Search

Recently, researchers have proposed various deep learning methods to accurately detect infrared targets with the characteristics of indistinct shape and texture. Due to the limited variety of infrared datasets, training deep learning models with good generalization poses a challenge. To augment the infrared dataset, researchers employ data augmentation techniques, which often involve generating new images by combining images from different datasets. However, these methods are lacking in two respects. In terms of realism, the images generated by mixup-based methods lack realism and are difficult to effectively simulate complex real-world scenarios. In terms of diversity, compared with real-world scenes, borrowing knowledge from another dataset inherently has a limited diversity. Currently, the diffusion model stands out as an innovative generative approach. Large-scale trained diffusion models have a strong generative prior that enables real-world modeling of images to generate diverse and realistic images. In this paper, we propose Diff-Mosaic, a data augmentation method based on the diffusion model. This model effectively alleviates the challenge of diversity and realism of data augmentation methods via diffusion prior. Specifically, our method consists of two stages. Firstly, we introduce an enhancement network called Pixel-Prior, which generates highly coordinated and realistic Mosaic images by harmonizing pixels. In the second stage, we propose an image enhancement strategy named Diff-Prior. This strategy utilizes diffusion priors to model images in the real-world scene, further enhancing the diversity and realism of the images. Extensive experiments have demonstrated that our approach significantly improves the performance of the detection network. The code is available at https://github.com/YupeiLin2388/Diff-Mosaic

Large Code Generation Models (LCGMs) have garnered significant attention and achieved promising results across various programming tasks. However, concerns arise regarding performance when using non-English prompts, as these models are primarily trained on English-centric corpora, and most programming language tokens resemble English. Existing benchmarks often rely on English programming questions and limited manual unit test cases, inadequately assessing LCGM-generated code quality. This paper investigates code quality differences, specifically effectiveness and efficiency, when employing different natural languages as inputs, focusing on Chinese and English due to their prominent corpora and LCGM availability. Evaluating LCGM-generated code quality under bilingual inputs presents three challenges: (1) lack of high-quality bilingual programming question datasets, (2) insufficient unit test cases for comprehensive correctness verification, and (3) limited support for comparing generated code performance. To address these challenges, we curated a test suite of 52 bilingual programming questions and developed automated input generators for each. We enhanced correctness verification by sampling larger unit test cases and estimated code performance by profiling execution time relative to input size growth. Using this framework, we conducted an empirical study on six state-of-the-art LCGMs. The results revealed that LCGM-generated code exhibits varying bilingual correctness on an average of 10.5% of tasks, with 39.5% of correct code showing diverse bilingual performance differences. Our findings suggested LCGMs may not consistently generate high-quality code across different languages, providing insights for future research directions., Comment: 10 and a quarter pages, 6 figures

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

Graphene based nanomaterials have attracted significant attention for their potentials in biomedical and biotechnology applications in recent years, owing to the outstanding physical and chemical properties. However, the interaction mechanism and impact on biological activity of macro and micro biomolecules still require more concerns and further research in order to enhance their applicability in biosensors, etc. Herein, an integrated method has been developed to predict the protein bioactivity performance when interacting with nanomaterials for protein based biosensor. Molecular dynamics simulation and molecular docking technique were consolidated to investigate several nanomaterials C60 fullerene, single walled carbon nanotube, pristine graphene and graphene oxide, and their effect when interacting with protein. The adsorption behavior, secondary structure changes and protein bioactivity changes were simulated, and the results of protein activity simulation were verified in combination with atomic force spectrum, circular dichroism spectrum fluorescence and electrochemical experiments. The best quantification alignment between bioactivity obtained by simulation and experiment measurements was further explored. The two proteins, RNase A and Exonuclease III, were regarded as analysis model for the proof of concept, and the prediction accuracy of protein bioactivty could reach up to 0.98.

Emotion decoding plays an important role in affective human-computer interaction. However, previous studies ignored the dynamic real-world scenario, where human experience a blend of multiple emotions which are incrementally integrated into the model, leading to the multi-label class incremental learning (MLCIL) problem. Existing methods have difficulty in solving MLCIL issue due to notorious catastrophic forgetting caused by partial label problem and inadequate label semantics mining. In this paper, we propose an augmented emotional semantics learning framework for multi-label class incremental emotion decoding. Specifically, we design an augmented emotional relation graph module with label disambiguation to handle the past-missing partial label problem. Then, we leverage domain knowledge from affective dimension space to alleviate future-missing partial label problem by knowledge distillation. Besides, an emotional semantics learning module is constructed with a graph autoencoder to obtain emotion embeddings in order to guide the semantic-specific feature decoupling for better multi-label learning. Extensive experiments on three datasets show the superiority of our method for improving emotion decoding performance and mitigating forgetting on MLCIL problem.

Spatio-temporal compression of videos, utilizing networks such as Variational Autoencoders (VAE), plays a crucial role in OpenAI's SORA and numerous other video generative models. For instance, many LLM-like video models learn the distribution of discrete tokens derived from 3D VAEs within the VQVAE framework, while most diffusion-based video models capture the distribution of continuous latent extracted by 2D VAEs without quantization. The temporal compression is simply realized by uniform frame sampling which results in unsmooth motion between consecutive frames. Currently, there lacks of a commonly used continuous video (3D) VAE for latent diffusion-based video models in the research community. Moreover, since current diffusion-based approaches are often implemented using pre-trained text-to-image (T2I) models, directly training a video VAE without considering the compatibility with existing T2I models will result in a latent space gap between them, which will take huge computational resources for training to bridge the gap even with the T2I models as initialization. To address this issue, we propose a method for training a video VAE of latent video models, namely CV-VAE, whose latent space is compatible with that of a given image VAE, e.g., image VAE of Stable Diffusion (SD). The compatibility is achieved by the proposed novel latent space regularization, which involves formulating a regularization loss using the image VAE. Benefiting from the latent space compatibility, video models can be trained seamlessly from pre-trained T2I or video models in a truly spatio-temporally compressed latent space, rather than simply sampling video frames at equal intervals. With our CV-VAE, existing video models can generate four times more frames with minimal finetuning. Extensive experiments are conducted to demonstrate the effectiveness of the proposed video VAE., Comment: Project Page: https://ailab-cvc.github.io/cvvae/index.html

Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the training dynamics of DMs and observe an unanticipated phenomenon: during the training process, image fidelity initially improves, then unexpectedly deteriorates with the emergence of noisy patterns, only to recover later with severe overfitting. We term the stage with generated noisy patterns as corruption stage. To understand this corruption stage, we begin by theoretically modeling the one-shot fine-tuning scenario, and then extend this modeling to more general cases. Through this modeling, we identify the primary cause of this corruption stage: a narrowed learning distribution inherent in the nature of few-shot fine-tuning. To tackle this, we apply Bayesian Neural Networks (BNNs) on DMs with variational inference to implicitly broaden the learned distribution, and present that the learning target of the BNNs can be naturally regarded as an expectation of the diffusion loss and a further regularization with the pretrained DMs. This approach is highly compatible with current few-shot fine-tuning methods in DMs and does not introduce any extra inference costs. Experimental results demonstrate that our method significantly mitigates corruption, and improves the fidelity, quality and diversity of the generated images in both object-driven and subject-driven generation tasks., Comment: Preprint. Under review

We study locally finitary realizations of simple transitive module categories of infinite rank over the monoidal category $\mathscr{C}$ of finite dimensional modules for the complex Lie algebra $\mathfrak{sl}_2$. Combinatorics of such realizations is governed by six infinite Coxeter diagrams. We show that five of these are realizable in our setup, while one (type $B_\infty$) is not. We also describe the $\mathscr{C}$-module subcategories of $\mathfrak{sl}_2$-mod generated by simple modules as well as the $\mathscr{C}$-module categories coming from the natural action of $\mathscr{C}$ on the categories of finite dimensional modules over Lie subalgebras of $\mathfrak{sl}_2$.

Neural 3D representations such as Neural Radiance Fields (NeRF), excel at producing photo-realistic rendering results but lack the flexibility for manipulation and editing which is crucial for content creation. Previous works have attempted to address this issue by deforming a NeRF in canonical space or manipulating the radiance field based on an explicit mesh. However, manipulating NeRF is not highly controllable and requires a long training and inference time. With the emergence of 3D Gaussian Splatting (3DGS), extremely high-fidelity novel view synthesis can be achieved using an explicit point-based 3D representation with much faster training and rendering speed. However, there is still a lack of effective means to manipulate 3DGS freely while maintaining rendering quality. In this work, we aim to tackle the challenge of achieving manipulable photo-realistic rendering. We propose to utilize a triangular mesh to manipulate 3DGS directly with self-adaptation. This approach reduces the need to design various algorithms for different types of Gaussian manipulation. By utilizing a triangle shape-aware Gaussian binding and adapting method, we can achieve 3DGS manipulation and preserve high-fidelity rendering after manipulation. Our approach is capable of handling large deformations, local manipulations, and soft body simulations while keeping high-quality rendering. Furthermore, we demonstrate that our method is also effective with inaccurate meshes extracted from 3DGS. Experiments conducted demonstrate the effectiveness of our method and its superiority over baseline approaches., Comment: Project page here: https://gaoxiangjun.github.io/mani_gs/

Drawing inspiration from the hierarchical processing of the human auditory system, which transforms sound from low-level acoustic features to high-level semantic understanding, we introduce a novel coarse-to-fine audio reconstruction method. Leveraging non-invasive functional Magnetic Resonance Imaging (fMRI) data, our approach mimics the inverse pathway of auditory processing. Initially, we utilize CLAP to decode fMRI data coarsely into a low-dimensional semantic space, followed by a fine-grained decoding into the high-dimensional AudioMAE latent space guided by semantic features. These fine-grained neural features serve as conditions for audio reconstruction through a Latent Diffusion Model (LDM). Validation on three public fMRI datasets-Brain2Sound, Brain2Music, and Brain2Speech-underscores the superiority of our coarse-to-fine decoding method over stand-alone fine-grained approaches, showcasing state-of-the-art performance in metrics like FD, FAD, and KL. Moreover, by employing semantic prompts during decoding, we enhance the quality of reconstructed audio when semantic features are suboptimal. The demonstrated versatility of our model across diverse stimuli highlights its potential as a universal brain-to-audio framework. This research contributes to the comprehension of the human auditory system, pushing boundaries in neural decoding and audio reconstruction methodologies.

Artificial intelligence is revolutionizing architecture through text-to-image synthesis, converting textual descriptions into detailed visual representations. We explore AI-assisted floor plan design, focusing on technical background, practical methods, and future directions. Using tools like, Stable Diffusion, AI leverages models such as Generative Adversarial Networks and Variational Autoencoders to generate complex and functional floorplans designs. We evaluates these AI models' effectiveness in generating residential floor plans from text prompts. Through experiments with reference images, text prompts, and sketches, we assess the strengths and limitations of current text-to-image technology in architectural visualization. Architects can use these AI tools to streamline design processes, create multiple design options, and enhance creativity and collaboration. We highlight AI's potential to drive smarter, more efficient floorplan design, contributing to ongoing discussions on AI integration in the design profession and its future impact., Comment: 13 pages, 7 figures

With the emergence of Gaussian Splats, recent efforts have focused on large-scale scene geometric reconstruction. However, most of these efforts either concentrate on memory reduction or spatial space division, neglecting information in the semantic space. In this paper, we propose a novel method, named SA-GS, for fine-grained 3D geometry reconstruction using semantic-aware 3D Gaussian Splats. Specifically, we leverage prior information stored in large vision models such as SAM and DINO to generate semantic masks. We then introduce a geometric complexity measurement function to serve as soft regularization, guiding the shape of each Gaussian Splat within specific semantic areas. Additionally, we present a method that estimates the expected number of Gaussian Splats in different semantic areas, effectively providing a lower bound for Gaussian Splats in these areas. Subsequently, we extract the point cloud using a novel probability density-based extraction method, transforming Gaussian Splats into a point cloud crucial for downstream tasks. Our method also offers the potential for detailed semantic inquiries while maintaining high image-based reconstruction results. We provide extensive experiments on publicly available large-scale scene reconstruction datasets with highly accurate point clouds as ground truth and our novel dataset. Our results demonstrate the superiority of our method over current state-of-the-art Gaussian Splats reconstruction methods by a significant margin in terms of geometric-based measurement metrics. Code and additional results will soon be available on our project page., Comment: Might need more comparison, will be add later

In the field of medical image compression, Implicit Neural Representation (INR) networks have shown remarkable versatility due to their flexible compression ratios, yet they are constrained by a one-to-one fitting approach that results in lengthy encoding times. Our novel method, ``\textbf{UniCompress}'', innovatively extends the compression capabilities of INR by being the first to compress multiple medical data blocks using a single INR network. By employing wavelet transforms and quantization, we introduce a codebook containing frequency domain information as a prior input to the INR network. This enhances the representational power of INR and provides distinctive conditioning for different image blocks. Furthermore, our research introduces a new technique for the knowledge distillation of implicit representations, simplifying complex model knowledge into more manageable formats to improve compression ratios. Extensive testing on CT and electron microscopy (EM) datasets has demonstrated that UniCompress outperforms traditional INR methods and commercial compression solutions like HEVC, especially in complex and high compression scenarios. Notably, compared to existing INR techniques, UniCompress achieves a 4$\sim$5 times increase in compression speed, marking a significant advancement in the field of medical image compression. Codes will be publicly available.

Autoregressive next-token prediction is a standard pretraining method for large-scale language models, but its application to vision tasks is hindered by the non-sequential nature of image data, leading to cumulative errors. Most vision models employ masked autoencoder (MAE) based pretraining, which faces scalability issues. To address these challenges, we introduce \textbf{TokenUnify}, a novel pretraining method that integrates random token prediction, next-token prediction, and next-all token prediction. We provide theoretical evidence demonstrating that TokenUnify mitigates cumulative errors in visual autoregression. Cooperated with TokenUnify, we have assembled a large-scale electron microscopy (EM) image dataset with ultra-high resolution, ideal for creating spatially correlated long sequences. This dataset includes over 120 million annotated voxels, making it the largest neuron segmentation dataset to date and providing a unified benchmark for experimental validation. Leveraging the Mamba network inherently suited for long-sequence modeling on this dataset, TokenUnify not only reduces the computational complexity but also leads to a significant 45\% improvement in segmentation performance on downstream EM neuron segmentation tasks compared to existing methods. Furthermore, TokenUnify demonstrates superior scalability over MAE and traditional autoregressive methods, effectively bridging the gap between pretraining strategies for language and vision models. Code is available at \url{https://github.com/ydchen0806/TokenUnify}.

Dataset condensation can be used to reduce the computational cost of training multiple models on a large dataset by condensing the training dataset into a small synthetic set. State-of-the-art approaches rely on matching the model gradients between the real and synthetic data. However, there is no theoretical guarantee of the generalizability of the condensed data: data condensation often generalizes poorly across hyperparameters/architectures in practice. This paper considers a different condensation objective specifically geared toward hyperparameter search. We aim to generate a synthetic validation dataset so that the validation-performance rankings of the models, with different hyperparameters, on the condensed and original datasets are comparable. We propose a novel hyperparameter-calibrated dataset condensation (HCDC) algorithm, which obtains the synthetic validation dataset by matching the hyperparameter gradients computed via implicit differentiation and efficient inverse Hessian approximation. Experiments demonstrate that the proposed framework effectively maintains the validation-performance rankings of models and speeds up hyperparameter/architecture search for tasks on both images and graphs.

Linear conjugacy offers a new perspective to broaden the scope of stable biochemical reaction networks to the systems linearly conjugated to the well-established complex balanced mass action systems ($\ell$cCBMASs). This paper addresses the challenge posed by time delay, which can disrupt the linear conjugacy relationship and complicate stability analysis for delayed versions of $\ell$cCBMASs (D$\ell$cCBMAS). Firstly, we develop Lyapunov functionals tailored to some D$\ell$cCBMASs by using the persisted parameter relationships under time delays. Subsequently, we redivide the phase space as several invariant sets of trajectories and further investigate the existence and uniqueness of equilibriums in each newly defined invariant set. This enables us to determine the local asymptotic stability of some D$\ell$cCBMASs within an updated framework. Furthermore, illustrative examples are provided to demonstrate the practical implications of our approach.

We study electron-electron interaction induced states of twisted bilayer MoTe$_2$ in an out-of-plane magnetic field $B\hat{\bf z}$ near one hole per moir\'e unit cell filling. The 3D phase diagram showing the evolution of competing phases with $B$, interaction strength and an out-of-plane electric field is presented at electron fillings that follow the Diophantine equation along Chern number $-\text{sign}\left(B\right)$ line, that is pointing away from the charge neutral filling, where we find prominent Chern insulators consistent with the experiments. We also explain the experimental absence of prominent Chern insulators along the Chern number $+\text{sign}\left(B\right)$ line., Comment: 6+9 pages, 4+7 figures typo in Fig 2g corrected, a reference added, minor edits

In this work, we address the issue of quality of experience (QoE) in unmanned aerial vehicle (UAV) aided multiuser rate-splitting multiple access (RSMA) networks under secrecy constraints. The problem is formulated as maximization of sum mean opinion scores (MOSs) of the users. The problem is decomposed into two subproblems, beamforming and rate allocation and UAV trajectory subproblem. For, beamforming and rate allocation subproblem, we use the epigraph method, property of polynomials, and the norm-bounded error of channels, we linearize the objective function. Then, applying second-order conic (SOC) and first Taylor expansion, we convexify the remaining nonconvex constraints. For the highly nonconvex UAV trajectory, we unroll the constraints and we apply first Taylor expansion on the unrolled constraints. The simulation results demonstrate the efficiency of the proposed framework., Comment: 6 pages, 4 figures

Class-imbalanced node classification tasks are prevalent in real-world scenarios. Due to the uneven distribution of nodes across different classes, learning high-quality node representations remains a challenging endeavor. The engineering of loss functions has shown promising potential in addressing this issue. It involves the meticulous design of loss functions, utilizing information about the quantities of nodes in different categories and the network's topology to learn unbiased node representations. However, the design of these loss functions heavily relies on human expert knowledge and exhibits limited adaptability to specific target tasks. In this paper, we introduce a high-performance, flexible, and generalizable automated loss function search framework to tackle this challenge. Across 15 combinations of graph neural networks and datasets, our framework achieves a significant improvement in performance compared to state-of-the-art methods. Additionally, we observe that homophily in graph-structured data significantly contributes to the transferability of the proposed framework., Comment: ICML 2024

Real-world data often exhibit extreme imbalances and out-of-distribution (OOD) instances, which significantly biases the model training. While it has been extensively studied in vision and language domains separately, the impact of long-tailed open worlds on multi-modal large language models (MLLMs) has been largely overlooked. In this paper, we first demonstrate the susceptibility and vulnerability of vision-language models to significant biases caused by tail drift and out-of-distribution (OOD) drift during both the pre-training and fine-tuning stages. To eliminate the bias from different sources, we integrate the tailed drift adaptation and OOD drift detection into a unified framework by extending the concept drift theory to multi-modal. Specifically, a T-distribution-based drift adapter is proposed to effectively mitigate the bias induced by the long-tailed problem, which also facilitates the model in distinguishing OOD data through explicit distribution modelling. Extensive experiments show significant improvements in our model's ability to adapt to tailed drift and OOD drift. Moreover, it enhances the efficiency and accuracy of image-text alignment in vision language model pre-training, particularly in the long-tail open world scenario. Furthermore, we create a set of multi-modal datasets called OpenMMlo, specifically tailored for the long-tailed open world scenario, to validate our findings. To foster the development of the multi-modal community, we have made both OpenMMlo datasets and our code publicly available at: https://github.com/Anonymous0Knight/ConceptDriftMLLMs., Comment: 26 pages

Using a sample of $448.1 \times 10^6$ $\psi(2S)$ events collected with the BESIII detector, we perform a study of the decay $J/\psi\rightarrow K^+K^-$ via $\psi(2S)\rightarrow \pi^+\pi^-J/\psi$. The branching fraction of $J/\psi\rightarrow K^+K^-$ is determined to be $\mathcal{B}_{K^+K^-}=(3.072\pm 0.023({\rm stat.})\pm 0.050({\rm syst.}))\times 10^{-4}$, which is consistent with previous measurements but with significantly improved precision., Comment: to be submitted to PRD

Based on the newly acquired dense gas observations from the JCMT MALATANG survey and X-ray data from Chandra, we explore the correlation between hot gas and HCN $J=4 \rightarrow 3$, HCO$^+\ J=4 \rightarrow 3$ emission for the first time at sub-kiloparsec scale of five nearby star-forming galaxies, namely M82, M83, IC 342, NGC 253, and NGC 6946. We find that both HCN $J=4 \rightarrow 3$ and HCO$^+\ J=4 \rightarrow 3$ line luminosity show a statistically significant correlation with the 0.5${-}$2 keV X-ray emission of the diffuse hot gas ($L_{\rm 0.5 - 2\,keV}^{\rm gas}$). The Bayesian regression analysis gives the best fit of ${\rm log}(L_{\rm 0.5-2\,keV}^{\rm gas} /{\rm erg\,s^{-1}})=2.39\,{\rm log}(L'_{\rm HCN(4-3)} /{\rm K\,km\,s^{-1}\,pc^{2}})+24.83$ and ${\rm log}(L_{\rm 0.5-2\,keV}^{\rm gas} /{\rm erg\,s^{-1}})=2.48\,{\rm log}(L'_{\rm HCO^{+}(4-3)} /{\rm K\,km\,s^{-1}\,pc^{2}})+23.84$, with dispersion of $\thicksim$0.69 dex and 0.54 dex, respectively. At the sub-kiloparsec scale, we find that the power-law index of the $L_{\rm 0.5 - 2\,keV}^{\rm gas}$ ${-}$ star formation rate (SFR) relation is ${\rm log}(L_{\rm 0.5-2\,keV}^{\rm gas} /{\rm erg\,s^{-1}})=1.80\,{\rm log} ({\rm SFR} /M_\odot\,{\rm yr}^{-1})+39.16$, deviated from previous linear relations at global scale. This implies that the global property of hot gas significantly differs from individual resolved regions, which is influenced by the local physical conditions close to the sites of star formation., Comment: 10 pages, 3figures, accepted for publication in the ApJ Letters. Dedicated to Prof. Yu Gao, who initiated this work

Regression analysis with probability measures as input predictors and output response has recently drawn great attention. However, it is challenging to handle multiple input probability measures due to the non-flat Riemannian geometry of the Wasserstein space, hindering the definition of arithmetic operations, hence additive linear structure is not well-defined. In this work, a distribution-in-distribution-out regression model is proposed by introducing parallel transport to achieve provable commutativity and additivity of newly defined arithmetic operations in Wasserstein space. The appealing properties of the DIDO regression model can serve a foundation for model estimation, prediction, and inference. Specifically, the Fr\'echet least squares estimator is employed to obtain the best linear unbiased estimate, supported by the newly established Fr\'echet Gauss-Markov Theorem. Furthermore, we investigate a special case when predictors and response are all univariate Gaussian measures, leading to a simple close-form solution of linear model coefficients and $R^2$ metric. A simulation study and real case study in intraoperative cardiac output prediction are performed to evaluate the performance of the proposed method.

In the rapidly evolving automotive industry, Systems-on-Chips (SoCs) are playing an increasingly crucial role in enhancing vehicle intelligence, connectivity, and safety features. For enterprises whose business encompasses automotive SoCs, the sustained and stable provision and receipt of SoC relevant goods or services are essential. Considering the imperative for a resilient and adaptable supply network, enterprises are concentrating their efforts on formulating strategies to address risks stemming from supply chain disruptions caused by technological obsolescence, natural disasters, and geopolitical tensions. This study presents an open supply knowledge extraction and complement approach and build a supply chain network of automotive SoC enterprises in China, which incorporates cross-domain named entity recognition under limited information, fuzzy matching of firm entities, and supply relation inferring based on knowledge graph. Subsequently, we exhibit the degree and registered capital distribution across firms, and analyze the correlations between centrality metrics in the supply chain network. Finally, based on recovery capacity and risk transfer, two interaction disruption models (IDMs) are developed to elucidate the adaptive behaviors and effect of network disruptions under various business and attack strategies. This research not only aids in exploring the complexities of Chinese automotive SoC supply chain but also enriches our understanding of the dynamics of firm behavior in this crucial industry sector., Comment: arXiv admin note: text overlap with arXiv:2304.10428 by other authors

Real-time Bidding (RTB) advertisers wish to \textit{know in advance} the expected cost and yield of ad campaigns to avoid trial-and-error expenses. However, Campaign Performance Forecasting (CPF), a sequence modeling task involving tens of thousands of ad auctions, poses challenges of evolving user interest, auction representation, and long context, making coarse-grained and static-modeling methods sub-optimal. We propose \textit{AdVance}, a time-aware framework that integrates local auction-level and global campaign-level modeling. User preference and fatigue are disentangled using a time-positioned sequence of clicked items and a concise vector of all displayed items. Cross-attention, conditioned on the fatigue vector, captures the dynamics of user interest toward each candidate ad. Bidders compete with each other, presenting a complete graph similar to the self-attention mechanism. Hence, we employ a Transformer Encoder to compress each auction into embedding by solving auxiliary tasks. These sequential embeddings are then summarized by a conditional state space model (SSM) to comprehend long-range dependencies while maintaining global linear complexity. Considering the irregular time intervals between auctions, we make SSM's parameters dependent on the current auction embedding and the time interval. We further condition SSM's global predictions on the accumulation of local results. Extensive evaluations and ablation studies demonstrate its superiority over state-of-the-art methods. AdVance has been deployed on the Tencent Advertising platform, and A/B tests show a remarkable 4.5\% uplift in Average Revenue per User (ARPU)., Comment: 12 pages, 4 figures, accepted at ACM SIGKDD 2024

We present the first search for the leptonic decays $D^{*+}\to e^+\nu_e$ and $D^{*+}\to \mu^+\nu_\mu$ by analyzing a data sample of electron-positron collisions recorded with the BESIII detector at center-of-mass energies between 4.178 and 4.226 GeV, corresponding to an integrated luminosity of 6.32~fb$^{-1}$. No significant signal is observed. The upper limits on the branching fractions for $D^{*+}\to e^+\nu_e$ and $D^{*+}\to \mu^+\nu_\mu$ are set to be $1.1 \times 10^{-5}$ and $4.3 \times 10^{-6}$ at 90\% confidence level, respectively., Comment: 14 pages, 7 figures

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods utilize mundane point cloud representations as input and deep learning-based LiDAR-based Place Recognition (LPR) approaches employing different point cloud image inputs with convolutional neural networks (CNNs) or transformer architectures. However, the recently proposed Mamba deep learning model, combined with state space models (SSMs), holds great potential for long sequence modeling. Therefore, we developed OverlapMamba, a novel network for place recognition, which represents input range views (RVs) as sequences. In a novel way, we employ a stochastic reconstruction approach to build shift state space models, compressing the visual representation. Evaluated on three different public datasets, our method effectively detects loop closures, showing robustness even when traversing previously visited locations from different directions. Relying on raw range view inputs, it outperforms typical LiDAR and multi-view combination methods in time complexity and speed, indicating strong place recognition capabilities and real-time efficiency.

Decoding language information from brain signals represents a vital research area within brain-computer interfaces, particularly in the context of deciphering the semantic information from the fMRI signal. However, many existing efforts concentrate on decoding small vocabulary sets, leaving space for the exploration of open vocabulary continuous text decoding. In this paper, we introduce a novel method, the \textbf{Brain Prompt GPT (BP-GPT)}. By using the brain representation that is extracted from the fMRI as a prompt, our method can utilize GPT-2 to decode fMRI signals into stimulus text. Further, we introduce a text-to-text baseline and align the fMRI prompt to the text prompt. By introducing the text-to-text baseline, our BP-GPT can extract a more robust brain prompt and promote the decoding of pre-trained LLM. We evaluate our BP-GPT on the open-source auditory semantic decoding dataset and achieve a significant improvement up to $4.61\%$ on METEOR and $2.43\%$ on BERTScore across all the subjects compared to the state-of-the-art method. The experimental results demonstrate that using brain representation as a prompt to further drive LLM for auditory neural decoding is feasible and effective.

Using 9.0 $\rm fb^{-1}$ of $e^+e^-$ collision data collected at center-of-mass energies from 4.178 to 4.278 GeV with the BESIII detector at the BEPCII collider, we perform the first search for the radiative transition $\chi_{c1}(3872)\to\gamma \psi_2(3823)$. No $\chi_{c1}(3872)\to\gamma \psi_2(3823)$ signal is observed. The upper limit on the ratio of branching fractions $\mathcal{B}(\chi_{c1}(3872)\to\gamma \psi_2(3823), \psi_2(3823)\to\gamma\chi_{c1})/\mathcal{B}(\chi_{c1}(3872)\to\pi^+\pi^- J/\psi)$ is set as 0.075 at the 90\% confidence level. Our result contradicts theoretical predictions under the assumption that the $\chi_{c1}(3872)$ is the pure charmonium state $\chi_{c1}(2P)$., Comment: 8 pages, 2 figures

Point cloud registration is a fundamental task for estimating rigid transformations between point clouds. Previous studies have used geometric information for extracting features, matching and estimating transformation. Recently, owing to the advancement of RGB-D sensors, researchers have attempted to combine visual and geometric information to improve registration performance. However, these studies focused on extracting distinctive features by deep feature fusion, which cannot effectively solve the negative effects of each feature's weakness, and cannot sufficiently leverage the valid information. In this paper, we propose a new feature combination framework, which applies a looser but more effective combination. An explicit filter based on transformation consistency is designed for the combination framework, which can overcome each feature's weakness. And an adaptive threshold determined by the error distribution is proposed to extract more valid information from the two types of features. Owing to the distinctive design, our proposed framework can estimate more accurate correspondences and is applicable to both hand-crafted and learning-based feature descriptors. Experiments on ScanNet and 3DMatch show that our method achieves a state-of-the-art performance.

Elastic contact in hydrodynamic environments is a complex multiphysics phenomenon and can be found in applications ranging from engineering to biological systems. Understanding the intricacies of this problem requires the development of a generalized framework capable of handling topological changes and transitioning implicitly from fluid-structure interaction (FSI) conditions to solid-solid contact conditions. We propose a mono-field interface advancing method for handling multibody contact simulations in a submerged environment. Given the physical demands of the problem, we adopt a phase-field based fully Eulerian approach to resolve the multiphase and multibody interactions in the system. We employ a stabilized finite element formulation and a partitioned iterative procedure to solve the unified momentum equation comprising solid and fluid dynamics coupled with the Allen-Cahn phase-field equation. We introduce a contact force approach to handle smooth elastic-elastic and elastic-rigid contact based on the overlap of the diffused interfaces of two colliding bodies. The diffuse interface representation ameliorates the issue of discontinuous contact forces generally found in conventional approaches. The implemented model is verified for smooth dry contact and FSI contact scenarios. We obtain a spatial convergence rate of around $1.8$ for the Hertzian contact case involving a deformable cylinder on an elastic plane. Relative volume error is found to be within $5\%$ for the FSI contact case. The developed approach eliminates the need for solving multiple phase-field equations or reconstructing the solid boundaries at every time step. This reduces the overall computational time by nearly $10\%$ compared to an explicit interface extraction method. Using the proposed framework, we demonstrate the collision dynamics between multiple bodies submerged in an open tank., Comment: 32 pages

Coherent elastic neutrino-nucleus scattering (CEvNS) provides a unique probe for neutrino properties Beyond the Standard Model (BSM) physics. REactor neutrino LIquid xenon Coherent Scattering experiment (RELICS), a proposed reactor neutrino program using liquid xenon time projection chamber (LXeTPC) technology, aims to investigate the CEvNS process of antineutrinos off xenon atomic nuclei. In this work, the design of the experiment is studied and optimized based on Monte Carlo (MC) simulations. To achieve a sufficiently low energy threshold for CEvNS detection, an ionization-only analysis channel is adopted for RELICS. A high emission rate of delayed electrons after a big ionization signal is the major background, leading to an analysis threshold of 120 photo-electrons in the CEvNS search. The second largest background, nuclear recoils induced by cosmic-ray neutrons, is suppressed via a passive water shield. The physics potential of RELICS is explored with a 32 kg-yr exposure at a baseline of 25 m from a reactor core with a 3 GW thermal power. In an energy range of 120 to 240 PE, we expect 4902.4 CEvNS and 1318.4 background events. The sensitivity of RELICS to the weak mixing angle is investigated at a low momentum transfer. Our study shows that RELICS can further improve the constraints on the non-standard neutrino interaction (NSI) compared to the current best results.

Cross-domain offline reinforcement learning leverages source domain data with diverse transition dynamics to alleviate the data requirement for the target domain. However, simply merging the data of two domains leads to performance degradation due to the dynamics mismatch. Existing methods address this problem by measuring the dynamics gap via domain classifiers while relying on the assumptions of the transferability of paired domains. In this paper, we propose a novel representation-based approach to measure the domain gap, where the representation is learned through a contrastive objective by sampling transitions from different domains. We show that such an objective recovers the mutual-information gap of transition functions in two domains without suffering from the unbounded issue of the dynamics gap in handling significantly different domains. Based on the representations, we introduce a data filtering algorithm that selectively shares transitions from the source domain according to the contrastive score functions. Empirical results on various tasks demonstrate that our method achieves superior performance, using only 10% of the target data to achieve 89.2% of the performance on 100% target dataset with state-of-the-art methods., Comment: This paper has been accepted by ICML2024

This paper is devoted to the study of Mean-field Games (MFG) systems in the mass critical exponent case. We firstly establish the optimal Gagliardo-Nirenberg type inequality associated with the potential-free MFG system. Then, under some mild assumptions on the potential function, we show that there exists a critical mass $M^*$ such that the MFG system admits a least energy solution if and only if the total mass of population density $M$ satisfies $M

Quantum computing holds the potential to revolutionize various fields by efficiently tackling complex problems. At its core are quantum circuits, sequences of quantum gates manipulating quantum states. The selection of the right quantum circuit ansatz, which defines initial circuit structures and serves as the basis for optimization techniques, is crucial in quantum algorithm design.This paper presents a categorized catalog of quantum circuit ansatzes aimed at supporting quantum algorithm design and implementation. Each ansatz is described with details such as intent, motivation, applicability, circuit diagram, implementation, example, and see also. Practical examples are provided to illustrate their application in quantum algorithm design.The catalog aims to assist quantum algorithm designers by offering insights into the strengths and limitations of different ansatzes, thereby facilitating decision-making for specific tasks., Comment: Accepted as full paper in the Research Papers track of QSW 2024

This paper presents the first concolic testing framework specifically designed for quantum programs. The framework defines quantum conditional statements that quantify quantum states and presents a symbolization method for quantum variables. Utilizing this framework, we generate path constraints for each concrete execution path of a quantum program. These constraints guide the exploration of new paths, with a quantum constraint solver determining the outcomes to generate novel input samples and enhance branch coverage. We implemented this framework in Python and integrated it with Qiskit for practical evaluation. Experimental results demonstrate that our concolic testing framework significantly improves branch coverage and the quality of quantum input samples, demonstrating its effectiveness and efficiency in quantum software testing.

This paper describes a new research paradigm for studying human-AI collaboration, named "human-AI mutual learning", defined as the process where humans and AI agents preserve, exchange, and improve knowledge during human-AI collaboration. We describe relevant methodologies, motivations, domain examples, benefits, challenges, and future research agenda under this paradigm.

Pretrained Optimization Models (POMs) leverage knowledge gained from optimizing various tasks, providing efficient solutions for new optimization challenges through direct usage or fine-tuning. Despite the inefficiencies and limited generalization abilities observed in current POMs, our proposed model, the general pre-trained optimization model (GPOM), addresses these shortcomings. GPOM constructs a population-based pretrained Black-Box Optimization (BBO) model tailored for continuous optimization. Evaluation on the BBOB benchmark and two robot control tasks demonstrates that GPOM outperforms other pretrained BBO models significantly, especially for high-dimensional tasks. Its direct optimization performance exceeds that of state-of-the-art evolutionary algorithms and POMs. Furthermore, GPOM exhibits robust generalization capabilities across diverse task distributions, dimensions, population sizes, and optimization horizons.

Let $ES_{\ell}(n)$ be the minimum $N$ such that every $N$-element point set in the plane contains either $\ell$ collinear members or $n$ points in convex position. We prove that there is a constant $C>0$ such that, for each $\ell, n \ge 3$, $$ (3\ell - 1) \cdot 2^{n-5} < ES_{\ell}(n) < \ell^2 \cdot 2^{n+ C\sqrt{n\log n}}.$$ A similar extension of the well-known Erd\H os--Szekeres cups-caps theorem is also proved.

To defend against conflict-based cache side-channel attacks, cache partitioning or remapping techniques were proposed to prevent set conflicts between different security domains or obfuscate the locations of such conflicts. But such techniques complicate cache design and may result in significant performance penalties. Therefore, there have been lightweight prefetching-based schemes proposed to introduce noise to confuse attackers' observation. However, we have validated experimentally that relying on prefetching to only introduce noise is insufficient, as attackers can still reliably distinguish the victim's cache accesses. This paper proposes a novel prefetching-based scheme, called PCG. It combines adding victim-irrelevant cache occupancy changes and reducing victim-relevant cache occupancy changes to disrupt attackers by generating noisy and indistinguishable cache access patterns. Additionally, PCG can either work independently or seamlessly be integrated with most of the commonly used prefetchers. We have implemented and evaluated PCG in both gem5 and the open-source RISC-V core BOOMv3. The evaluation results show the PCG's robust security superior to the existing solutions, while without resulting in significant performance degradation. According to the evaluation based on the SPEC CPU 2017 benchmark suite, PCG even shows an average performance improvement of about 1.64%. Moreover, it incurs only 1.26% overhead on hardware resource consumption., Comment: 12 pages, 9 figures, submitting to a journal

One-shot segmentation of brain tissue requires training registration-segmentation (reg-seg) dual-model iteratively, where reg-model aims to provide pseudo masks of unlabeled images for seg-model by warping a carefully-labeled atlas. However, the imperfect reg-model induces image-mask misalignment, poisoning the seg-model subsequently. Recent StyleSeg bypasses this bottleneck by replacing the unlabeled images with their warped copies of atlas, but needs to borrow the diverse image patterns via style transformation. Here, we present StyleSeg V2, inherited from StyleSeg but granted the ability of perceiving the registration errors. The motivation is that good registration behaves in a mirrored fashion for mirrored images. Therefore, almost at no cost, StyleSeg V2 can have reg-model itself "speak out" incorrectly-aligned regions by simply mirroring (symmetrically flipping the brain) its input, and the registration errors are symmetric inconsistencies between the outputs of original and mirrored inputs. Consequently, StyleSeg V2 allows the seg-model to make use of correctly-aligned regions of unlabeled images and also enhances the fidelity of style-transformed warped atlas image by weighting the local transformation strength according to registration errors. The experimental results on three public datasets demonstrate that our proposed StyleSeg V2 outperforms other state-of-the-arts by considerable margins, and exceeds StyleSeg by increasing the average Dice by at least 2.4%., Comment: 10 pages, 11 figures, 2 tables

Whole-arm tactile feedback is crucial for robots to ensure safe physical interaction with their surroundings. This paper introduces CushSense, a fabric-based soft and stretchable tactile-sensing skin designed for physical human-robot interaction (pHRI) tasks such as robotic caregiving. Using stretchable fabric and hyper-elastic polymer, CushSense identifies contacts by monitoring capacitive changes due to skin deformation. CushSense is cost-effective ($\sim$US\$7 per taxel) and easy to fabricate. We detail the sensor design and fabrication process and perform characterization, highlighting its high sensing accuracy (relative error of 0.58%) and durability (0.054% accuracy drop after 1000 interactions). We also present a user study underscoring its perceived safety and comfort for the assistive task of limb manipulation. We open source all sensor-related resources on https://emprise.cs.cornell.edu/cushsense., Comment: 8 pages, 8 figures, ICRA2024

Vector quantization, renowned for its unparalleled feature compression capabilities, has been a prominent topic in signal processing and machine learning research for several decades and remains widely utilized today. With the emergence of large models and generative AI, vector quantization has gained popularity in recommender systems, establishing itself as a preferred solution. This paper starts with a comprehensive review of vector quantization techniques. It then explores systematic taxonomies of vector quantization methods for recommender systems (VQ4Rec), examining their applications from multiple perspectives. Further, it provides a thorough introduction to research efforts in diverse recommendation scenarios, including efficiency-oriented approaches and quality-oriented approaches. Finally, the survey analyzes the remaining challenges and anticipates future trends in VQ4Rec, including the challenges associated with the training of vector quantization, the opportunities presented by large language models, and emerging trends in multimodal recommender systems. We hope this survey can pave the way for future researchers in the recommendation community and accelerate their exploration in this promising field.

Score matching with Langevin dynamics (SMLD) method has been successfully applied to accelerated MRI. However, the hyperparameters in the sampling process require subtle tuning, otherwise the results can be severely corrupted by hallucination artifacts, especially with out-of-distribution test data. To address the limitations, we proposed a novel workflow where naive SMLD samples serve as additional priors to guide model-driven network training. First, we adopted a pretrained score network to generate samples as preliminary guidance images (PGI), obviating the need for network retraining, parameter tuning and in-distribution test data. Although PGIs are corrupted by hallucination artifacts, we believe they can provide extra information through effective denoising steps to facilitate reconstruction. Therefore, we designed a denoising module (DM) in the second step to coarsely eliminate artifacts and noises from PGIs. The features are extracted from a score-based information extractor (SIE) and a cross-domain information extractor (CIE), which directly map to the noise patterns. Third, we designed a model-driven network guided by denoised PGIs (DGIs) to further recover fine details. DGIs are densely connected with intermediate reconstructions in each cascade to enrich the information and are periodically updated to provide more accurate guidance. Our experiments on different datasets reveal that despite the low average quality of PGIs, the proposed workflow can effectively extract valuable information to guide the network training, even with severely reduced training data and sampling steps. Our method outperforms other cutting-edge techniques by effectively mitigating hallucination artifacts, yielding robust and high-quality reconstruction results.

Due to the limited model capacity, leveraging distributed Neural Radiance Fields (NeRFs) for modeling extensive urban environments has become a necessity. However, current distributed NeRF registration approaches encounter aliasing artifacts, arising from discrepancies in rendering resolutions and suboptimal pose precision. These factors collectively deteriorate the fidelity of pose estimation within NeRF frameworks, resulting in occlusion artifacts during the NeRF blending stage. In this paper, we present a distributed NeRF system with tri-stage pose optimization. In the first stage, precise poses of images are achieved by bundle adjusting Mip-NeRF 360 with a coarse-to-fine strategy. In the second stage, we incorporate the inverting Mip-NeRF 360, coupled with the truncated dynamic low-pass filter, to enable the achievement of robust and precise poses, termed Frame2Model optimization. On top of this, we obtain a coarse transformation between NeRFs in different coordinate systems. In the third stage, we fine-tune the transformation between NeRFs by Model2Model pose optimization. After obtaining precise transformation parameters, we proceed to implement NeRF blending, showcasing superior performance metrics in both real-world and simulation scenarios. Codes and data will be publicly available at https://github.com/boilcy/Distributed-NeRF.