Search

Vision-centric autonomous driving has demonstrated excellent performance with economical sensors. As the fundamental step, 3D perception aims to infer 3D information from 2D images based on 3D-2D projection. This makes driving perception models susceptible to sensor configuration (e.g., camera intrinsics and extrinsics) variations. However, generalizing across camera configurations is important for deploying autonomous driving models on different car models. In this paper, we present UniDrive, a novel framework for vision-centric autonomous driving to achieve universal perception across camera configurations. We deploy a set of unified virtual cameras and propose a ground-aware projection method to effectively transform the original images into these unified virtual views. We further propose a virtual configuration optimization method by minimizing the expected projection error between original cameras and virtual cameras. The proposed virtual camera projection can be applied to existing 3D perception methods as a plug-and-play module to mitigate the challenges posed by camera parameter variability, resulting in more adaptable and reliable driving perception models. To evaluate the effectiveness of our framework, we collect a dataset on Carla by driving the same routes while only modifying the camera configurations. Experimental results demonstrate that our method trained on one specific camera configuration can generalize to varying configurations with minor performance degradation., Comment: Preprint; 14 pages, 5 figures, 2 tables; Code at https://github.com/ywyeli/UniDrive

The performance of radiofrequency (RF) coils has a significant impact on the quality and speed of magnetic resonance imaging (MRI). Consequently, rigid coils with attached cables are commonly employed to achieve optimal SNR performance and parallel imaging capability. However, since the adoption of MRI in clinical imaging, both patients and doctors have long suffered from the poor examination experience and physical strain caused by the bulky housings and cumbersome cables of traditional coils. This paper presents a new architectural concept, the Near-Field Coupling (NFC) coil system, which integrates a pickup coil array within the magnet with an NFC coil worn by the patient. In contrast to conventional coils, the NFC coil system obviates the necessity for bed-mounted connectors. It provides a lightweight, cost-effective solution that enhances patient comfort and supports disposable, custom designs for the NFC coils. The paper also derives the SNR expression for the NFC coil system, proposes two key design principles, and demonstrates the system's potential in SNR and parallel imaging through an implementation case.

Federated Learning (FL) has been demonstrated to be vulnerable to backdoor attacks. As a decentralized machine learning framework, most research focuses on the Single-Label Backdoor Attack (SBA), where adversaries share the same target but neglect the fact that adversaries may be unaware of each other's existence and hold different targets, i.e., Multi-Label Backdoor Attack (MBA). Unfortunately, directly applying prior work to the MBA would not only be ineffective but also potentially mitigate each other. In this paper, we first investigate the limitations of applying previous work to the MBA. Subsequently, we propose M2M, a novel multi-label backdoor attack in federated learning (FL), which adversarially adapts the backdoor trigger to ensure that the backdoored sample is processed as clean target samples in the global model. Our key intuition is to establish a connection between the trigger pattern and the target class distribution, allowing different triggers to activate backdoors along clean activation paths of the target class without concerns about potential mitigation. Extensive evaluations comprehensively demonstrate that M2M outperforms various state-of-the-art attack methods. This work aims to alert researchers and developers to this potential threat and to inspire the design of effective detection methods. Our code will be made available later., Comment: 10 pages, 9 figures

Learning operators for parametric partial differential equations (PDEs) using neural networks has gained significant attention in recent years. However, standard approaches like Deep Operator Networks (DeepONets) require extensive labeled data, and physics-informed DeepONets encounter training challenges. In this paper, we introduce a novel physics-informed tailored finite point operator network (PI-TFPONet) method to solve parametric interface problems without the need for labeled data. Our method fully leverages the prior physical information of the problem, eliminating the need to include the PDE residual in the loss function, thereby avoiding training challenges. The PI-TFPONet is specifically designed to address certain properties of the problem, allowing us to naturally obtain an approximate solution that closely matches the exact solution. Our method is theoretically proven to converge if the local mesh size is sufficiently small and the training loss is minimized. Notably, our approach is uniformly convergent for singularly perturbed interface problems. Extensive numerical studies show that our unsupervised PI-TFPONet is comparable to or outperforms existing state-of-the-art supervised deep operator networks in terms of accuracy and versatility.

Emotion Recognition in Conversations (ERCs) is a vital area within multimodal interaction research, dedicated to accurately identifying and classifying the emotions expressed by speakers throughout a conversation. Traditional ERC approaches predominantly rely on unimodal cues\-such as text, audio, or visual data\-leading to limitations in their effectiveness. These methods encounter two significant challenges: 1) Consistency in multimodal information. Before integrating various modalities, it is crucial to ensure that the data from different sources is aligned and coherent. 2) Contextual information capture. Successfully fusing multimodal features requires a keen understanding of the evolving emotional tone, especially in lengthy dialogues where emotions may shift and develop over time. To address these limitations, we propose a novel Mamba-enhanced Text-Audio-Video alignment network (MaTAV) for the ERC task. MaTAV is with the advantages of aligning unimodal features to ensure consistency across different modalities and handling long input sequences to better capture contextual multimodal information. The extensive experiments on the MELD and IEMOCAP datasets demonstrate that MaTAV significantly outperforms existing state-of-the-art methods on the ERC task with a big margin.

Interface problems pose significant challenges due to the discontinuity of their solutions, particularly when they involve singular perturbations or high-contrast coefficients, resulting in intricate singularities that complicate resolution. The increasing adoption of deep learning techniques for solving partial differential equations has spurred our exploration of these methods for addressing interface problems. In this study, we introduce Tailored Finite Point Operator Networks (TFPONets) as a novel approach for tackling parameterized interface problems. Leveraging DeepONets and integrating the Tailored Finite Point method (TFPM), TFPONets offer enhanced accuracy in reconstructing solutions without the need for intricate equation manipulation. Experimental analyses conducted in both one- and two-dimensional scenarios reveal that, in comparison to existing methods such as DeepONet and IONet, TFPONets demonstrate superior learning and generalization capabilities even with limited locations.

Solving Singularly Perturbed Differential Equations (SPDEs) poses computational challenges arising from the rapid transitions in their solutions within thin regions. The effectiveness of deep learning in addressing differential equations motivates us to employ these methods for solving SPDEs. In this manuscript, we introduce Component Fourier Neural Operator (ComFNO), an innovative operator learning method that builds upon Fourier Neural Operator (FNO), while simultaneously incorporating valuable prior knowledge obtained from asymptotic analysis. Our approach is not limited to FNO and can be applied to other neural network frameworks, such as Deep Operator Network (DeepONet), leading to potential similar SPDEs solvers. Experimental results across diverse classes of SPDEs demonstrate that ComFNO significantly improves accuracy compared to vanilla FNO. Furthermore, ComFNO exhibits natural adaptability to diverse data distributions and performs well in few-shot scenarios, showcasing its excellent generalization ability in practical situations.

Continuous blood pressure (BP) monitoring is essential for timely diagnosis and intervention in critical care settings. However, BP varies significantly across individuals, this inter-patient variability motivates the development of personalized models tailored to each patient's physiology. In this work, we propose a personalized BP forecasting model mainly using electrocardiogram (ECG) and photoplethysmogram (PPG) signals. This time-series model incorporates 2D representation learning to capture complex physiological relationships. Experiments are conducted on datasets collected from three diverse scenarios with BP measurements from 60 subjects total. Results demonstrate that the model achieves accurate and robust BP forecasts across scenarios within the Association for the Advancement of Medical Instrumentation (AAMI) standard criteria. This reliable early detection of abnormal fluctuations in BP is crucial for at-risk patients undergoing surgery or intensive care. The proposed model provides a valuable addition for continuous BP tracking to reduce mortality and improve prognosis., Comment: 5 pages, 2 figures

Physics-informed deep learning (PIDL)-based models have recently garnered remarkable success in traffic state estimation (TSE). However, the prior knowledge used to guide regularization training in current mainstream architectures is based on deterministic physical models. The drawback is that a solely deterministic model fails to capture the universally observed traffic flow dynamic scattering effect, thereby yielding unreliable outcomes for traffic control. This study, for the first time, proposes stochastic physics-informed deep learning (SPIDL) for traffic state estimation. The idea behind such SPIDL is simple and is based on the fact that a stochastic fundamental diagram provides the entire range of possible speeds for any given density with associated probabilities. Specifically, we select percentile-based fundamental diagram and distribution-based fundamental diagram as stochastic physics knowledge, and design corresponding physics-uninformed neural networks for effective fusion, thereby realizing two specific SPIDL models, namely \text{$\alpha$}-SPIDL and \text{$\cal B$}-SPIDL. The main contribution of SPIDL lies in addressing the "overly centralized guidance" caused by the one-to-one speed-density relationship in deterministic models during neural network training, enabling the network to digest more reliable knowledge-based constraints.Experiments on the real-world dataset indicate that proposed SPIDL models achieve accurate traffic state estimation in sparse data scenarios. More importantly, as expected, SPIDL models reproduce well the scattering effect of field observations, demonstrating the effectiveness of fusing stochastic physics model knowledge with deep learning frameworks., Comment: under review in Information Fusion

System-level performance evaluation over satellite networks often requires a simulated or emulated environment for reproducibility and low cost. However, the existing tools may not meet the needs for scenarios such as the low-earth orbit (LEO) satellite networks. To address the problem, this paper proposes and implements a trace-driven emulation method based on Linux's eBPF technology. Building a Starlink traces collection system, we demonstrate that the method can effectively and efficiently emulate the connection conditions, and therefore provides a means for evaluating applications on local hosts., Comment: 4 pages, 4 figures

Full waveform inversion (FWI) plays a crucial role in the field of geophysics. There has been lots of research about applying deep learning (DL) methods to FWI. The success of DL-FWI relies significantly on the quantity and diversity of the datasets. Nevertheless, existing FWI datasets, like OpenFWI, where sources have fixed locations or identical frequencies, provide limited information and do not represent the complex real-world scene. For instance, low frequencies help in resolving larger-scale structures. High frequencies allow for a more detailed subsurface features. %A single source frequency is insufficient to describe subsurface structural properties. We consider that simultaneously using sources with different frequencies, instead of performing inversion using low frequencies data and then gradually introducing higher frequencies data, has rationale and potential advantages. Hence, we develop three enhanced datasets based on OpenFWI where each source have varying locations, frequencies or both. Moreover, we propose a novel deep operator network (DeepONet) architecture Inversion-DeepONet for FWI. We utilize convolutional neural network (CNN) to extract the features from seismic data in branch net. Source parameters, such as locations and frequencies, are fed to trunk net. Then another CNN is employed as the decoder of DeepONet to reconstruct the velocity models more effectively. Through experiments, we confirm the superior performance on accuracy and generalization ability of our network, compared with existing data-driven FWI methods.

Underwater object detection has higher requirements of running speed and deployment efficiency for the detector due to its specific environmental challenges. NMS of two- or one-stage object detectors and transformer architecture of query-based end-to-end object detectors are not conducive to deployment on underwater embedded devices with limited processing power. As for the detrimental effect of underwater color cast noise, recent underwater object detectors make network architecture or training complex, which also hinders their application and deployment on underwater vehicle platforms. In this paper, we propose the Underwater DECO with improved deNoising training (U-DECN), the query-based end-to-end object detector (with ConvNet encoder-decoder architecture) for underwater color cast noise that addresses the above problems. We integrate advanced technologies from DETR variants into DECO and design optimization methods specifically for the ConvNet architecture, including Separate Contrastive DeNoising Forward and Deformable Convolution in SIM. To address the underwater color cast noise issue, we propose an underwater color denoising query to improve the generalization of the model for the biased object feature information by different color cast noise. Our U-DECN, with ResNet-50 backbone, achieves 61.4 AP (50 epochs), 63.3 AP (72 epochs), 64.0 AP (100 epochs) on DUO, and 21 FPS (5 times faster than Deformable DETR and DINO 4 FPS) on NVIDIA AGX Orin by TensorRT FP16, outperforming the other state-of-the-art query-based end-to-end object detectors. The code is available at https://github.com/LEFTeyex/U-DECN.

First-order methods, such as gradient descent (GD) and stochastic gradient descent (SGD), have been proven effective in training neural networks. In the context of over-parameterization, there is a line of work demonstrating that randomly initialized (stochastic) gradient descent converges to a globally optimal solution at a linear convergence rate for the quadratic loss function. However, the learning rate of GD for training two-layer neural networks exhibits poor dependence on the sample size and the Gram matrix, leading to a slow training process. In this paper, we show that for the $L^2$ regression problems, the learning rate can be improved from $\mathcal{O}(\lambda_0/n^2)$ to $\mathcal{O}(1/\|\bm{H}^{\infty}\|_2)$, which implies that GD actually enjoys a faster convergence rate. Furthermore, we generalize the method to GD in training two-layer Physics-Informed Neural Networks (PINNs), showing a similar improvement for the learning rate. Although the improved learning rate has a mild dependence on the Gram matrix, we still need to set it small enough in practice due to the unknown eigenvalues of the Gram matrix. More importantly, the convergence rate is tied to the least eigenvalue of the Gram matrix, which can lead to slow convergence. In this work, we provide the convergence analysis of natural gradient descent (NGD) in training two-layer PINNs, demonstrating that the learning rate can be $\mathcal{O}(1)$, and at this rate, the convergence rate is independent of the Gram matrix.

We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifically, PRANCE~ leverages adaptive token optimization strategies for a certain computational budget, aiming to accelerate ViTs' inference from a unified data and architectural perspective. However, the joint framework poses challenges to both architectural and decision-making aspects. Firstly, while ViTs inherently support variable-token inference, they do not facilitate dynamic computations for variable channels. To overcome this limitation, we propose a meta-network using weight-sharing techniques to support arbitrary channels of the Multi-head Self-Attention and Multi-layer Perceptron layers, serving as a foundational model for architectural decision-making. Second, simultaneously optimizing the structure of the meta-network and input data constitutes a combinatorial optimization problem with an extremely large decision space, reaching up to around $10^{14}$, making supervised learning infeasible. To this end, we design a lightweight selector employing Proximal Policy Optimization for efficient decision-making. Furthermore, we introduce a novel "Result-to-Go" training mechanism that models ViTs' inference process as a Markov decision process, significantly reducing action space and mitigating delayed-reward issues during training. Extensive experiments demonstrate the effectiveness of PRANCE~ in reducing FLOPs by approximately 50\%, retaining only about 10\% of tokens while achieving lossless Top-1 accuracy. Additionally, our framework is shown to be compatible with various token optimization techniques such as pruning, merging, and sequential pruning-merging strategies. The code is available at \href{https://github.com/ChildTang/PRANCE}{https://github.com/ChildTang/PRANCE}.

Optimization algorithms are crucial in training physics-informed neural networks (PINNs), as unsuitable methods may lead to poor solutions. Compared to the common gradient descent (GD) algorithm, implicit gradient descent (IGD) outperforms it in handling certain multi-scale problems. In this paper, we provide convergence analysis for the IGD in training over-parameterized two-layer PINNs. We first demonstrate the positive definiteness of Gram matrices for some general smooth activation functions, such as sigmoidal function, softplus function, tanh function, and others. Then, over-parameterization allows us to prove that the randomly initialized IGD converges a globally optimal solution at a linear convergence rate. Moreover, due to the distinct training dynamics of IGD compared to GD, the learning rate can be selected independently of the sample size and the least eigenvalue of the Gram matrix. Additionally, the novel approach used in our convergence analysis imposes a milder requirement on the network width. Finally, empirical results validate our theoretical findings.

Fast radio bursts (FRBs) are immensely energetic radio pulses with durations of milliseconds. Given their high all-sky rate, the probability of an FRB being lensed by an intervening massive object is non-negligible. In this study, we search for possible lensing candidates within the first Canadian Hydrogen Intensity Mapping Experiment FRB catalogue using an autocorrelation algorithm and verification through signal simulations. We identify FRB 20190308C as a lensed candidate with a significance of 3.4 sigma. Furthermore, we constrain the mass of the lensing object using the Chang-Refsdal lens model, based on the flux ratio and time delay between the substructures of FRB 20190308C. Future long-term and high-precision observations are expected to reveal more lensed FRBs., Comment: 5 pages, 4 figures, submitted

Large language models (LLMs) have captured significant interest from both academia and industry due to their impressive performance across various textual tasks. However, the potential of LLMs to analyze physiological time-series data remains an emerging research field. Particularly, there is a notable gap in the utilization of LLMs for analyzing wearable biosignals to achieve cuffless blood pressure (BP) measurement, which is critical for the management of cardiovascular diseases. This paper presents the first work to explore the capacity of LLMs to perform cuffless BP estimation based on wearable biosignals. We extracted physiological features from electrocardiogram (ECG) and photoplethysmogram (PPG) signals and designed context-enhanced prompts by combining these features with BP domain knowledge and user information. Subsequently, we adapted LLMs to BP estimation tasks through fine-tuning. To evaluate the proposed approach, we conducted assessments of ten advanced LLMs using a comprehensive public dataset of wearable biosignals from 1,272 participants. The experimental results demonstrate that the optimally fine-tuned LLM significantly surpasses conventional task-specific baselines, achieving an estimation error of 0.00 $\pm$ 9.25 mmHg for systolic BP and 1.29 $\pm$ 6.37 mmHg for diastolic BP. Notably, the ablation studies highlight the benefits of our context enhancement strategy, leading to an 8.9% reduction in mean absolute error for systolic BP estimation. This paper pioneers the exploration of LLMs for cuffless BP measurement, providing a potential solution to enhance the accuracy of cuffless BP measurement.

Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy. While real-world datasets are invaluable, simulation-based benchmarks offer a scalable approach for robustness evaluations. However, the creation of a challenging and controllable noisy world with diverse perturbations remains under-explored. To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations. The pipeline comprises a comprehensive taxonomy of sensor and motion perturbations for embodied multi-modal (specifically RGB-D) sensing, categorized by their sources and propagation order, allowing for procedural composition. We also provide a toolbox for synthesizing these perturbations, enabling the transformation of clean environments into challenging noisy simulations. Utilizing the pipeline, we instantiate the large-scale Noisy-Replica benchmark, which includes diverse perturbation types, to evaluate the risk tolerance of existing advanced RGB-D SLAM models. Our extensive analysis uncovers the susceptibilities of both neural (NeRF and Gaussian Splatting -based) and non-neural SLAM models to disturbances, despite their demonstrated accuracy in standard benchmarks. Our code is publicly available at https://github.com/Xiaohao-Xu/SLAM-under-Perturbation., Comment: 50 pages. arXiv admin note: substantial text overlap with arXiv:2402.08125

Vision camera and sonar are naturally complementary in the underwater environment. Combining the information from two modalities will promote better observation of underwater targets. However, this problem has not received sufficient attention in previous research. Therefore, this paper introduces a new challenging RGB-Sonar (RGB-S) tracking task and investigates how to achieve efficient tracking of an underwater target through the interaction of RGB and sonar modalities. Specifically, we first propose an RGBS50 benchmark dataset containing 50 sequences and more than 87000 high-quality annotated bounding boxes. Experimental results show that the RGBS50 benchmark poses a challenge to currently popular SOT trackers. Second, we propose an RGB-S tracker called SCANet, which includes a spatial cross-attention module (SCAM) consisting of a novel spatial cross-attention layer and two independent global integration modules. The spatial cross-attention is used to overcome the problem of spatial misalignment of between RGB and sonar images. Third, we propose a SOT data-based RGB-S simulation training method (SRST) to overcome the lack of RGB-S training datasets. It converts RGB images into sonar-like saliency images to construct pseudo-data pairs, enabling the model to learn the semantic structure of RGB-S-like data. Comprehensive experiments show that the proposed spatial cross-attention effectively achieves the interaction between RGB and sonar modalities and SCANet achieves state-of-the-art performance on the proposed benchmark. The code is available at https://github.com/LiYunfengLYF/RGBS50.

Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains. Under the domain-hungry configuration, how to expand the coverage of source domain and find intrinsic causal features across different distributions is the key to enhancing the models' generalization ability. Existing methods mainly depend on the meticulous design of finite image-level transformation techniques and learning invariant features across domains based on statistical correlation between samples and labels in source domain. This makes it difficult to capture stable semantics between source and target domains, which hinders the improvement of the model's generalization performance. In this paper, we propose a novel causality-inspired latent feature augmentation method for Single-DG by learning the meta-knowledge of feature-level transformation based on causal learning and interventions. Instead of strongly relying on the finite image-level transformation, with the learned meta-knowledge, we can generate diverse implicit feature-level transformations in latent space based on the consistency of causal features and diversity of non-causal features, which can better compensate for the domain-hungry defect and reduce the strong reliance on initial finite image-level transformations and capture more stable domain-invariant causal features for generalization. Extensive experiments on several open-access benchmarks demonstrate the outstanding performance of our model over other state-of-the-art single domain generalization and also multi-source domain generalization methods.

Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges. This has motivated the development of self-supervised pretraining strategies. However, existing pretraining methods mainly employ distinct approaches for each modality. In contrast, we focus on LiDAR-Camera 3D perception models and introduce a unified pretraining strategy, NeRF-Supervised Masked Auto Encoder (NS-MAE), which optimizes all modalities through a shared formulation. NS-MAE leverages NeRF's ability to encode both appearance and geometry, enabling efficient masked reconstruction of multi-modal data. Specifically, embeddings are extracted from corrupted LiDAR point clouds and images, conditioned on view directions and locations. Then, these embeddings are rendered into multi-modal feature maps from two crucial viewpoints for 3D driving perception: perspective and bird's-eye views. The original uncorrupted data serve as reconstruction targets for self-supervised learning. Extensive experiments demonstrate the superior transferability of NS-MAE across various 3D perception tasks under different fine-tuning settings. Notably, NS-MAE outperforms prior SOTA pre-training methods that employ separate strategies for each modality in BEV map segmentation under the label-efficient fine-tuning setting. Our code is publicly available at https://github.com/Xiaohao-Xu/Unified-Pretrain-AD/ ., Comment: 8 pages

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method called \emph{optimum shifting}, which changes the parameters of a neural network from a sharp minimum to a flatter one while maintaining the same training loss value. Our method is based on the observation that when the input and output of a neural network are fixed, the matrix multiplications within the network can be treated as systems of under-determined linear equations, enabling adjustment of parameters in the solution space, which can be simply accomplished by solving a constrained optimization problem. Furthermore, we introduce a practical stochastic optimum shifting technique utilizing the Neural Collapse theory to reduce computational costs and provide more degrees of freedom for optimum shifting. Extensive experiments (including classification and detection) with various deep neural network architectures on benchmark datasets demonstrate the effectiveness of our method.

Rogue waves (RWs) can form on the ocean surface due to quasi-four wave resonant interaction or superposition principle. Both mechanisms have been acutely studied. The first of the two is known as the nonlinear focusing mechanism and leads to an increased probability of rogue waves when wave conditions are favourable, i.e., when unidirectionality and high narrowband energy of the wave field are satisfied. This work delves into the dynamics of extreme wave focusing in crossing seas, revealing a distinct type of nonlinear RWs, characterized by a decisive longevity compared to those generated by the dispersive focusing mechanism. In fact, through fully nonlinear hydrodynamic numerical simulations, we show that the interactions between two crossing unidirectional wave beams can trigger fully localized and robust development of RWs. These coherent structures, characterized by a typical spectral broadening then spreading in the form of dual bimodality and recurrent wave group focusing, not only defy the weakening expectation of quasi-four wave resonant interaction in directionally spread wave fields, but also differ from classical focusing mechanisms already mentioned. This has been determined following a rigorous lifespan-based statistical analysis of extreme wave events in our fully nonlinear simulations. Utilizing the coupled nonlinear Schr\"odinger framework, we also show that such intrinsic focusing dynamics can also be captured by weakly nonlinear wave evolution equations. This opens new research avenues for further explorations of these complex and intriguing wave phenomena in hydrodynamics as well as other nonlinear and dispersive multi-wave systems.

How to better fuse cross-modal features is the core issue of RGB-T tracking. Some previous methods either insufficiently fuse RGB and TIR features, or depend on intermediaries containing information from both modalities to achieve cross-modal information interaction. The former does not fully exploit the potential of using only RGB and TIR information of the template or search region for channel and spatial feature fusion, and the latter lacks direct interaction between the template and search area, which limits the model's ability to fully exploit the original semantic information of both modalities. To alleviate these limitations, we explore how to improve the performance of a visual Transformer by using direct fusion of cross-modal channels and spatial features, and propose CSTNet. CSTNet uses ViT as a backbone and inserts cross-modal channel feature fusion modules (CFM) and cross-modal spatial feature fusion modules (SFM) for direct interaction between RGB and TIR features. The CFM performs parallel joint channel enhancement and joint multilevel spatial feature modeling of RGB and TIR features and sums the features, and then globally integrates the sum feature with the original features. The SFM uses cross-attention to model the spatial relationship of cross-modal features and then introduces a convolutional feedforward network for joint spatial and channel integration of multimodal features. We retrain the model with CSNet as the pre-training weights in the model with CFM and SFM removed, and propose CSTNet-small, which achieves 36% reduction in parameters and 24% reduction in Flops, and 50% speedup with a 1-2% performance decrease. Comprehensive experiments show that CSTNet achieves state-of-the-art performance on three public RGB-T tracking benchmarks. Code is available at https://github.com/LiYunfengLYF/CSTNet., Comment: This work has been submitted to the IEEE for possible publication

Propagating spiral waves have been discovered in various chemical, biological and physical systems. Spiral waves in multicellular organisms are often associated with essential living functions. Although certain eukaryotic microorganisms have long been known to generate spiral waves, evidence of spiral wave pattern has not been lacking in the bacterial world. Here we report the discovery of a unique form of propagating spiral waves in dense bacterial populations where cells engage in cyclic force-generating processes driven by type-IV pilus motility. Specifically, we discovered that synchronization of pilus activity in the bacterial living matter leads to large-scale spatiotemporal regulation of tension force in the form of propagating spiral waves. Theoretical modelling reveals that the spiral tension waves result from nonreciprocity in cell-cell interactions. Our findings reveal a novel mechanism of large-scale force regulation in bacterial world and may shed light on the emergent mechanics of biofilms and microbiomes. Pilus-driven bacterial living matter also provides a mechanical active medium for studying electrical or chemical spiral waves in living systems., Comment: 27 pages, 4 main figures

The reliability of driving perception systems under unprecedented conditions is crucial for practical usage. Latest advancements have prompted increasing interest in multi-LiDAR perception. However, prevailing driving datasets predominantly utilize single-LiDAR systems and collect data devoid of adverse conditions, failing to capture the complexities of real-world environments accurately. Addressing these gaps, we proposed Place3D, a full-cycle pipeline that encompasses LiDAR placement optimization, data generation, and downstream evaluations. Our framework makes three appealing contributions. 1) To identify the most effective configurations for multi-LiDAR systems, we introduce the Surrogate Metric of the Semantic Occupancy Grids (M-SOG) to evaluate LiDAR placement quality. 2) Leveraging the M-SOG metric, we propose a novel optimization strategy to refine multi-LiDAR placements. 3) Centered around the theme of multi-condition multi-LiDAR perception, we collect a 280,000-frame dataset from both clean and adverse conditions. Extensive experiments demonstrate that LiDAR placements optimized using our approach outperform various baselines. We showcase exceptional results in both LiDAR semantic segmentation and 3D object detection tasks, under diverse weather and sensor failure conditions., Comment: NeurIPS 2024 (Spotlight); 36 pages, 16 figures, 14 tables; Code at https://github.com/ywyeli/Place3D

In the context of changing travel behaviors and the expanding user base of Geographic Information System (GIS) services, conventional centralized architectures responsible for handling shortest distance queries are facing increasing challenges, such as heightened load pressure and longer response times. To mitigate these concerns, this study is the first to develop an edge computing framework specially tailored for processing distance queries. In conjunction with this innovative system, we have developed a straightforward, yet effective, labeling technique termed Border Labeling. Furthermore, we have devised and implemented a range of query strategies intended to capitalize on the capabilities of the edge computing infrastructure. Our experiments demonstrate that our solution surpasses other methods in terms of both indexing time and query speed across various road network datasets. The empirical evidence from our experiments supports the claim that our edge computing architecture significantly reduces the latency encountered by end-users, thus markedly decreasing their waiting times., Comment: 15pages, 18(sub)pages

Large language models (LLMs) have demonstrated impressive performance in various natural language processing (NLP) tasks. However, there is limited understanding of how well LLMs perform in specific domains (e.g, the intellectual property (IP) domain). In this paper, we contribute a new benchmark, the first Multilingual-oriented quiZ on Intellectual Property (MoZIP), for the evaluation of LLMs in the IP domain. The MoZIP benchmark includes three challenging tasks: IP multiple-choice quiz (IPQuiz), IP question answering (IPQA), and patent matching (PatentMatch). In addition, we also develop a new IP-oriented multilingual large language model (called MoZi), which is a BLOOMZ-based model that has been supervised fine-tuned with multilingual IP-related text data. We evaluate our proposed MoZi model and four well-known LLMs (i.e., BLOOMZ, BELLE, ChatGLM and ChatGPT) on the MoZIP benchmark. Experimental results demonstrate that MoZi outperforms BLOOMZ, BELLE and ChatGLM by a noticeable margin, while it had lower scores compared with ChatGPT. Notably, the performance of current LLMs on the MoZIP benchmark has much room for improvement, and even the most powerful ChatGPT does not reach the passing level. Our source code, data, and models are available at \url{https://github.com/AI-for-Science/MoZi}.

Robustness is a crucial factor for the successful deployment of robots in unstructured environments, particularly in the domain of Simultaneous Localization and Mapping (SLAM). Simulation-based benchmarks have emerged as a highly scalable approach for robustness evaluation compared to real-world data collection. However, crafting a challenging and controllable noisy world with diverse perturbations remains relatively under-explored. To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations. This pipeline incorporates customizable hardware setups, software components, and perturbed environments. In particular, we introduce comprehensive perturbation taxonomy along with a perturbation composition toolbox, allowing the transformation of clean simulations into challenging noisy environments. Utilizing the pipeline, we instantiate the Robust-SLAM benchmark, which includes diverse perturbation types, to evaluate the risk tolerance of existing advanced multi-modal SLAM models. Our extensive analysis uncovers the susceptibilities of existing SLAM models to real-world disturbance, despite their demonstrated accuracy in standard benchmarks. Our perturbation synthesis toolbox, SLAM robustness evaluation pipeline, and Robust-SLAM benchmark will be made publicly available at https://github.com/Xiaohao-Xu/SLAM-under-Perturbation/., Comment: 40 pages

We present a unified three-state model (TSM) framework for evaluating treatment effects in clinical trials in the presence of treatment crossover. Researchers have proposed diverse methodologies to estimate the treatment effect that would have hypothetically been observed if treatment crossover had not occurred. However, there is little work on understanding the connections between these different approaches from a statistical point of view. The proposed TSM framework unifies existing methods, effectively identifying potential biases, model assumptions, and inherent limitations for each method. This can guide researchers in understanding when these methods are appropriate and choosing a suitable approach for their data. The TSM framework also facilitates the creation of new methods to adjust for confounding effects from treatment crossover. To illustrate this capability, we introduce a new imputation method that falls under its scope. Through simulation experiments, we demonstrate the performance of different approaches for estimating the treatment effects. Codes for implementing the methods within the TSM framework are available at https://github.com/JasonZhao111/TSM., Comment: 39 pages, 7 figures, 4 tables. Another method was added to Section 3.6, and more extensive simulation studies were added to Section 4 and Appendix B

We present a method to estimate the detection expectations of host galaxies of long gamma-ray bursts (LGRBs) in the {\it grizJHKL} bands. It is found that given the same limiting magnitude $m_{grizJHKL,\rm lim}$ in each band, the {\it z} band produces the largest number of overall LGRB hosts and low-mass hosts ($M_\ast\leq10^8$ M$_\odot$) at $m_{grizJHKL,\rm lim}\gtrsim 26$ mag. For the detection of high-redshift LGRB hosts (redshift $\geq5$), it is recommended to prioritize the {\it L} band due to its good performance at both low and high limiting magnitudes. We specifically estimate the expectation of LGRB-host detection with $m_{grizJHKL,\rm lim}=28$ mag, which the James Webb Space Telescope can partially attain. We find that there may exist 116, 259, 277, 439, 266, 294, 274, and 316 LGRB hosts, including 0.54, 31, 28, 143, 12, 20, 14, and 35 low-mass ones in the {\it grizJHKL} bands and 13, 14, 15, 14, and 15 high-redshift ones in the {\it zJHKL} bands, for 15 yr {\it Swift} LGRBs with $S\geq10^{-6}$ erg cm$^{-2}$. The results show that the study of LGRB hosts under next-generation observational conditions holds significant potential, especially for low-mass host studies. However, it appears that deeper sensitivities of galaxy telescopes may not significantly enhance statistical studies of high-redshift hosts. Strategies aimed at increasing the number of distant LGRB hosts may require the expansion of high-redshift LGRB detection., Comment: Updating published version

This paper presents Graph-of-Thought (GoT), a new model for workflow automation that enhances the flexibility and efficiency of Large Language Models (LLMs) in complex task execution. GoT advances beyond traditional linear and tree-like cognitive models with a graph structure that enables dynamic path selection. The open-source engine GoTFlow demonstrates the practical application of GoT, facilitating automated, data-driven decision-making across various domains. Despite challenges in complexity and transparency, GoTFlow's potential for improving business processes is significant, promising advancements in both efficiency and decision quality with continuous development., Comment: Keywords: Graph-of-Thought (GoT), Workflow Automation, Large Language Models (LLMs), Task Execution, Data-Driven Decision Making, Complexity Management

Physics-informed neural networks (PINNs) have shown promising potential for solving partial differential equations (PDEs) using deep learning. However, PINNs face training difficulties for evolutionary PDEs, particularly for dynamical systems whose solutions exhibit multi-scale or turbulent behavior over time. The reason is that PINNs may violate the temporal causality property since all the temporal features in the PINNs loss are trained simultaneously. This paper proposes to use implicit time differencing schemes to enforce temporal causality, and use transfer learning to sequentially update the PINNs in space as surrogates for PDE solutions in different time frames. The evolving PINNs are better able to capture the varying complexities of the evolutionary equations, while only requiring minor updates between adjacent time frames. Our method is theoretically proven to be convergent if the time step is small and each PINN in different time frames is well-trained. In addition, we provide state-of-the-art (SOTA) numerical results for a variety of benchmarks for which existing PINNs formulations may fail or be inefficient. We demonstrate that the proposed method improves the accuracy of PINNs approximation for evolutionary PDEs and improves efficiency by a factor of 4-40x., Comment: 23 pages, 20 figures

Multimodal semantic segmentation is developing rapidly, but the modality of RGB-Polarization remains underexplored. To delve into this problem, we construct a UPLight RGB-P segmentation benchmark with 12 typical underwater semantic classes. In this work, we design the ShareCMP, an RGB-P semantic segmentation framework with a shared dual-branch architecture, which reduces the number of parameters by about 26-33% compared to previous dual-branch models. It encompasses a Polarization Generate Attention (PGA) module designed to generate polarization modal images with richer polarization properties for the encoder. In addition, we introduce the Class Polarization-Aware Loss (CPALoss) to improve the learning and understanding of the encoder for polarization modal information and to optimize the PGA module. With extensive experiments on a total of three RGB-P benchmarks, our ShareCMP achieves state-of-the-art performance in mIoU with fewer parameters on the UPLight (92.45(+0.32)%), ZJU (92.7(+0.1)%), and MCubeS (50.99(+1.51)%) datasets compared to the previous best methods. The code is available at https://github.com/LEFTeyex/ShareCMP., Comment: 10 pages, 5 figures