distillation methods are either limited to the handcrafted functions for relation extraction, such as L2 norm, or weak in inter- and intra- class relation modeling. Besides, the feature divergence of heterogeneous teacher-student architectures may lead to inaccurate relational knowledge transferring. In this work, we propose a novel training framework named Class-Oriented Relational Self Distillation (CORSD) to address the limitations. The trainable relation networks are designed to extract relation of structured data input, and they enable the whole model to better classify samples by transferring the relational knowledge from the deepest layer of the model to shallow layers. Besides, auxiliary classifiers are proposed to make relation networks capture class-oriented relation that benefits classification task. Experiments demonstrate that CORSD achieves remarkable improvements. Compared to baseline, 3.8%, 1.5% and 4.5% averaged accuracy boost can be observed on CIFAR100, ImageNet and CUB-200-2011, respectively., Comment: 4 pages, 4 figures, accepted to ICASSP2023

Water freezing is ubiquitous on Earth, affecting many areas from biology to climate science and aviation technology. Probing the atomic structure in the homogeneous ice nucleation process from scratch is of great value but still experimentally unachievable. Theoretical simulations have found that ice originates from the low-mobile region with increasing abundance and persistence of tetrahedrally coordinated water molecules. However, a detailed microscopic picture of how the disordered hydrogen-bond network rearranges itself into an ordered network is still unclear. In this work, we use a deep neural network (DNN) model to "learn" the interatomic potential energy from quantum mechanical data, thereby allowing for large-scale and long molecular dynamics (MD) simulations with ab initio accuracy. The nucleation mechanism and dynamics at atomic resolution, represented by a total of 36 $\mu$s-long MD trajectories, are deeply affected by the structural and dynamical heterogeneity in supercooled water. We find that imperfectly coordinated (IC) water molecules with high mobility pave the way for hydrogen-bond network rearrangement, leading to the growth or shrinkage of the ice nucleus. The hydrogen-bond network formed by perfectly coordinated (PC) molecules stabilizes the nucleus, thus preventing it from vanishing and growing. Consequently, ice is born through competition and cooperation between IC and PC molecules. We anticipate that our picture of the microscopic mechanism of ice nucleation will provide new insights into many properties of water and other relevant materials., Comment: 20 pages, 4 figures, under peer review

Recently deep learning based quantitative structure-activity relationship (QSAR) models has shown surpassing performance than traditional methods for property prediction tasks in drug discovery. However, most DL based QSAR models are restricted to limited labeled data to achieve better performance, and also are sensitive to model scale and hyper-parameters. In this paper, we propose Uni-QSAR, a powerful Auto-ML tool for molecule property prediction tasks. Uni-QSAR combines molecular representation learning (MRL) of 1D sequential tokens, 2D topology graphs, and 3D conformers with pretraining models to leverage rich representation from large-scale unlabeled data. Without any manual fine-tuning or model selection, Uni-QSAR outperforms SOTA in 21/22 tasks of the Therapeutic Data Commons (TDC) benchmark under designed parallel workflow, with an average performance improvement of 6.09\%. Furthermore, we demonstrate the practical usefulness of Uni-QSAR in drug discovery domains.

Atomistic simulations hold significant value in clarifying crucial phenomena such as phase transitions and energy transport in materials science. Their success stems from the presence of potential energy functions capable of accurately depicting the relationship between system energy and lattice changes. In magnetic materials, two atomic scale degrees of freedom come into play: the lattice and the spin. However, accurately tracing the simultaneous evolution of both lattice and spin in magnetic materials at an atomic scale is a substantial challenge. This is largely due to the complexity involved in depicting the interaction energy precisely, and its influence on lattice and spin-driving forces, such as atomic force and magnetic torque, which continues to be a daunting task in computational science. Addressing this deficit, we present DeepSPIN, a versatile approach that generates high-precision predictive models of energy, atomic forces, and magnetic torque in magnetic systems. This is achieved by integrating first-principles calculations of magnetic excited states with deep learning techniques via active learning. We thoroughly explore the methodology, accuracy, and scalability of our proposed model in this paper. Our technique adeptly connects first-principles computations and atomic-scale simulations of magnetic materials. This synergy presents opportunities to utilize these calculations in devising and tackling theoretical and practical obstacles concerning magnetic materials.

DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials (MLP) known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used in the fields of physics, chemistry, biology, and material science for studying atomistic systems. The current version of DeePMD-kit offers numerous advanced features such as DeepPot-SE, attention-based and hybrid descriptors, the ability to fit tensile properties, type embedding, model deviation, Deep Potential - Range Correction (DPRc), Deep Potential Long Range (DPLR), GPU support for customized operators, model compression, non-von Neumann molecular dynamics (NVNMD), and improved usability, including documentation, compiled binary packages, graphical user interfaces (GUI), and application programming interfaces (API). This article presents an overview of the current major version of the DeePMD-kit package, highlighting its features and technical details. Additionally, the article benchmarks the accuracy and efficiency of different models and discusses ongoing developments., Comment: 51 pages, 2 figures

Recent developments in deep learning have made remarkable progress in speeding up the prediction of quantum chemical (QC) properties by removing the need for expensive electronic structure calculations like density functional theory. However, previous methods learned from 1D SMILES sequences or 2D molecular graphs failed to achieve high accuracy as QC properties primarily depend on the 3D equilibrium conformations optimized by electronic structure methods, far different from the sequence-type and graph-type data. In this paper, we propose a novel approach called Uni-Mol+ to tackle this challenge. Uni-Mol+ first generates a raw 3D molecule conformation from inexpensive methods such as RDKit. Then, the raw conformation is iteratively updated to its target DFT equilibrium conformation using neural networks, and the learned conformation will be used to predict the QC properties. To effectively learn this update process towards the equilibrium conformation, we introduce a two-track Transformer model backbone and train it with the QC property prediction task. We also design a novel approach to guide the model's training process. Our extensive benchmarking results demonstrate that the proposed Uni-Mol+ significantly improves the accuracy of QC property prediction in various datasets. We have made the code and model publicly available at \url{https://github.com/dptech-corp/Uni-Mol}.

The multicomponent oxide solid solution is a versatile platform to tune the delicate balance between competing spin, charge, orbital, and lattice degrees of freedom for materials design and discovery. The development of compositionally complex oxides with superior functional properties has been largely empirical and serendipitous, in part due to the exceedingly complex chemistry and structure of solid solutions that span a range of length scales. The classical molecular dynamics (MD), as a powerful statistical method to investigate materials properties over large spatial and temporal scales, often plays a secondary role in computer-aided materials discovery because of the limited availability and accuracy of classical force fields. Here, we introduce the strategy of ``modular developing deep potential" (ModDP) that enables a systematic development and improvement of deep neural network-based model potential, termed as deep potential, for complex solid solutions with minimum human intervention. The converged training database associated with an end-member material is treated as an independent module and is reused to train the deep potential of solid solutions via a concurrent learning procedure. We apply ModDP to obtain classical force fields of two technologically important solid solutions, Pb$_x$Sr$_{1-x}$TiO$_3$ and Hf$_x$Zr$_{1-x}$O$_2$. For both materials systems, a single model potential is capable of predicting various properties of solid solutions including temperature-driven and composition-driven phase transitions over a wide range of compositions. In particular, the deep potential of Pb$_x$Sr$_{1-x}$TiO$_3$ reproduces a few known topological textures such as polar vortex lattice and electric dipole waves in PbTiO$_3$/SrTiO$_3$ superlattices, paving the way for MD investigations on the dynamics of topological structures in response to external stimuli., Comment: 32 pages, 9 figures

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT). The pretrained Transformers are transferred as cross-modal 3D teachers using discrete variational autoencoding self-supervision, during which the Transformers are frozen with prompt tuning for better knowledge inheritance. The latent features encoded by the 3D teachers are used as the target of masked point modeling, wherein the dark knowledge is distilled to the 3D Transformer students as foundational geometry understanding. Our ACT pretrained 3D learner achieves state-of-the-art generalization capacity across various downstream benchmarks, e.g., 88.21% overall accuracy on ScanObjectNN. Codes have been released at https://github.com/RunpeiDong/ACT., Comment: Accepted at ICLR 2023

Ti exhibits complex plastic deformation controlled by active dislocation and twinning systems. Understandings on dislocation cores and twin interfaces are currently not complete or quantitative, despite extensive experimental and simulation studies. Here, we determine all the core and twin interface properties in both HCP and BCC Ti using a Deep Potential (DP) and DFT. We determine the core structures, critical resolved shear stresses and mobilities of , , dislocations in HCP and <111>/2 dislocations in BCC Ti. The slip consists of slow core migration on pyramidal-I planes and fast migration on prism-planes, and is kinetically limited by cross-slips among them. This behaviour is consistent with "locking-unlocking" phenomena in TEM and is likely an intrinsic property. Large-scale DFT calculations provide a peek at the screw core and glide behaviour, which is further quantified using DP-Ti. The screw is unstable on pyramidal-II planes. The mixed is nearly sessile on pyramidal-I planes, consistent with observations of long dislocations in this orientation. The edge and mixed are unstable against a pyramidal-to-basal (PB) transition and become sessile at high temperatures, corroborate the difficulties in -axis compression of Ti. Finally, in BCC Ti, the <111>/2 screw has a degenerate core with average glide on {112} planes; the <111>/2 edge and mixed dislocations have non-dissociated cores on {110} planes. This work paints a self-consistent, complete picture on all dislocations in Ti, rationalises previous experimental observations and points to future HRTEM examinations of unusual dislocations such as the mixed and PB transformed cores.

We propose a quantum Monte Carlo approach to solve the ground state many-body Schrodinger equation for the electronic ground state. The method combines optimization from variational Monte Carlo and propagation from auxiliary field quantum Monte Carlo, in a way that significantly alleviates the sign problem. In application to molecular systems, we obtain highly accurate results for configurations dominated by either dynamic or static electronic correlation.

Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision BEV (bird's-eye-view) detection models is accompanied with enormous parameters and computation, which make them unaffordable on edge devices. To address this problem, in this paper, we propose a structured knowledge distillation framework, aiming to improve the efficiency of modern vision-only BEV detection models. The proposed framework mainly includes: (a) spatial-temporal distillation which distills teacher knowledge of information fusion from different timestamps and views, (b) BEV response distillation which distills teacher response to different pillars, and (c) weight-inheriting which solves the problem of inconsistent inputs between students and teacher in modern transformer architectures. Experimental results show that our method leads to an average improvement of 2.16 mAP and 2.27 NDS on the nuScenes benchmark, outperforming multiple baselines by a large margin., Comment: Codes will be released if this paper is accepted

A hallmark of meso-scale interfacial fluids is the multi-faceted, scale-dependent interfacial energy, which often manifests different characteristics across the molecular and continuum scale. The multi-scale nature imposes a challenge to construct reliable coarse-grained (CG) models, where the CG potential function needs to faithfully encode the many-body interactions arising from the unresolved atomistic interactions and account for the heterogeneous density distributions across the interface. We construct the CG models of both single- and two-component of polymeric fluid systems based on the recently developed deep coarse-grained potential (DeePCG) scheme, where each polymer molecule is modeled as a CG particle. By only using the training samples of the instantaneous force under the thermal equilibrium state, the constructed CG models can accurately reproduce both the probability density function of the void formation in bulk and the spectrum of the capillary wave across the fluid interface. More importantly, the CG models accurately predict the volume-to-area scaling transition for the apolar solvation energy, illustrating the effectiveness to probe the meso-scale collective behaviors encoded with molecular-level fidelity.