Search

Learning a precise robotic grasping policy is crucial for embodied agents operating in complex real-world manipulation tasks. Despite significant advancements, most models still struggle with accurate spatial positioning of objects to be grasped. We first show that this spatial generalization challenge stems primarily from the extensive data requirements for adequate spatial understanding. However, collecting such data with real robots is prohibitively expensive, and relying on simulation data often leads to visual generalization gaps upon deployment. To overcome these challenges, we then focus on state-based policy generalization and present \textbf{ManiBox}, a novel bounding-box-guided manipulation method built on a simulation-based teacher-student framework. The teacher policy efficiently generates scalable simulation data using bounding boxes, which are proven to uniquely determine the objects' spatial positions. The student policy then utilizes these low-dimensional spatial states to enable zero-shot transfer to real robots. Through comprehensive evaluations in simulated and real-world environments, ManiBox demonstrates a marked improvement in spatial grasping generalization and adaptability to diverse objects and backgrounds. Further, our empirical study into scaling laws for policy performance indicates that spatial volume generalization scales positively with data volume. For a certain level of spatial volume, the success rate of grasping empirically follows Michaelis-Menten kinetics relative to data volume, showing a saturation effect as data increases. Our videos and code are available in https://thkkk.github.io/manibox.

We study the well-posedness of solutions to the general nonlinear parabolic equations with merely integrable data in time-dependent Musielak-Orlicz spaces. With the help of a density argument, we establish the existence and uniqueness of both renormalized and entropy solutions. Moreover, we conclude that the entropy and renormalized solutions for this equation are equivalent. Our results cover a variety of problems, including those with Orlicz growth, variable exponents, and double-phase growth.

Here we show a photonic computing accelerator utilizing a system-level thin-film lithium niobate circuit which overcomes this limitation. Leveraging the strong electro-optic (Pockels) effect and the scalability of this platform, we demonstrate photonic computation at speeds up to 1.36 TOPS while consuming 0.057 pJ/OP. Our system features more than 100 thin-film lithium niobate high-performance components working synergistically, surpassing state-of-the-art systems on this platform. We further demonstrate binary-classification, handwritten-digit classification, and image classification with remarkable accuracy, showcasing our system's capability of executing real algorithms. Finally, we investigate the opportunities offered by combining our system with a hybrid-integrated distributed feedback laser source and a heterogeneous-integrated modified uni-traveling carrier photodiode. Our results illustrate the promise of thin-film lithium niobate as a computational platform, addressing current bottlenecks in both electronic and photonic computation. Its unique properties of high-performance electro-optic weight encoding and conversion, wafer-scale scalability, and compatibility with integrated lasers and detectors, position thin-film lithium niobate photonics as a valuable complement to silicon photonics, with extensions to applications in ultrafast and power-efficient signal processing and ranging.

In computer graphics, simplifying a polygonal mesh surface~$\mathcal{M}$ into a geometric proxy that maintains close conformity to~$\mathcal{M}$ is crucial, as it can significantly reduce computational demands in various applications. In this paper, we introduce the Implicit Thin Shell~(ITS), a concept designed to implicitly represent the sandwich-walled space surrounding~$\mathcal{M}$, defined as~$\{\textbf{x}\in\mathbb{R}^3|\epsilon_1\leq f(\textbf{x}) \leq \epsilon_2, \epsilon_1< 0, \epsilon_2>0\}$. Here, $f$ is an approximation of the signed distance function~(SDF) of~$\mathcal{M}$, and we aim to minimize the thickness~$\epsilon_2-\epsilon_1$. To achieve a balance between mathematical simplicity and expressive capability in~$f$, we employ a tri-variate tensor-product B-spline to represent~$f$. This representation is coupled with adaptive knot grids that adapt to the inherent shape variations of~$\mathcal{M}$, while restricting~$f$'s basis functions to the first degree. In this manner, the analytical form of~$f$ can be rapidly determined by solving a sparse linear system. Moreover, the process of identifying the extreme values of~$f$ among the infinitely many points on~$\mathcal{M}$ can be simplified to seeking extremes among a finite set of candidate points. By exhausting the candidate points, we find the extreme values~$\epsilon_1<0$ and $\epsilon_2>0$ that minimize the thickness. The constructed ITS is guaranteed to wrap~$\mathcal{M}$ rigorously, without any intersections between the bounding surfaces and~$\mathcal{M}$. ITS offers numerous potential applications thanks to its rigorousness, tightness, expressiveness, and computational efficiency. We demonstrate the efficacy of ITS in rapid inside-outside tests and in mesh simplification through the control of global error.

For open vocabulary recognition of ingredients in food images, segmenting the ingredients is a crucial step. This paper proposes a novel approach that explores PCA-based feature representations of image pixels using a convolutional neural network (CNN) to enhance segmentation. An internal clustering metric based on the silhouette score is defined to evaluate the clustering quality of various pixel-level feature representations generated by different feature maps derived from various CNN backbones. Using this metric, the paper explores optimal feature representation selection and suitable clustering methods for ingredient segmentation. Additionally, it is found that principal component (PC) maps derived from concatenations of backbone feature maps improve the clustering quality of pixel-level feature representations, resulting in stable segmentation outcomes. Notably, the number of selected eigenvalues can be used as the number of clusters to achieve good segmentation results. The proposed method performs well on the ingredient-labeled dataset FoodSeg103, achieving a mean Intersection over Union (mIoU) score of 0.5423. Importantly, the proposed method is unsupervised, and pixel-level feature representations from backbones are not fine-tuned on specific datasets. This demonstrates the flexibility, generalizability, and interpretability of the proposed method, while reducing the need for extensive labeled datasets.

With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient finetuning (PEFT) method to this trend. Despite its successes, a notable research challenge persists within almost all PEFT approaches: significant performance degradation is observed when there is a substantial disparity between the datasets applied in pretraining and finetuning phases. To address this challenge, we draw inspiration from human visual cognition, and propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based models. Our approach innovatively incorporates the Fast Fourier Transform into prompt embeddings and harmoniously considers both spatial and frequency domain information. Apart from its inherent simplicity and intuitiveness, VFPT exhibits superior performance across all datasets, offering a general solution to dataset challenges, irrespective of data disparities. Empirical results demonstrate that our approach outperforms current state-of-the-art baselines on two benchmarks, with low parameter usage (e.g., 0.57% of model parameters on VTAB-1k) and notable performance enhancements (e.g., 73.20% of mean accuracy on VTAB-1k). Our code is avaliable at https://github.com/runtsang/VFPT., Comment: Conference on Neural Information Processing Systems (NeurIPS) 2024

Architectural deficiencies in EPICS lead to inefficiency in the development and application of EPICS input/output controllers (IOCs). An unintrusive solution is replacing EPICS IOCs with more maintainable and flexible Python IOCs, only reusing the Channel Access (CA) protocol of EPICS. After a digression about GUI development inspired by EPICS operator interfaces (OPIs), the structural similarity between standalone GUI backends, the Mamba backend, EPICS IOCs and other server programs is analysed. By combining the caproto library and event loops like those in these server programs, the QueueIOC framework for Python IOCs is created, which has the potential to systematically replace most EPICS IOCs currently used. Examples are first given for workalikes of StreamDevice and asyn; examples for seq-like applications include monochromators, motor anti-bumping and motor multiplexing. Also shown is software to use with the ~/iocBoot convention which addresses some issues with a similar solution based on procServ, along with a workalike of procServControl. A QueueIOC-based framework for detector integration, which overcomes areaDetector's limitations in performance and architecture, is presented in an accompanying paper., Comment: 14 pages, 8 figures

This research addresses command-line embedding in cybersecurity, a field obstructed by the lack of comprehensive datasets due to privacy and regulation concerns. We propose the first dataset of similar command lines, named CyPHER, for training and unbiased evaluation. The training set is generated using a set of large language models (LLMs) comprising 28,520 similar command-line pairs. Our testing dataset consists of 2,807 similar command-line pairs sourced from authentic command-line data. In addition, we propose a command-line embedding model named CmdCaliper, enabling the computation of semantic similarity with command lines. Performance evaluations demonstrate that the smallest version of CmdCaliper (30 million parameters) suppresses state-of-the-art (SOTA) sentence embedding models with ten times more parameters across various tasks (e.g., malicious command-line detection and similar command-line retrieval). Our study explores the feasibility of data generation using LLMs in the cybersecurity domain. Furthermore, we release our proposed command-line dataset, embedding models' weights and all program codes to the public. This advancement paves the way for more effective command-line embedding for future researchers.

Understanding node representations in graph-based models is crucial for uncovering biases ,diagnosing errors, and building trust in model decisions. However, previous work on explainable AI for node representations has primarily emphasized explanations (reasons for model predictions) rather than interpretations (mapping representations to understandable concepts). Furthermore, the limited research that focuses on interpretation lacks validation, and thus the reliability of such methods is unclear. We address this gap by proposing a novel interpretation method-Node Coherence Rate for Representation Interpretation (NCI)-which quantifies how well different node relations are captured in node representations. We also propose a novel method (IME) to evaluate the accuracy of different interpretation methods. Our experimental results demonstrate that NCI reduces the error of the previous best approach by an average of 39%. We then apply NCI to derive insights about the node representations produced by several graph-based methods and assess their quality in unsupervised settings.

The nature of the high-pressure plaquette-singlet (PS) phase of SrCu$_2$(BO$_3$)$_2$ remains enigmatic. In this work, we revisit the high-pressure $^{11}$B NMR study and identify two distinct coexisting gapped PS states within the NMR spectra. In addition to the previously reported full-plaquette phase, a second PS phase is discerned, characterized by a slightly lower resonance frequency and larger spin-lattice relaxation rates in its ordered phase. Notably, this second phase exhibits enhanced spin fluctuations in its precursor liquid state above the transition temperature. The volume fraction of this phase increases significantly with pressure, reaching approximately 70\% at 2.65~GPa. Furthermore, at 2.4~GPa, a field-induced quantum phase transition from the PS phase to an antiferromagnetic phase is observed around 5.5~T, with a scaling behavior of $1/T_1 \sim T^{0.6}$ near the transition field. This behavior suggests a continuous or nearly continuous nature for the field-induced transition. Our findings provide experimental evidence for the long-sought empty-plaquette singlet phase in SrCu$_2$(BO$_3$)$_2$ within the framework of the Shastry-Sutherland model, thus establishing a promising platform for future studies of deconfined quantum criticality in this model system., Comment: 6 pages, 5 figures

Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling accurate motion estimation across entire videos. Our approach leverages a joint global-local attention mechanism for reduced-resolution tracking, followed by a transformer-based upsampler to achieve high-resolution predictions. Unlike existing methods, which are limited by computational inefficiency or sparse tracking, DELTA delivers dense 3D tracking at scale, running over 8x faster than previous methods while achieving state-of-the-art accuracy. Furthermore, we explore the impact of depth representation on tracking performance and identify log-depth as the optimal choice. Extensive experiments demonstrate the superiority of DELTA on multiple benchmarks, achieving new state-of-the-art results in both 2D and 3D dense tracking tasks. Our method provides a robust solution for applications requiring fine-grained, long-term motion tracking in 3D space., Comment: Project Page: https://snap-research.github.io/DELTA/

This paper presents a novel approach to glass composition screening through a self-supervised learning framework, addressing the challenges posed by glass transition temperature (Tg) prediction. Given the critical role of Tg in determining glass performance across various applications, we reformulate the composition screening task as a classification problem, allowing for direct prediction of whether specific compositional samples fall within a designated Tg range. Our model leverages advanced self-supervised learning techniques to optimize for the area under the curve (AUC) metric, mitigating the adverse effects of noise and class imbalances in training data. We introduce a data augmentation method based on the law of large numbers to enhance sample size and improve noise robustness. Additionally, our DeepGlassNet backbone encoder captures intricate second-order and higher-order interactions among components, providing insights into their collective impact on glass properties. We validate our approach using data from the SciGlass database, demonstrating its capability to accurately predict Tg for compositions within the specified range, while also exploring extrapolation to untested samples. This work not only enhances the accuracy of glass composition screening but also offers scalable solutions applicable to material screening across various fields, thereby advancing the development of novel materials.

The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks in a stepwise manner. However, training CoT capabilities requires detailed reasoning data, which is often scarce. The self-taught reasoner (STaR) framework addresses this by using reinforcement learning to automatically generate reasoning steps, reducing reliance on human-labeled data. Although STaR and its variants have demonstrated empirical success, a theoretical foundation explaining these improvements is lacking. This work provides a theoretical framework for understanding the effectiveness of reinforcement learning on CoT reasoning and STaR. Our contributions are: (1) an analysis of policy improvement, showing why LLM reasoning improves iteratively with STaR; (2) conditions for convergence to an optimal reasoning policy; (3) an examination of STaR's robustness, explaining how it can improve reasoning even when incorporating occasional incorrect steps; and (4) criteria for the quality of pre-trained models necessary to initiate effective reasoning improvement. This framework aims to bridge empirical findings with theoretical insights, advancing reinforcement learning approaches for reasoning in LLMs.

Large Language Models (LLMs) have shown remarkable reasoning capabilities on complex tasks, but they still suffer from out-of-date knowledge, hallucinations, and opaque decision-making. In contrast, Knowledge Graphs (KGs) can provide explicit and editable knowledge for LLMs to alleviate these issues. Existing paradigm of KG-augmented LLM manually predefines the breadth of exploration space and requires flawless navigation in KGs. However, this paradigm cannot adaptively explore reasoning paths in KGs based on the question semantics and self-correct erroneous reasoning paths, resulting in a bottleneck in efficiency and effect. To address these limitations, we propose a novel self-correcting adaptive planning paradigm for KG-augmented LLM named Plan-on-Graph (PoG), which first decomposes the question into several sub-objectives and then repeats the process of adaptively exploring reasoning paths, updating memory, and reflecting on the need to self-correct erroneous reasoning paths until arriving at the answer. Specifically, three important mechanisms of Guidance, Memory, and Reflection are designed to work together, to guarantee the adaptive breadth of self-correcting planning for graph reasoning. Finally, extensive experiments on three real-world datasets demonstrate the effectiveness and efficiency of PoG.

Recent research on large language models (LLMs) has primarily focused on their adaptation and application in specialized domains. The application of LLMs in the medical field is mainly concentrated on tasks such as the automation of medical report generation, summarization, diagnostic reasoning, and question-and-answer interactions between doctors and patients. The challenge of becoming a good teacher is more formidable than that of becoming a good student, and this study pioneers the application of LLMs in the field of medical education. In this work, we investigate the extent to which LLMs can generate medical qualification exam questions and corresponding answers based on few-shot prompts. Utilizing a real-world Chinese dataset of elderly chronic diseases, we tasked the LLMs with generating open-ended questions and answers based on a subset of sampled admission reports across eight widely used LLMs, including ERNIE 4, ChatGLM 4, Doubao, Hunyuan, Spark 4, Qwen, Llama 3, and Mistral. Furthermore, we engaged medical experts to manually evaluate these open-ended questions and answers across multiple dimensions. The study found that LLMs, after using few-shot prompts, can effectively mimic real-world medical qualification exam questions, whereas there is room for improvement in the correctness, evidence-based statements, and professionalism of the generated answers. Moreover, LLMs also demonstrate a decent level of ability to correct and rectify reference answers. Given the immense potential of artificial intelligence in the medical field, the task of generating questions and answers for medical qualification exams aimed at medical students, interns and residents can be a significant focus of future research.

The one-dimensional Kronig-Penney potential in the Schr\"{o}dinger equation, a standard periodic potential in quantum mechanics textbooks known for generating band structures, is solved by using the finite difference method with periodic boundary conditions. This method significantly improves the eigenvalue accuracy compared to existing approaches such as the filter method. The effects of the width and height of the Kronig-Penney potential on the eigenvalues and wave functions are then analyzed. As the potential height increases, the variation of eigenvalues with the wave vector slows down. Additionally, for higher-order band structures, the magnitude of the eigenvalue significantly decreases with increasing potential width. Finally, the Dirac comb potential, a periodic $\delta$ potential, is examined using the present framework. This potential corresponds to the Kronig-Penney potential's width and height approaching zero and infinity, respectively. The numerical results obtained by the finite difference method for the Dirac comb potential are also perfectly consistent with the analytical solution., Comment: 17 pages, 11 figures, 2 tables, accepted by European Journal of Physics

Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local optimum may not be ideal for out-of-distribution data or tasks such as merging and pruning. In this work, we propose a novel progressive training strategy for LoRA with random layer dropping. This strategy also optimizes the Shapley value of LoRA parameters in each layer, treating each layer as a player in a cooperative game. We refer to this method as Cooperative LoRA (CopRA). Our experimental results demonstrate that parameters trained with CopRA exhibit linear mode connectivity, which enables efficient model merging. This also paves the way for federated learning and multi-task learning via LoRA merging. Additionally, by optimizing the Shapley value, CopRA shows superior performance in pruning tasks., Comment: Published in UniReps Workshop (Extended Abstract Track), NeurIPS 2024

The radiative seesaw model with gauged $\mathrm{U(1)}_{B-L}\times\mathbb{Z}_2$ extension is a well-motivated scenario which gives consistent predictions of active neutrino masses and the abundance of dark matter. Majorana masses of right-handed neutrinos, the lightest of which can be identified as dark matter, are given by the spontaneous breaking of the $\mathrm{U(1)}_{B-L}$ gauge symmetry. We revisit this model with the latest constraints from dark matter searches, neutrino oscillations, flavor experiments and collider experiments. We explore the feasible parameter space of this model, and find that there are still allowed regions under the latest experimental constraints. We present new viable benchmark scenarios for this model, i.e., the right-handed neutrino dark matter scenario and the scalar dark matter scenario. We also mention the testability of these benchmark scenarios at future experiments., Comment: 21 pages, 6 figures, 2 tables

In the molecular quantum chemistry community, coupled-cluster (CC) methods are well-recognized for their systematic convergence and reliability. The extension of the theory to extended systems has been comparably recent, so that developments and studies of periodic CC methods for both the ground-state and for excited states are still active fields of research and provide valuable benchmark data when the reliability of density functional approximations is questionable. In this contribution we describe the CC-aims interface between the FHI-aims and the Cc4s software packages. This linkage makes a variety of correlated wave function-based ground-state methods including M\o ller-Plesset perturbation theory (MP2), the random-phase approximation (RPA) and the gold-standard of quantum chemistry CCSD(T) method for both molecular and periodic applications accessible. This contribution discusses these ground-state methods for clusters and molecules, as well as for periodic systems. In particular, we discuss recent advancements and the implementation of the equation-of-motion CC method for the calculation of ionization (IP-EOM-CCSD) and electron attachment (EA-EOM-CCSD) processes. Open questions and routes to solutions are discussed as well., Comment: 7 pages, 5 figures. This is a contribution/chapter to the upcoming "Roadmap on Advancements of the FHI-aims Software Package"

Policy Space Response Oracle (PSRO) with policy population construction has been demonstrated as an effective method for approximating Nash Equilibrium (NE) in zero-sum games. Existing studies have attempted to improve diversity in policy space, primarily by incorporating diversity regularization into the Best Response (BR). However, these methods cause the BR to deviate from maximizing rewards, easily resulting in a population that favors diversity over performance, even when diversity is not always necessary. Consequently, exploitability is difficult to reduce until policies are fully explored, especially in complex games. In this paper, we propose Conflux-PSRO, which fully exploits the diversity of the population by adaptively selecting and training policies at state-level. Specifically, Conflux-PSRO identifies useful policies from the existing population and employs a routing policy to select the most appropriate policies at each decision point, while simultaneously training them to enhance their effectiveness. Compared to the single-policy BR of traditional PSRO and its diversity-improved variants, the BR generated by Conflux-PSRO not only leverages the specialized expertise of diverse policies but also synergistically enhances overall performance. Our experiments on various environments demonstrate that Conflux-PSRO significantly improves the utility of BRs and reduces exploitability compared to existing methods.

Recent experiments suggest a new paradigm towards novel colossal magnetoresistance (CMR) in a family of materials EuM$_2$X$_2$(M=Cd, In, Zn; X=P, As), distinct from the traditional avenues involving Kondo-RKKY crossovers, magnetic phase transitions with structural distortions, or topological phase transitions. Here, we use angle-resolved photoemission spectroscopy (ARPES) and density functional theory (DFT) calculations to explore their origin, particularly focusing on EuCd$_2$P$_2$. While the low-energy spectral weight royally tracks that of the resistivity anomaly near the temperature with maximum magnetoresistance (T$_{MR}$) as expected from transport-spectroscopy correspondence, the spectra are completely incoherent and strongly suppressed with no hint of a Landau quasiparticle. Using systematic material and temperature dependence investigation complemented by theory, we attribute this non-quasiparticle caricature to the strong presence of entangled magnetic and lattice interactions, a characteristic enabled by the $p$-$f$ mixing. Given the known presence of ferromagnetic clusters, this naturally points to the origin of CMR being the scattering of spin-polarized polarons at the boundaries of ferromagnetic clusters. These results are not only illuminating to investigate the strong correlations and topology in EuCd$_2$X$_2$ family, but, in a broader view, exemplify how multiple cooperative interactions can give rise to extraordinary behaviors in condensed matter systems.

Current surgical procedures for spinal cord tumors lack in vivo high-resolution, high-speed multifunctional imaging systems, posing challenges for precise tumor resection and intraoperative decision-making. This study introduces the Fast Adaptive Focus Tracking Robotic Optical Coherence Tomography (FACT-ROCT) system,designed to overcome these obstacles by providing real-time, artifact-free multifunctional imaging of spinal cord tumors during surgery. By integrating cross-scanning, adaptive focus tracking and robotics, the system addresses motion artifacts and resolution degradation from tissue movement, achieving wide-area, high-resolution imaging. We conducted intraoperative imaging on 21 patients, including 13 with spinal gliomas and 8 with other tumors. This study marks the first demonstration of OCT in situ imaging of human spinal cord tumors, providing micrometer-scale in vivo structural images and demonstrating FACT-ROCT's potential to differentiate various tumor types in real-time. Analysis of the attenuation coefficients of spinal gliomas revealed increased heterogeneity with higher malignancy grades. So, we proposed the standard deviation of the attenuation coefficient as a physical marker, achieving over 90% accuracy in distinguishing high- from low-grade gliomas intraoperatively at a threshold. FACT-ROCT even enabled extensive in vivo microvascular imaging of spinal cord tumors, covering 70 mm * 13 mm * 10 mm within 2 minutes. Quantitative vascular tortuosity comparisons confirmed greater tortuosity in higher-grade tumors. The ability to perform extensive vascular imaging and real-time tumor grading during surgery provides critical information for surgical strategy, such as minimizing intraoperative bleeding and optimizing tumor resection while preserving functional tissue.

We investigate the energy band structure and energy levels of a heterojunction composed of two antiferromagnetic graphene nanoflakes with opposite in-plane antiferromagnetic orderings, in which the modified Kane-Mele model is employed. Before forming an antiferromagnetic graphene heterojunction, the energy gap of helical edge states in each isolated graphene nanoflake are opened by the antiferromagnetic ordering and there is no the in-gap corner state. We find that when two opposite antiferromagnetic graphenes are coupled to form a heterojunction nanoflake, topologically protected zero-dimensional in-gap states can be induced. In addition, we demonstrate that the in-gap states locate at the end of the interface and are robust against magnetic disorder, Anderson disorder, and interfacial magnetic defects. The position and number of the in-gap interface end states in the heterojunction sample can be precise quantum controlled., Comment: 13 pages,12 figures

We study the energy spectrum and energy levels of the extended Kane-Mele model with magnetic atoms on their zigzag edges. It is demonstrated that the edges of ferromagnetism or antiferromagnetism are enough to break the time-reversal symmetry and host one-dimensional gapped edge states. Thus, a second-order topological phase transition could happen, which leads to the emergence of topological in-gap zero-dimensional corner states. We also prove that the in-gap corner states are robust against corner defects and magnetic disorder. Our proposal based on the edge antiferromagnetism shows that the high-order topological states can be realized, although the net magnetization of the material is zero. In addition, we discuss the influence of spin magnetization orientation on the degeneracy and energy of in-gap corner states., Comment: 9 pages, 8 figures

We study the energy spectrum and transport property of a one-dimensional Kitaev quantum ring in a threading magnetic field. It is demonstrated that the magnetic field can effectively induce topological phase transitions for the ring in the topologically nontrivial phase at the zero magnetic field. However, for the ring in the topologically trivial phase at the zero field, there is no topological phase transition, and the energy spectrum of the system is always gapped. The magnetic field can control the appearance and disappearance of Majorana zero-energy states in the Kitaev quantum ring, when one half of the ring is in the topologically nontrivial phase and the other half is in the topologically trivial phase. Furthermore, we calculate the transport properties of the ring connected by two semi-infinite leads. It is found that the resonant peaks of transmission coefficient TQT correspond to the critical points of topological phase transition. In addition, we extend our findings to a more realistic quantum ring adopting a semiconductor nanowire with high spin-orbit coupling, superconducting s-wave pairing, and Zeeman splitting, and prove that our findings are universal.

As Advanced Persistent Threats (APTs) grow increasingly sophisticated, the demand for effective detection methods has intensified. This study addresses the challenge of identifying APT campaign attacks through system event logs. A cascading approach, name SFM, combines Technique hunting and APT campaign attribution. Our approach assumes that real-world system event logs contain a vast majority of normal events interspersed with few suspiciously malicious ones and that these logs are annotated with Techniques of MITRE ATT&CK framework for attack pattern recognition. Then, we attribute APT campaign attacks by aligning detected Techniques with known attack sequences to determine the most likely APT campaign. Evaluations on five real-world APT campaigns indicate that the proposed approach demonstrates reliable performance.

Mission-oriented drone networks have been widely used for structural inspection, disaster monitoring, border surveillance, etc. Due to the limited battery capacity of drones, mission execution strategy impacts network performance and mission completion. However, collaborative execution is a challenging problem for drones in such a dynamic environment as it also involves efficient trajectory design. We leverage multi-agent reinforcement learning (MARL) to manage the challenge in this study, letting each drone learn to collaboratively execute tasks and plan trajectories based on its current status and environment. Simulation results show that the proposed collaborative execution model can successfully complete the mission at least 80% of the time, regardless of task locations and lengths, and can even achieve a 100% success rate when the task density is not way too sparse. To the best of our knowledge, our work is one of the pioneer studies on leveraging MARL on collaborative execution for mission-oriented drone networks; the unique value of this work lies in drone battery level driving our model design., Comment: 2022 International Conference on Computer Communications and Networks

The integration of Large Language Models (LLMs) into medical applications has sparked widespread interest across the healthcare industry, from drug discovery and development to clinical decision support, assisting telemedicine, medical devices, and healthcare insurance applications. This perspective paper aims to discuss the inner workings of building LLM-powered medical AI applications and introduces a comprehensive framework for their development. We review existing literature and outline the unique challenges of applying LLMs in specialized medical contexts. Additionally, we introduce a three-step framework to organize medical LLM research activities: 1) Modeling: breaking down complex medical workflows into manageable steps for developing medical-specific models; 2) Optimization: optimizing the model performance with crafted prompts and integrating external knowledge and tools, and 3) System engineering: decomposing complex tasks into subtasks and leveraging human expertise for building medical AI applications. Furthermore, we offer a detailed use case playbook that describes various LLM-powered medical AI applications, such as optimizing clinical trial design, enhancing clinical decision support, and advancing medical imaging analysis. Finally, we discuss various challenges and considerations for building medical AI applications with LLMs, such as handling hallucination issues, data ownership and compliance, privacy, intellectual property considerations, compute cost, sustainability issues, and responsible AI requirements.

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based model is the mismatch between the limited-range modeling power of full attention and the long-range token dependency in the input sequence. In this work, we propose to scale up the attention receptive field by tensorizing long input sequences into compact tensor representations followed by attention on each transformed dimension. The resulting Tensorized Attention can be adopted as efficient transformer backbones to extend input context length with improved memory and time efficiency. We show that the proposed attention tensorization encodes token dependencies as a multi-hop attention process, and is equivalent to Kronecker decomposition of full attention. Extensive experiments show that tensorized attention can be used to adapt pretrained LLMs with improved efficiency. Notably, Llama-8B with tensorization is trained under 32,768 context length and can steadily extrapolate to 128k length during inference with $11\times$ speedup, compared to full attention with FlashAttention-2.

Multimodal Question Answering (MMQA) is crucial as it enables comprehensive understanding and accurate responses by integrating insights from diverse data representations such as tables, charts, and text. Most existing researches in MMQA only focus on two modalities such as image-text QA, table-text QA and chart-text QA, and there remains a notable scarcity in studies that investigate the joint analysis of text, tables, and charts. In this paper, we present C$\text{T}^2$C-QA, a pioneering Chinese reasoning-based QA dataset that includes an extensive collection of text, tables, and charts, meticulously compiled from 200 selectively sourced webpages. Our dataset simulates real webpages and serves as a great test for the capability of the model to analyze and reason with multimodal data, because the answer to a question could appear in various modalities, or even potentially not exist at all. Additionally, we present AED (\textbf{A}llocating, \textbf{E}xpert and \textbf{D}esicion), a multi-agent system implemented through collaborative deployment, information interaction, and collective decision-making among different agents. Specifically, the Assignment Agent is in charge of selecting and activating expert agents, including those proficient in text, tables, and charts. The Decision Agent bears the responsibility of delivering the final verdict, drawing upon the analytical insights provided by these expert agents. We execute a comprehensive analysis, comparing AED with various state-of-the-art models in MMQA, including GPT-4. The experimental outcomes demonstrate that current methodologies, including GPT-4, are yet to meet the benchmarks set by our dataset., Comment: 10 pages, 6 figures

In applications, an anticipated situation is where the system of interest has never been encountered before and sparse observations can be made only once. Can the dynamics be faithfully reconstructed from the limited observations without any training data? This problem defies any known traditional methods of nonlinear time-series analysis as well as existing machine-learning methods that typically require extensive data from the target system for training. We address this challenge by developing a hybrid transformer and reservoir-computing machine-learning scheme. The key idea is that, for a complex and nonlinear target system, the training of the transformer can be conducted not using any data from the target system, but with essentially unlimited synthetic data from known chaotic systems. The trained transformer is then tested with the sparse data from the target system. The output of the transformer is further fed into a reservoir computer for predicting the long-term dynamics or the attractor of the target system. The power of the proposed hybrid machine-learning framework is demonstrated using a large number of prototypical nonlinear dynamical systems, with high reconstruction accuracy even when the available data is only 20% of that required to faithfully represent the dynamical behavior of the underlying system. The framework provides a paradigm of reconstructing complex and nonlinear dynamics in the extreme situation where training data does not exist and the observations are random and sparse., Comment: 31 pages, 21 figures

Chirality is ubiquitous in nature and manifests in a wide range of phenomena including chemical reactions, biological processes, and quantum transport of electrons. In quantum materials, the chirality of fermions, given by the relative directions between the electron spin and momentum, is connected to the band topology of electronic states. Here, we show that in structurally chiral materials like CoSi, the orbital angular momentum (OAM) serves as the main driver of a nontrivial band topology in this new class of unconventional topological semimetals, even when spin-orbit coupling is negligible. A nontrivial orbital-momentum locking of multifold chiral fermions in the bulk leads to a pronounced OAM texture of the helicoid Fermi arcs at the surface. Our findings highlight the pivotal role of the orbital degree of freedom for the chirality and topology of electron states, in general, and pave the way towards the application of topological chiral semimetals in orbitronic devices.

We prove that every simple flop of type $D_5$, i.e. resolved by blowups with exceptional divisor isomorphic to a generalized Grassmann bundle with fiber $OG(4, 10)$, induces a derived equivalence. This provides new evidence for the DK conjecture of Bondal--Orlov and Kawamata. The proof is based on a sequence of mutations of exceptional objects: we use the same argument to prove derived equivalence for some pairs of non birational Calabi--Yau fivefolds in $OG(5, 10)$, related to Manivel's double--spinor Calabi--Yau varieties. We extend the construction to prove derived equivalence of Calabi--Yau fibrations which are described as zero loci in some generalized Grassmann bundles., Comment: 30 pages, comments are very welcome!

In this work, we introduce an advanced acoustic leaky-wave antenna employing zero-refractive-index metamaterials (ZIMs) that significantly surpasses traditional designs in terms of radiation ef-ficiency and directivity. Our design features a novel space-coiling structure, which manipulates the Dirac-like dispersion based on accidental degeneracy to achieve double-zero-index metamaterials (DZIM). The newly developed acoustic Dirac leaky-wave antenna (ADLWA) achieves more than double the radiation efficiency of conventional antennas based on arrays with side holes and mem-branes. It exhibits superior directional control, allowing for precise beam scanning by adjusting the frequency. Additionally, the ADLWA functions effectively as a passive sonar system, capable of de-tecting the direction of moving sound sources. This breakthrough enhances acoustic wave control and promises significant advancements in sensing and communication technologies., Comment: 11 pages, 6 figures

Stock trading has always been a key economic indicator in modern society and a primary source of profit for financial giants such as investment banks, quantitative trading firms, and hedge funds. Discovering the underlying patterns within the seemingly volatile yet intrinsically structured economic activities has become a central focus of research for many companies. Our study leverages widely-used modern financial forecasting algorithms, including LSTM, ANN, CNN, and BiLSTM. We begin by comparing the predictive performance of these well-known algorithms on our stock market data, utilizing metrics such as R2, MAE, MSE, RMSE for detailed evaluation. Based on the performance of these models, we then aim to combine their strengths while mitigating their weaknesses, striving to construct a powerful hybrid model that overcomes the performance limitations of individual models.Through rigorous experimentation and exploration, we ultimately developed an LSTM+ANN model that breaks through prior performance bottlenecks, achieving promising and exciting results., Comment: This paper is accepted by ICISCAE 2024

In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications. As the use of LLMs expands, precisely estimating the uncertainty in their predictions has become crucial. Current methods often struggle to accurately identify, measure, and address the true uncertainty, with many focusing primarily on estimating model confidence. This discrepancy is largely due to an incomplete understanding of where, when, and how uncertainties are injected into models. This paper introduces a comprehensive framework specifically designed to identify and understand the types and sources of uncertainty, aligned with the unique characteristics of LLMs. Our framework enhances the understanding of the diverse landscape of uncertainties by systematically categorizing and defining each type, establishing a solid foundation for developing targeted methods that can precisely quantify these uncertainties. We also provide a detailed introduction to key related concepts and examine the limitations of current methods in mission-critical and safety-sensitive applications. The paper concludes with a perspective on future directions aimed at enhancing the reliability and practical adoption of these methods in real-world scenarios.

Accurately predicting the dynamic responses of building structures under seismic loads is essential for ensuring structural safety and minimizing potential damage. This critical aspect of structural analysis allows engineers to evaluate how structures perform under various loading conditions, facilitating informed design and safety decisions. Traditional methods, which rely on complex finite element models often struggle with balancing computational efficiency and accuracy. To address this challenge, we introduce SeisGPT, a data-driven, large physics-informed model that leverages deep neural networks based on the Generative Pre-trained Transformer (GPT) architecture. SeisGPT is designed to predict, in real-time the dynamic behavior of building structures under seismic forces. Trained on a diverse corpus of seismic data and structural engineering principles, it instantly generates predictive responses, including displacement, acceleration, and inter-story drift, with high accuracy and computational efficiency. Its adaptability across various building typologies and seismic intensities makes this framework a valuable tool for designing robust structures and assessing seismic risk. Through comprehensive validation, this approach exhibits superior performance, offering engineers and researchers a powerful tool for assessing seismic response and informing resilient design strategies. This innovative framework represents a significant advancement in seismic engineering practice, with potential applications in mitigating seismic hazards and enhancing structural resilience., Comment: 23 pages, 6 figures

The increasing concern for data privacy has driven the rapid development of federated learning (FL), a privacy-preserving collaborative paradigm. However, the statistical heterogeneity among clients in FL results in inconsistent performance of the server model across various clients. Server model may show favoritism towards certain clients while performing poorly for others, heightening the challenge of fairness. In this paper, we reconsider the inconsistency in client performance distribution and introduce the concept of adversarial multi-armed bandit to optimize the proposed objective with explicit constraints on performance disparities. Practically, we propose a novel multi-armed bandit-based allocation FL algorithm (FedMABA) to mitigate performance unfairness among diverse clients with different data distributions. Extensive experiments, in different Non-I.I.D. scenarios, demonstrate the exceptional performance of FedMABA in enhancing fairness.

Recently, ternary clathrate hydrides are promising candidates for high-temperature superconductor. However, it is a formidable challenge to effectively hunt high-temperature superconductivity among multinary hydrides due to the expensive computational cost associated with large unit cells and huge stoichiometric choices. Here we present an efficiently data-driven strategy, including generated clathrate frameworks, the quick estimation of stability for each framework and superconducting critical temperature (Tc) for each hydride structure, to accelerate the discovery of high-temperature superconducting hydrides. Our strategy was initialized with more than one million input structures via zeolite databases and our generated dataset. As a result, such a strategy hitherto uncovered 14 prototypical hydrogen frameworks for clathrate hydrides, which is 1.5 times greater than the number (9) of previously reported prototypes. Remarkably, eleven ternary clathrate structures were predicted to have Tcs above 250 K at 300 GPa. Further extensive global structure-searching simulations support that Li2NaH17 and ThY2H24 are thermodynamically stable at 220 and 150 GPa, respectively, with Tcs approaching room temperature of 297 K and 303 K, which are promising for future synthesis. These results offer a platform to explore high-temperature superconductors via a great number of databases., Comment: 24pages

Chaos characterized by its irregularity and high sensitivity to initial conditions finds various applications in secure optical communications, random number generations, light detection and ranging systems, etc. Semiconductor lasers serve as ideal light platforms for chaos generations owing to the advantages in on-chip integration and complex nonlinear effects. In near-infrared wavelengths, semiconductor laser based chaotic light sources have been extensively studied and experimentally demonstrated. However, in the terahertz (THz) spectral range, due to the lack of effective THz light sources and high-speed detectors, chaos generation in THz semiconductor lasers, e.g., quantum cascade lasers (QCLs), is particularly challenging. Due to the fast intersubband carrier transitions, single mode THz QCLs resemble Class A lasers, where chaos can be hardly excited, even with external perturbations. In this work, we experimentally show a THz chaos source based on a sole multimode THz QCL without any external perturbations. Such a dynamical regime is characterized by the largest Lyapunov exponent associated to the temporal traces of the measured radio frequency (intermode beatnote) signal of the laser. The experimental results and chaos validation are confirmed by simulations of our model based on effective semiconductor Maxwell-Bloch Equations. To further understand the physical mechanism of the chaos generation in THz QCLs, a reduced model based on two coupled complex Ginzburg-Landau equations is derived from the full model cited above to systematically investigate the effects of the linewidth enhancement factor and group velocity dispersion on the chaotic regime. This model allows us to show that the chaos generation in the THz QCL can be ascribed to the system attaining the defect mediated turbulence regime., Comment: 30 pages, 6 figures

Here we investigate the internal sublattice symmetry, and thus the enriched topological classification of bosonic Bogoliubov excitations of thermodynamically stable free-boson systems with non-vanishing particle-number-nonconserving terms. Specifically, we show that such systems well described by the bosonic Bogoliubov-de Gennes Hamiltonian can be in general reduced to particle-number-conserving (single-particle) ones. Building upon this observation, the sublattice symmetry is uncovered with respect to an excitation energy, which is usually hidden in the bosonic Bogoliubov-de Gennes Hamiltonian. Thus, we obtain an additional topological class, i.e., class AIII, which enriches the framework for the topological threefold way of free-boson systems. Moreover, a construction is proposed to show a category of systems respecting such a symmetry. For illustration, we resort to a one-dimensional (1D) prototypical model to demonstrate the topological excitation characterized by a winding number or symplectic polarization. By introducing the correlation function, we present an approach to measure the topological invariant. In addition, the edge excitation together with its robustness to symmetry-preserving disorders is also discussed., Comment: 18 pages, 4 figures

Isolated Sign Language Recognition (ISLR) focuses on identifying individual sign language glosses. Considering the diversity of sign languages across geographical regions, developing region-specific ISLR datasets is crucial for supporting communication and research. Auslan, as a sign language specific to Australia, still lacks a dedicated large-scale word-level dataset for the ISLR task. To fill this gap, we curate \underline{\textbf{the first}} large-scale Multi-view Multi-modal Word-Level Australian Sign Language recognition dataset, dubbed MM-WLAuslan. Compared to other publicly available datasets, MM-WLAuslan exhibits three significant advantages: (1) the largest amount of data, (2) the most extensive vocabulary, and (3) the most diverse of multi-modal camera views. Specifically, we record 282K+ sign videos covering 3,215 commonly used Auslan glosses presented by 73 signers in a studio environment. Moreover, our filming system includes two different types of cameras, i.e., three Kinect-V2 cameras and a RealSense camera. We position cameras hemispherically around the front half of the model and simultaneously record videos using all four cameras. Furthermore, we benchmark results with state-of-the-art methods for various multi-modal ISLR settings on MM-WLAuslan, including multi-view, cross-camera, and cross-view. Experiment results indicate that MM-WLAuslan is a challenging ISLR dataset, and we hope this dataset will contribute to the development of Auslan and the advancement of sign languages worldwide. All datasets and benchmarks are available at MM-WLAuslan.

Weakly-supervised methods typically guided the pixel-wise training by comparing the predictions to single-level labels containing diverse segmentation-related information at once, but struggled to represent delicate feature differences between nodule and background regions and confused incorrect information, resulting in underfitting or overfitting in the segmentation predictions. In this work, we propose a weakly-supervised network that generates multi-level labels from four-point annotation to refine diverse constraints for delicate nodule segmentation. The Distance-Similarity Fusion Prior referring to the points annotations filters out information irrelevant to nodules. The bounding box and pure foreground/background labels, generated from the point annotation, guarantee the rationality of the prediction in the arrangement of target localization and the spatial distribution of target/background regions, respectively. Our proposed network outperforms existing weakly-supervised methods on two public datasets with respect to the accuracy and robustness, improving the applicability of deep-learning based segmentation in the clinical practice of thyroid nodule diagnosis.

Two-dimensional (2D) hybrid organic-inorganic perovskite (HOIP) demonstates great potential for developing flexible and wearable spintronic devices, by serving as spin sources via the bulk Rashba effect (BRE). However, the practical application of BRE in 2D HOIP faces huge challenges, particularly due to the toxicity of lead, which is crucial for achieving large spin-orbit coupling, and the restrictions in 2D HOIP candidates to meet specific symmetry-breaking requirements. To overcome these obstacles, we design a strategy to exploit the interfacial Rashba effect (IRE) of lead-free 2D HOIP (C6H5CH2CH2NH3)2CuCl4 (PEA-CuCl), manifesting as an efficient spin generator at room temperature. IRE of PEA-CuCl originates from the large orbital hybridization at the interface between PEA-CuCl and adjacent ferromagnetic layers. Spin-torque ferromagnetic resonance measurements further quantify a large Rashba effective field of 14.04 Oe per 10^11 A m-2, surpassing those of lead-based HOIP and traditional all-inorganic heterojunctions with noble metals. Our lead-free 2D HOIP PEA-CuCl, which harnesses large IRE for spin generation, is efficient, nontoxic, and economic, offering huge promise for future flexible and wearable spintronic devices.

We develop an approach for calculating heavy quark effective theory (HQET) light-cone distribution amplitudes (LCDAs) by employing a sequential effective theory methodology. The theoretical foundation of the framework is established, elucidating how the quasi distribution amplitudes (quasi DAs) with three scales can be utilized to compute HQET LCDAs. We provide theoretical support for this approach by demonstrating the rationale behind devising a hierarchical ordering for the three involved scales, discussing the factorization at each step, clarifying the underlying reason for obtaining HQET LCDAs in the final phase, and addressing potential theoretical challenges. The lattice QCD simulation aspect is explored in detail, and the computations of quasi DAs are presented. We employ three fitting strategies to handle contributions from excited states and extract the bare matrix elements. For renormalization purposes, we apply hybrid renormalization schemes at short and long distance separations. To mitigate long-distance perturbations, we perform an extrapolation in $\lambda= z\cdot P^z$ and assess the stability against various parameters. After two-step matching, our results for HQET LCDAs are found in agreement with existing model parametrizations. The potential phenomenological implications of the results are discussed, shedding light on how these findings could impact our understanding of the strong interaction dynamics and physics beyond the standard model. It should be noted, however, that systematic uncertainties have not been accounted for yet., Comment: 27 pages, 23 figures

Using $(27.12\pm0.14) \times 10^{8}$ $\psi(2S)$ events collected by the BESIII detector operating at BEPCII, we search for the decay $\eta_c(2S)\to p\bar{p}$ via the process $\psi(2S)\to \gamma\eta_c(2S)$, and only find a signal with a significance of $1.7\,\sigma$. The upper limit of the product branching fraction at the 90% confidence level is determined to be $\mathcal{B}(\psi(2S)\to \gamma\eta_c(2S))\times \mathcal{B}(\eta_c(2S)\to p\bar{p})<2.4\times 10^{-7}$. The branching fractions of $\chi_{cJ}\to p\bar{p}~(J=0,1,2)$ are also measured to be $\mathcal{B}(\chi_{c0}\to p\bar{p})=(2.51\pm0.02\pm0.08)\times 10^{-4}$, $\mathcal{B}(\chi_{c1}\to p\bar{p})=(8.16\pm0.09\pm0.25)\times 10^{-4}$, and $\mathcal{B}(\chi_{c2}\to p\bar{p})=(8.33\pm0.09\pm0.22)\times 10^{-4}$, where the first uncertainty is statistical and the second systematic.

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks for MLLMs show limitations in query quality and evaluation reliability limiting the detection of model safety implications as MLLMs continue to evolve. In this paper, we propose \toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol that aims to address the above limitations, respectively. We first design an automatic safety dataset generation pipeline, where we employ a set of LLM judges to recognize and categorize the risk scenarios that are most harmful and diverse for MLLMs; based on the taxonomy, we further ask these judges to generate high-quality harmful queries accordingly resulting in 23 risk scenarios with 2,300 multi-modal harmful query pairs. During safety evaluation, we draw inspiration from the jury system in judicial proceedings and pioneer the jury deliberation evaluation protocol that adopts collaborative LLMs to evaluate whether target models exhibit specific harmful behaviors, providing a reliable and unbiased assessment of content security risks. In addition, our benchmark can also be extended to the audio modality showing high scalability and potential. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs (e.g., GPT-4o, Gemini), where we revealed widespread safety issues in existing MLLMs and instantiated several insights on MLLM safety performance such as image quality and parameter size.

The medial axis, a lower-dimensional shape descriptor, plays an important role in the field of digital geometry processing. Despite its importance, robust computation of the medial axis transform from diverse inputs, especially point clouds with defects, remains a significant challenge. In this paper, we tackle the challenge by proposing a new implicit method that diverges from mainstream explicit medial axis computation techniques. Our key technical insight is the difference between the signed distance field (SDF) and the medial field (MF) of a solid shape is the unsigned distance field (UDF) of the shape's medial axis. This allows for formulating medial axis computation as an implicit reconstruction problem. Utilizing a modified double covering method, we extract the medial axis as the zero level-set of the UDF. Extensive experiments show that our method has enhanced accuracy and robustness in learning compact medial axis transform from thorny meshes and point clouds compared to existing methods.

Random feature latent variable models (RFLVMs) represent the state-of-the-art in latent variable models, capable of handling non-Gaussian likelihoods and effectively uncovering patterns in high-dimensional data. However, their heavy reliance on Monte Carlo sampling results in scalability issues which makes it difficult to use these models for datasets with a massive number of observations. To scale up RFLVMs, we turn to the optimization-based variational Bayesian inference (VBI) algorithm which is known for its scalability compared to sampling-based methods. However, implementing VBI for RFLVMs poses challenges, such as the lack of explicit probability distribution functions (PDFs) for the Dirichlet process (DP) in the kernel learning component, and the incompatibility of existing VBI algorithms with RFLVMs. To address these issues, we introduce a stick-breaking construction for DP to obtain an explicit PDF and a novel VBI algorithm called ``block coordinate descent variational inference" (BCD-VI). This enables the development of a scalable version of RFLVMs, or in short, SRFLVM. Our proposed method shows scalability, computational efficiency, superior performance in generating informative latent representations and the ability of imputing missing data across various real-world datasets, outperforming state-of-the-art competitors.

Memristive associative learning has gained significant attention for its ability to mimic fundamental biological learning mechanisms while maintaining system simplicity. In this work, we introduce a high-order memristive associative learning framework with a biologically realistic structure. By utilizing memristors as synaptic modules and their state information to bridge different orders of associative learning, our design effectively establishes associations between multiple stimuli and replicates the transient nature of high-order associative learning. In Pavlov's classical conditioning experiments, our design achieves a 230% improvement in learning efficiency compared to previous works, with memristor power consumption in the synaptic modules remaining below 11 {\mu}W. In large-scale image recognition tasks, we utilize a 20*20 memristor array to represent images, enabling the system to recognize and label test images with semantic information at 100% accuracy. This scalability across different tasks highlights the framework's potential for a wide range of applications, offering enhanced learning efficiency for current memristor-based neuromorphic systems., Comment: 5 pages, 7 figures