Search

Large Language Models (LLMs) are often English-centric due to the disproportionate distribution of languages in their pre-training data. Enhancing non-English language capabilities through post-pretraining often results in catastrophic forgetting of the ability of original languages. Previous methods either achieve good expansion with severe forgetting or slight forgetting with poor expansion, indicating the challenge of balancing language expansion while preventing forgetting. In this paper, we propose a method called MoE-LPR (Mixture-of-Experts with Language Priors Routing) to alleviate this problem. MoE-LPR employs a two-stage training approach to enhance the multilingual capability. First, the model is post-pretrained into a Mixture-of-Experts (MoE) architecture by upcycling, where all the original parameters are frozen and new experts are added. In this stage, we focus improving the ability on expanded languages, without using any original language data. Then, the model reviews the knowledge of the original languages with replay data amounting to less than 1% of post-pretraining, where we incorporate language priors routing to better recover the abilities of the original languages. Evaluations on multiple benchmarks show that MoE-LPR outperforms other post-pretraining methods. Freezing original parameters preserves original language knowledge while adding new experts preserves the learning ability. Reviewing with LPR enables effective utilization of multilingual knowledge within the parameters. Additionally, the MoE architecture maintains the same inference overhead while increasing total model parameters. Extensive experiments demonstrate MoE-LPR's effectiveness in improving expanded languages and preserving original language proficiency with superior scalability. Code and scripts are freely available at https://github.com/zjwang21/MoE-LPR.git.

We consider the problem of fair allocation with subsidy when agents have weighted entitlements. After highlighting several important differences from the unweighted cases, we present several results concerning weighted envy-freeability including general characterizations, algorithms for achieving and testing weighted envy-freeability, lower and upper bounds for worst case subsidy for non-wasteful and envy-freeable allocations, and algorithms for achieving weighted envy-freeability along with other properties., Comment: 20 pages, 1 Table

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance problem-solving, but MLLMs perform worse as information shifts from textual to visual modality. This decline is mainly due to their shortcomings in aligning images and text. To tackle aforementioned challenges, we propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment. This approach is designed to improve the mathematical reasoning skills of MLLMs through a three-stage training process, with the second stage being the critical alignment stage. We first enhance the language model's mathematical reasoning capabilities with extensive set of textual mathematical problems. We then construct a multimodal dataset with varying degrees of textual and visual information, creating data pairs by presenting each problem in at least two forms. By leveraging the Kullback-Leibler (KL) divergence of next-token prediction distributions to align visual and textual modalities, consistent problem-solving abilities are ensured. Finally, we utilize multimodal instruction tuning for MLLMs with high-quality multimodal data. Experimental results on multiple mathematical reasoning benchmarks demonstrate that the MLLMs trained with Math-PUMA surpass most open-source MLLMs. Our approach effectively narrows the performance gap for problems presented in different modalities.

Checkpoint/Restart (C/R) has been widely deployed in numerous HPC systems, Clouds, and industrial data centers, which are typically operated by system engineers. Nevertheless, there is no existing approach that helps system engineers without domain expertise, and domain scientists without system fault tolerance knowledge identify those critical variables accounted for correct application execution restoration in a failure for C/R. To address this problem, we propose an analytical model and a tool (AutoCheck) that can automatically identify critical variables to checkpoint for C/R. AutoCheck relies on first, analytically tracking and optimizing data dependency between variables and other application execution state, and second, a set of heuristics that identify critical variables for checkpointing from the refined data dependency graph (DDG). AutoCheck allows programmers to pinpoint critical variables to checkpoint quickly within a few minutes. We evaluate AutoCheck on 14 representative HPC benchmarks, demonstrating that AutoCheck can efficiently identify correct critical variables to checkpoint., Comment: 11 pages, 7 figures, 4 tables

Unified graph representation learning aims to produce node embeddings, which can be applied to multiple downstream applications. However, existing studies based on graph neural networks and language models either suffer from the limitations of numerous training needed toward specific downstream predictions or have shallow semantic features. In this work, we propose a novel Path-LLM model to learn unified graph representation, which leverages a powerful large language model (LLM) to incorporate our proposed path features. Our Path-LLM framework consists of several well-designed techniques. First, we develop a new mechanism of long-to-short shortest path (L2SP) selection, which covers essential connections between different dense groups. An in-depth comparison of different path selection plans is offered to illustrate the strength of our designed L2SP. Then, we design path textualization to obtain L2SP-based training texts. Next, we feed the texts into a self-supervised LLM training process to learn embeddings. Extensive experiments on benchmarks validate the superiority of Path-LLM against the state-of-the-art WalkLM method on two classical graph learning tasks (node classification and link prediction) and one NP-hard graph query processing task (keyword search), meanwhile saving more than 90% of training paths., Comment: 12 pages, 8 figures

Sequential recommendation leverages interaction sequences to predict forthcoming user behaviors, crucial for crafting personalized recommendations. However, the true preferences of a user are inherently complex and high-dimensional, while the observed data is merely a simplified and low-dimensional projection of the rich preferences, which often leads to prevalent issues like data sparsity and inaccurate model training. To learn true preferences from the sparse data, most existing works endeavor to introduce some extra information or design some ingenious models. Although they have shown to be effective, extra information usually increases the cost of data collection, and complex models may result in difficulty in deployment. Innovatively, we avoid the use of extra information or alterations to the model; instead, we fill the transformation space between the observed data and the underlying preferences with randomness. Specifically, we propose a novel model-agnostic and highly generic framework for sequential recommendation called sample enrichment via temporary operations on subsequences (SETO), which temporarily and separately enriches the transformation space via sequence enhancement operations with rationality constraints in training. The transformation space not only exists in the process from input samples to preferences but also in preferences to target samples. We highlight our SETO's effectiveness and versatility over multiple representative and state-of-the-art sequential recommendation models (including six single-domain sequential models and two cross-domain sequential models) across multiple real-world datasets (including three single-domain datasets, three cross-domain datasets and a large-scale industry dataset)., Comment: 12 pages, 6 figures

Data summarization aims at utilizing a small-scale summary to represent massive datasets as a whole, which is useful for visualization and information sipped generation. However, most existing studies of hierarchical summarization only work on \emph{one single tree} by selecting $k$ representative nodes, which neglects an important problem of comparative summarization on two trees. In this paper, given two trees with the same topology structure and different node weights, we aim at finding $k$ representative nodes, where $k_1$ nodes summarize the common relationship between them and $k_2$ nodes highlight significantly different sub-trees meanwhile satisfying $k_1+k_2=k$. To optimize summarization results, we introduce a scaling coefficient for balancing the summary view between two sub-trees in terms of similarity and difference. Additionally, we propose a novel definition based on the Hellinger distance to quantify the node distribution difference between the sub-trees. We present a greedy algorithm SVDT to find high-quality results with approximation guaranteed in an efficient way. Furthermore, we explore an extension of our comparative summarization to handle two trees with different structures. Extensive experiments demonstrate the effectiveness and efficiency of our SVDT algorithm against existing summarization competitors.

This paper introduces MM-Instruct, a large-scale dataset of diverse and high-quality visual instruction data designed to enhance the instruction-following capabilities of large multimodal models (LMMs). While existing visual instruction datasets often focus on question-answering, they struggle to generalize to broader application scenarios such as creative writing, summarization, or image analysis. To address these limitations, we propose a novel approach to constructing MM-Instruct that leverages the strong instruction-following capabilities of existing LLMs to generate novel visual instruction data from large-scale but conventional image captioning datasets. MM-Instruct first leverages ChatGPT to automatically generate diverse instructions from a small set of seed instructions through augmenting and summarization. It then matches these instructions with images and uses an open-sourced large language model (LLM) to generate coherent answers to the instruction-image pairs. The LLM is grounded by the detailed text descriptions of images in the whole answer generation process to guarantee the alignment of the instruction data. Moreover, we introduce a benchmark based on the generated instruction data to evaluate the instruction-following capabilities of existing LMMs. We demonstrate the effectiveness of MM-Instruct by training a LLaVA-1.5 model on the generated data, denoted as LLaVA-Instruct, which exhibits significant improvements in instruction-following capabilities compared to LLaVA-1.5 models. The MM-Instruct dataset, benchmark, and pre-trained models are available at https://github.com/jihaonew/MM-Instruct., Comment: Dataset and models are available at https://github.com/jihaonew/MM-Instruct

Large Language Models have demonstrated impressive reasoning capabilities across multiple languages. However, the relationship between capabilities in different languages is less explored. In this work, we decompose the process of reasoning tasks into two separated parts: knowledge retrieval and knowledge-free reasoning, and analyze the cross-lingual transferability of them. With adapted and constructed knowledge-free reasoning datasets, we show that the knowledge-free reasoning capability can be nearly perfectly transferred across various source-target language directions despite the secondary impact of resource in some specific target languages, while cross-lingual knowledge retrieval significantly hinders the transfer. Moreover, by analyzing the hidden states and feed-forward network neuron activation during the reasoning tasks, we show that higher similarity of hidden representations and larger overlap of activated neurons could explain the better cross-lingual transferability of knowledge-free reasoning than knowledge retrieval. Thus, we hypothesize that knowledge-free reasoning embeds in some language-shared mechanism, while knowledge is stored separately in different languages.

Random feature neural network approximations of the potential in Hamiltonian systems yield approximations of molecular dynamics correlation observables that have the expected error $\mathcal{O}\big((K^{-1}+J^{-1/2})^{\frac{1}{2}}\big)$, for networks with $K$ nodes using $J$ data points, provided the Hessians of the potential and the observables are bounded. The loss function is based on the least squares error of the potential and regularizations, with the data points sampled from the Gibbs density. The proof uses an elementary new derivation of the generalization error for random feature networks that does not apply the Rademacher or related complexities., Comment: 28 page, 9 figures

We introduce a new type of equivalence between blocks of finite group algebras called an almost isotypy. An almost isotypy restricts to a weak isotypy in Brou\'{e}'s original definition, and it is slightly weaker than Linckelmann's version. We show that a bimodule of two block algebras of finite groups - which has an endopermutation module as a source and which induces a Morita equivalence - gives rise to an almost isotypy if and only if the character values of a (hence any) source are rational integers. This generalises a previous result of Huang and Zhou. Consequently, if two blocks are Morita equivalent via a bimodule with endopermutation source, then they are almost isotypic., Comment: revised version

Van der Waals heterostructures have emerged as an ideal platform for creating engineered artificial electronic states. While vertical heterostructures have been extensively studied, realizing high-quality lateral heterostructures with atomically sharp interfaces remains a major experimental challenge. Here, we advance a one-pot two-step molecular beam lateral epitaxy approach and successfully synthesize atomically well-defined 1T-VSe$_2$ -- 1H-NbSe$_2$ lateral heterostructures. We demonstrate the formation of defect-free lateral heterostructures and characterize their electronic structure using scanning tunnelling microscopy and spectroscopy together with density functional theory calculations. We find additional electronic states at the one-dimensional interface as well as signatures of Kondo resonances in a side-coupled geometry. Our experiments explore the full potential of lateral heterostructures for realizing exotic electronic states in low-dimensional systems for further studies of artificial designer quantum materials.

We explore the bound neutrons decay into invisible particles (e.g., $n\rightarrow 3 \nu$ or $nn \rightarrow 2 \nu$) in the JUNO liquid scintillator detector. The invisible decay includes two decay modes: $ n \rightarrow { inv} $ and $ nn \rightarrow { inv} $. The invisible decays of $s$-shell neutrons in $^{12}{\rm C}$ will leave a highly excited residual nucleus. Subsequently, some de-excitation modes of the excited residual nuclei can produce a time- and space-correlated triple coincidence signal in the JUNO detector. Based on a full Monte Carlo simulation informed with the latest available data, we estimate all backgrounds, including inverse beta decay events of the reactor antineutrino $\bar{\nu}_e$, natural radioactivity, cosmogenic isotopes and neutral current interactions of atmospheric neutrinos. Pulse shape discrimination and multivariate analysis techniques are employed to further suppress backgrounds. With two years of exposure, JUNO is expected to give an order of magnitude improvement compared to the current best limits. After 10 years of data taking, the JUNO expected sensitivities at a 90% confidence level are $\tau/B( n \rightarrow { inv} ) > 5.0 \times 10^{31} \, {\rm yr}$ and $\tau/B( nn \rightarrow { inv} ) > 1.4 \times 10^{32} \, {\rm yr}$., Comment: 28 pages, 7 figures, 4 tables

Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an effective method to enhance the LLMs' multilingual capabilities. In this work, we discover and comprehensively investigate the spontaneous multilingual alignment improvement of LLMs. We find that LLMs instruction-tuned on the question translation data (i.e. without annotated answers) are able to encourage the alignment between English and a wide range of languages, even including those unseen during instruction-tuning. Additionally, we utilize different settings and mechanistic interpretability methods to analyze the LLM's performance in the multilingual scenario comprehensively. Our work suggests that LLMs have enormous potential for improving multilingual alignment efficiently with great language and task generalization.

We present photometric and spectroscopic observations and analysis of the type IIb supernova (SN) SN 2019tua, which exhibits multiple bumps in its declining light curves between 40 and 65 days after discovery. SN 2019tua shows a time to peak of about 25 days similar to other type IIb SNe. Our observations indicate a decrease in its brightness of about 1 magnitude in the 60 days after the peak. At about days 50, and 60, its multiband light curves exhibit bumpy behavior. The complex luminosity evolution of SN 2019tua could not be well modeled with a single currently popular energy source model, e.g., radioactive decay of $^{56}$Ni, magnetar, interaction between the ejecta and a circumstellar shell. Even though the magnetar model has a smaller $\chi^2 / \text{dof}$ value, the complex changes in SN 2019tua's brightness suggest that more than one physical process might be involved. We propose a hybrid CSM interaction plus $^{56}$Ni model to explain the bolometric light curve (LC) of SN 2019tua. The fitting results show that the ejecta mass $M_{\rm ej} \approx 2.4~M_\odot$, the total CSM mass $M_{\rm CSM} \approx 1.0~M_\odot$, and the $^{56}$Ni mass $M_{\rm Ni} \approx 0.4~M_\odot$. The total kinetic energy of the ejecta is $E_k\approx 0.5 \times 10^{51}\rm~erg$. Pre-existing multiple shells suggest that the progenitor of SN 2019tua experienced mass ejections within approximately $\sim6 - 44$ years prior to the explosion., Comment: Accepted for publication in ApJ. 24 pages, 17 figures, 6 tables

In this paper, we associate the quantum toroidal algebra $\mathcal{E}_N$ of type $\mathfrak{gl}_N$ with quantum vertex algebra through equivariant $\phi$-coordinated quasi modules. More precisely, for every $\ell\in \mathbb{C}$, by deforming the universal affine vertex algebra of $\mathfrak{sl}_\infty$, we construct an $\hbar$-adic quantum $\Z$-vertex algebra $V_{\widehat{\mathfrak{sl}}_{\infty},\hbar}(\ell,0)$. Then we prove that the category of restricted $\mathcal{E}_N$-modules of level $\ell$ is canonically isomorphic to that of equivariant $\phi$-coordinated quasi $V_{\widehat{\mathfrak{sl}}_{\infty},\hbar}(\ell,0)$-modules.

A graph is a fundamental data model to represent various entities and their complex relationships in society and nature, such as social networks, transportation networks, financial networks, and biomedical systems. Recently, large language models (LLMs) have showcased a strong generalization ability to handle various NLP and multi-mode tasks to answer users' arbitrary questions and specific-domain content generation. Compared with graph learning models, LLMs enjoy superior advantages in addressing the challenges of generalizing graph tasks by eliminating the need for training graph learning models and reducing the cost of manual annotation. In this survey, we conduct a comprehensive investigation of existing LLM studies on graph data, which summarizes the relevant graph analytics tasks solved by advanced LLM models and points out the existing remaining challenges and future directions. Specifically, we study the key problems of LLM-based generative graph analytics (LLM-GGA) with three categories: LLM-based graph query processing (LLM-GQP), LLM-based graph inference and learning (LLM-GIL), and graph-LLM-based applications. LLM-GQP focuses on an integration of graph analytics techniques and LLM prompts, including graph understanding and knowledge graph (KG) based augmented retrieval, while LLM-GIL focuses on learning and reasoning over graphs, including graph learning, graph-formed reasoning and graph representation. We summarize the useful prompts incorporated into LLM to handle different graph downstream tasks. Moreover, we give a summary of LLM model evaluation, benchmark datasets/tasks, and a deep pro and cons analysis of LLM models. We also explore open problems and future directions in this exciting interdisciplinary research area of LLMs and graph analytics., Comment: 31 pages including references, 22 figures

Moir\'e materials provide a unique platform for studies of correlated many-body physics of the Fermi-Hubbard model on triangular spin-charge lattices. Bilayer Hubbard models are of particular significance with regard to the physics of Mott insulating states and their relation to unconventional superconductivity, yet their experimental implementation in moir\'e systems has so far remained elusive. Here, we demonstrate the realization of a staggered bilayer triangular lattice of electrons in an antiparallel MoSe$_{2}$/WS$_{2}$ heterostructure. The bilayer lattice emerges due to strong electron confinement in the moir\'e potential minima and the near-resonant alignment of conduction band edges in MoSe$_{2}$ and WS$_{2}$. As a result, charge filling proceeds layer-by-layer, with the first and second electron per moir\'e cell consecutively occupying first the MoSe$_{2}$ and then the WS$_{2}$ layer. We describe the observed charging sequence by an electrostatic model and provide experimental evidence of spin correlations on the vertically offset and laterally staggered bilayer lattice, yielding absolute exciton Land\'e factors as high as $600$ at lowest temperatures. The bilayer character of the implemented spin-charge lattice allows for electrostatic tunability of Ruderman-Kittel-Kasuya-Yosida magnetism, and establishes antiparallel MoSe$_{2}$/WS$_{2}$ heterostructures as a viable platform for studies of bilayer Hubbard model physics with exotic magnetic phases on frustrated lattices.

Graph neural networks have been shown successful in recent years. While different GNN architectures and training systems have been developed, GNN training on large-scale real-world graphs still remains challenging. Existing distributed systems load the entire graph in memory for graph partitioning, requiring a huge memory space to process large graphs and thus hindering GNN training on such large graphs using commodity workstations. In this paper, we propose CATGNN, a cost-efficient and scalable distributed GNN training system which focuses on scaling GNN training to billion-scale or larger graphs under limited computational resources. Among other features, it takes a stream of edges as input, instead of loading the entire graph in memory, for partitioning. We also propose a novel streaming partitioning algorithm named SPRING for distributed GNN training. We verify the correctness and effectiveness of CATGNN with SPRING on 16 open datasets. In particular, we demonstrate that CATGNN can handle the largest publicly available dataset with limited memory, which would have been infeasible without increasing the memory space. SPRING also outperforms state-of-the-art partitioning algorithms significantly, with a 50% reduction in replication factor on average.

Large language model evaluation plays a pivotal role in the enhancement of its capacity. Previously, numerous methods for evaluating large language models have been proposed in this area. Despite their effectiveness, these existing works mainly focus on assessing objective questions, overlooking the capability to evaluate subjective questions which is extremely common for large language models. Additionally, these methods predominantly utilize centralized datasets for evaluation, with question banks concentrated within the evaluation platforms themselves. Moreover, the evaluation processes employed by these platforms often overlook personalized factors, neglecting to consider the individual characteristics of both the evaluators and the models being evaluated. To address these limitations, we propose a novel anonymous crowd-sourcing evaluation platform, BingJian, for large language models that employs a competitive scoring mechanism where users participate in ranking models based on their performance. This platform stands out not only for its support of centralized evaluations to assess the general capabilities of models but also for offering an open evaluation gateway. Through this gateway, users have the opportunity to submit their questions, testing the models on a personalized and potentially broader range of capabilities. Furthermore, our platform introduces personalized evaluation scenarios, leveraging various forms of human-computer interaction to assess large language models in a manner that accounts for individual user preferences and contexts. The demonstration of BingJian can be accessed at https://github.com/Mingyue-Cheng/Bingjian.

3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning. Recent advances in deep learning have significantly enhanced fully supervised medical image segmentation. However, this approach heavily relies on labor-intensive and time-consuming fully annotated ground-truth labels, particularly for 3D volumes. To overcome this limitation, we propose a novel probabilistic-aware weakly supervised learning pipeline, specifically designed for 3D medical imaging. Our pipeline integrates three innovative components: a probability-based pseudo-label generation technique for synthesizing dense segmentation masks from sparse annotations, a Probabilistic Multi-head Self-Attention network for robust feature extraction within our Probabilistic Transformer Network, and a Probability-informed Segmentation Loss Function to enhance training with annotation confidence. Demonstrating significant advances, our approach not only rivals the performance of fully supervised methods but also surpasses existing weakly supervised methods in CT and MRI datasets, achieving up to 18.1% improvement in Dice scores for certain organs. The code is available at https://github.com/runminjiang/PW4MedSeg.

Understanding the dynamical behavior of a qubit in a reservoir is critical to applications in quantum technological protocols, ranging from quantum computation to quantum metrology. The effect of the reservoir depends on reservoir's spectral structure, as well as on the qubit-reservoir coupling strength. We here propose a measure for quantifying the non-Markovian effect of a reservoir with a Lorentzian spectrum, based on the maximum qubit-reservoir quantum entanglement that can be extracted. Numerical simulation shows this entanglement exhibits a monotonous behavior in response to the variation of the coupling strength. We confirm the validity of this measure with an experiment, where a superconducting qubit is controllably coupled to a lossy resonator, which acts as a reservoir for the qubit. The experimental results illustrate the maximal extractable entanglement is progressively increased with the strengthening of the non-Markovianity.

Due to the lack of depth cues in images, multi-frame inputs are important for the success of vision-based perception, prediction, and planning in autonomous driving. Observations from different angles enable the recovery of 3D object states from 2D image inputs if we can identify the same instance in different input frames. However, the dynamic nature of autonomous driving scenes leads to significant changes in the appearance and shape of each instance captured by the camera at different time steps. To this end, we propose a novel contrastive learning algorithm, Cohere3D, to learn coherent instance representations in a long-term input sequence robust to the change in distance and perspective. The learned representation aids in instance-level correspondence across multiple input frames in downstream tasks. In the pretraining stage, the raw point clouds from LiDAR sensors are utilized to construct the long-term temporal correspondence for each instance, which serves as guidance for the extraction of instance-level representation from the vision-based bird's eye-view (BEV) feature map. Cohere3D encourages a consistent representation for the same instance at different frames but distinguishes between representations of different instances. We evaluate our algorithm by finetuning the pretrained model on various downstream perception, prediction, and planning tasks. Results show a notable improvement in both data efficiency and task performance.

Mrk 501 is a prototypical high-synchrotron-peaked blazar (HBL) and serves as one of the primary targets for the {\it Imaging X-ray Polarimetry Explorer} ({\it IXPE}). In this study, we report X-ray polarization measurements of Mrk 501 based on six {\it IXPE} observations. The detection of X-ray polarization at a confidence level exceeding 99\% is achieved in four out of the six observations conducted across the entire energy range (2--8 keV) of {\it IXPE}. The maximum polarization degree ($\Pi_{\rm X}$) is measured to be $15.8\%\pm2.8\%$, accompanied by a polarization angle ($\psi_{\rm X}$) of $98.0\deg\pm5.1\deg$ at a confidence level of $5.6 \sigma$. During the remaining two observations, only an upper limit of $\Pi_{\rm X}<$12\% could be derived at the 99\% confidence level. No temporal variability in polarization is observed throughout all six {\it IXPE} observations for Mrk 501. A discernible trend of energy-dependent variation in the polarization degree is detected in optical spectropolarimetry; however, no analogous indication is observed in $\Pi_{\rm X}$. The chromatic behavior of $\Pi$ and the consistent values of $\psi$ across different frequencies from X-rays to radio waves, along with the agreement between $\psi$ and jet position angle, strongly support the interpretation of the energy-stratified model with shock-accelerated particles in the jet of Mrk 501. Additionally, the possibility of the presence of a global helical magnetic field in the jet of Mrk 501 is discussed., Comment: 20 pages, 8 figures, 4 tables, accepted for publication in ApJL

A method was proposed for the point cloud-based registration and image fusion between cardiac single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) and cardiac computed tomography angiograms (CTA). Firstly, the left ventricle (LV) epicardial regions (LVERs) in SPECT and CTA images were segmented by using different U-Net neural networks trained to generate the point clouds of the LV epicardial contours (LVECs). Secondly, according to the characteristics of cardiac anatomy, the special points of anterior and posterior interventricular grooves (APIGs) were manually marked in both SPECT and CTA image volumes. Thirdly, we developed an in-house program for coarsely registering the special points of APIGs to ensure a correct cardiac orientation alignment between SPECT and CTA images. Fourthly, we employed ICP, SICP or CPD algorithm to achieve a fine registration for the point clouds (together with the special points of APIGs) of the LV epicardial surfaces (LVERs) in SPECT and CTA images. Finally, the image fusion between SPECT and CTA was realized after the fine registration. The experimental results showed that the cardiac orientation was aligned well and the mean distance error of the optimal registration method (CPD with affine transform) was consistently less than 3 mm. The proposed method could effectively fuse the structures from cardiac CTA and SPECT functional images, and demonstrated a potential in assisting in accurate diagnosis of cardiac diseases by combining complementary advantages of the two imaging modalities.

We report experimental and theoretical studies of MoTe$_2$-MoSe$_2$ heterobilayers with rigid moir\'e superlattices controlled by the twist angle. Using an effective continuum model that combines resonant interlayer electron tunneling with stacking-dependent moir\'e potentials, we identify the nature of moir\'e excitons and the dependence of their energies, oscillator strengths and Land\'e $g$-factors on the twist angle. Within the same framework, we interpret distinct signatures of bound complexes among electrons and moir\'e excitons in nearly collinear heterostacks. Our work provides fundamental understanding of hybrid moir\'e excitons and trions in MoTe$_2$-MoSe$_2$ heterobilayers, and establishes the material system as a prime candidate for optical studies of correlated phenomena in moir\'e lattices.

Owing to the presence of exceptional points (EPs), non-Hermitian (NH) systems can display intriguing topological phenomena without Hermitian analogs. However, experimental characteristics of exceptional topological invariants have been restricted to second-order EPs (EP2s) in classical or semiclassical systems. We here propose an NH multi-qubit model with higher-order EPs, each of which is underlain by a multifold-degenerate multipartite entangled eigenstate. We implement the three-qubit model by controllably coupling a superconducting qubit to two microwave resonators, one serving as a Hermitian photonic qubit while the other as an NH qubit. We experimentally quantify the topological invariant for an EP3, by mapping out the complex eigenspectra along a loop surrounding this EP3 in the parameter space. The nonclassicality of the realized topology is manifested by the observed quantum correlations in the corresponding eigenstates. Our results extend research of exceptional topology to fully quantum-mechanical models with multi-partite entangled eigenstates. We further demonstrate the non-reciprocal transmission of a single photon, during which the photon is nonlocally shared by three individual elements.

In the realm of Earth science, effective cloud property retrieval, encompassing cloud masking, cloud phase classification, and cloud optical thickness (COT) prediction, remains pivotal. Traditional methodologies necessitate distinct models for each sensor instrument due to their unique spectral characteristics. Recent strides in Earth Science research have embraced machine learning and deep learning techniques to extract features from satellite datasets' spectral observations. However, prevailing approaches lack novel architectures accounting for hierarchical relationships among retrieval tasks. Moreover, considering the spectral diversity among existing sensors, the development of models with robust generalization capabilities over different sensor datasets is imperative. Surprisingly, there is a dearth of methodologies addressing the selection of an optimal model for diverse datasets. In response, this paper introduces MT-HCCAR, an end-to-end deep learning model employing multi-task learning to simultaneously tackle cloud masking, cloud phase retrieval (classification tasks), and COT prediction (a regression task). The MT-HCCAR integrates a hierarchical classification network (HC) and a classification-assisted attention-based regression network (CAR), enhancing precision and robustness in cloud labeling and COT prediction. Additionally, a comprehensive model selection method rooted in K-fold cross-validation, one standard error rule, and two introduced performance scores is proposed to select the optimal model over three simulated satellite datasets OCI, VIIRS, and ABI. The experiments comparing MT-HCCAR with baseline methods, the ablation studies, and the model selection affirm the superiority and the generalization capabilities of MT-HCCAR., Comment: 14 pages, 3 figures, accepted by ECML PKDD 2024

We extend a theorem of Kessar and Linckelmann concerning Morita equivalences and Brauer character bijections between blocks to virtual Morita equivalences. As a corollary, we obtain that Navarro's refinement of Alperin's weight conjecture holds for blocks with cyclic and Klein four defect groups, blocks of symmetric and alternating groups with abelian defect groups, and $p$-blocks of ${\rm SL}_2(q)$ and ${\rm GL}_2(q)$, where $p|q$., Comment: minor corrections, the block version of Navarro's refinement of Alperin's weight conjecture is stated out definitely

Deep learning could be prone to learning shortcuts raised by dataset bias and result in inaccurate, unreliable, and unfair models, which impedes its adoption in real-world clinical applications. Despite its significance, there is a dearth of research in the medical image classification domain to address dataset bias. Furthermore, the bias labels are often agnostic, as identifying biases can be laborious and depend on post-hoc interpretation. This paper proposes learning Adaptive Agreement from a Biased Council (Ada-ABC), a debiasing framework that does not rely on explicit bias labels to tackle dataset bias in medical images. Ada-ABC develops a biased council consisting of multiple classifiers optimized with generalized cross entropy loss to learn the dataset bias. A debiasing model is then simultaneously trained under the guidance of the biased council. Specifically, the debiasing model is required to learn adaptive agreement with the biased council by agreeing on the correctly predicted samples and disagreeing on the wrongly predicted samples by the biased council. In this way, the debiasing model could learn the target attribute on the samples without spurious correlations while also avoiding ignoring the rich information in samples with spurious correlations. We theoretically demonstrated that the debiasing model could learn the target features when the biased model successfully captures dataset bias. Moreover, to our best knowledge, we constructed the first medical debiasing benchmark from four datasets containing seven different bias scenarios. Our extensive experiments practically showed that our proposed Ada-ABC outperformed competitive approaches, verifying its effectiveness in mitigating dataset bias for medical image classification. The codes and organized benchmark datasets will be made publicly available., Comment: 10 pages, 5 figures, 3 tables. Code and benchmark will be released via https://github.com/LLYXC/Ada-ABC/tree/main

The doped Hubbard model is one of the paradigmatic platforms to engineer exotic quantum many-body states, including charge-ordered states, strange metals and unconventional superconductors. While undoped and doped correlated phases have been experimentally realized in a variety twisted van der Waals materials, experiments in monolayer materials, and in particular 1T transition metal dichalcogenides, have solely reached the conventional insulating undoped regime. Correlated phases in monolayer two-dimensional materials have much higher associated energy scales than their twisted counterparts, making doped correlated monolayers an attractive platform for high temperature correlated quantum matter. Here, we demonstrate the realization of a doped Mott phase in a van der Waals dichalcogenide 1T-NbSe$_2$ monolayer. The system is electron doped due to electron transfer to a monolayer van der Waals substrate via proximity, leading to a correlated triangular lattice with both half-filled and fully-filled sites. We analyze the distribution of the half-filled and filled sites and show the arrangement is unlikely to be controlled by disorder alone, and we show that the presence of competing non-local many-body correlations would account for the charge correlations found experimentally. Our results establish 1T-NbSe$_2$ as a potential monolayer platform to explore correlated doped Mott physics in a frustrated lattice.

The half-orthant model is a partially oriented model of a random medium involving a parameter $p\in [0,1]$, for which there is a critical value $p_c(d)$ (depending on the dimension $d$) below which every point is reachable from the origin. We prove a limit theorem for the graph-distance (or "chemical distance") for this model when $p

Semantic segmentation techniques for extracting building footprints from high-resolution remote sensing images have been widely used in many fields such as urban planning. However, large-scale building extraction demands higher diversity in training samples. In this paper, we construct a Global Building Semantic Segmentation (GBSS) dataset (The dataset will be released), which comprises 116.9k pairs of samples (about 742k buildings) from six continents. There are significant variations of building samples in terms of size and style, so the dataset can be a more challenging benchmark for evaluating the generalization and robustness of building semantic segmentation models. We validated through quantitative and qualitative comparisons between different datasets, and further confirmed the potential application in the field of transfer learning by conducting experiments on subsets., Comment: 5 pages,6 figures