Search

The field of autonomous driving increasingly demands high-quality annotated video training data. In this paper, we propose Panacea+, a powerful and universally applicable framework for generating video data in driving scenes. Built upon the foundation of our previous work, Panacea, Panacea+ adopts a multi-view appearance noise prior mechanism and a super-resolution module for enhanced consistency and increased resolution. Extensive experiments show that the generated video samples from Panacea+ greatly benefit a wide range of tasks on different datasets, including 3D object tracking, 3D object detection, and lane detection tasks on the nuScenes and Argoverse 2 dataset. These results strongly prove Panacea+ to be a valuable data generation framework for autonomous driving., Comment: Project page: https://panacea-ad.github.io/. arXiv admin note: text overlap with arXiv:2311.16813

The interplay of quantum emitters and non-Hermitian structured baths has received increasing attention in recent years. Here, we predict unconventional quantum optical behaviors of quantum emitters coupled to a non-Hermitian topological bath, which is realized in a 1D Su-Schrieffer-Heeger photonic chain subjected to nonlocal dissipation. In addition to the Hermitian-like chiral bound states in the middle line gap and skin-mode-like hidden bound states inside the point gap, we identify peculiar in-gap chiral and extended photon-emitter dressed states. This is due to the competition of topological-edge localization and non-Hermitian skin-mode localization in combination with the non-Bloch bulk-boundary correspondence. Furthermore, when two emitters are coupled to the same bath, such in-gap dressed states can mediate the nonreciprocal long-range emitter-emitter interactions, with the interaction range limited only by the dissipation of the bath. Our work opens the door to further study rich quantum optical phenomena and exotic many-body physics utilizing quantum emitters coupled to non-Hermitian topological baths., Comment: 22 pages, 10 figures; Comments are welcome

The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches., Comment: 10 pages, 12 figures

Accurate classification of blood cells is of vital significance in the diagnosis of hematological disorders. However, in real-world scenarios, domain shifts caused by the variability in laboratory procedures and settings, result in a rapid deterioration of the model's generalization performance. To address this issue, we propose a novel framework of domain-invariant representation learning (DoRL) via segment anything model (SAM) for blood cell classification. The DoRL comprises two main components: a LoRA-based SAM (LoRA-SAM) and a cross-domain autoencoder (CAE). The advantage of DoRL is that it can extract domain-invariant representations from various blood cell datasets in an unsupervised manner. Specifically, we first leverage the large-scale foundation model of SAM, fine-tuned with LoRA, to learn general image embeddings and segment blood cells. Additionally, we introduce CAE to learn domain-invariant representations across different-domain datasets while mitigating images' artifacts. To validate the effectiveness of domain-invariant representations, we employ five widely used machine learning classifiers to construct blood cell classification models. Experimental results on two public blood cell datasets and a private real dataset demonstrate that our proposed DoRL achieves a new state-of-the-art cross-domain performance, surpassing existing methods by a significant margin. The source code can be available at the URL (https://github.com/AnoK3111/DoRL).

Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods, particularly small models, struggle with processing logical reasoning, question-answering, and handling open scenario categories. On the other hand, generative multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks, due to weak spatial and local object perception, poor text-based geometric numerical output, and inability to handle camera focal variations. To address these challenges, we propose the following solutions: Spatial-Enhanced Local Feature Mining for better spatial feature extraction, 3D Query Token-Derived Info Decoding for precise geometric regression, and Geometry Projection-Based 3D Reasoning for handling camera focal length variations. We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM. Additionally, we have constructed the IG3D dataset, which provides fine-grained descriptions and question-answer annotations. Extensive experiments demonstrate that our LLMI3D achieves state-of-the-art performance, significantly outperforming existing methods.

Coordinated multipoint (CoMP) systems incur substantial resource consumption due to the management of backhaul links and the coordination among various base stations (BSs). Accurate prediction of coordinated spectral efficiency (CSE) can guide the optimization of network parameters, resulting in enhanced resource utilization efficiency. However, characterizing the CSE is intractable due to the inherent complexity of the CoMP channel model and the diversity of the 5G dynamic network environment, which poses a great challenge for CSE prediction in real-world 5G CoMP systems. To address this challenge, in this letter, we propose a data-driven model-assisted approach. Initially, we leverage domain knowledge to preprocess the collected raw data, thereby creating a well-informed dataset. Within this dataset, we explicitly define the target variable and the input feature space relevant to channel statistics for CSE prediction. Subsequently, a residual-based network model is built to capture the high-dimensional non-linear mapping function from the channel statistics to the CSE. The effectiveness of the proposed approach is validated by experimental results on real-world data.

Recent breakthroughs in understanding the human brain have revealed its impressive ability to efficiently process and interpret human thoughts, opening up possibilities for intervening in brain signals. In this paper, we aim to develop a straightforward framework that uses other modalities, such as natural language, to translate the original dreamland. We present DreamConnect, employing a dual-stream diffusion framework to manipulate visually stimulated brain signals. By integrating an asynchronous diffusion strategy, our framework establishes an effective interface with human dreams, progressively refining their final imagery synthesis. Through extensive experiments, we demonstrate the method ability to accurately instruct human brain signals with high fidelity. Our project will be publicly available on https://github.com/Sys-Nexus/DreamConnect

In this paper, we propose an information geometry (IG) framework to solve the standard linear regression problem. The proposed framework is an extension of the one for computing the mean of complex multivariate Gaussian distribution. By applying the proposed framework, the information geometry approach (IGA) and the approximate information geometry approach (AIGA) for basis pursuit de-noising (BPDN) in standard linear regression are derived. The framework can also be applied to other standard linear regression problems. With the transformations of natural and expectation parameters of Gaussian distributions, we then show the relationship between the IGA and the message passing (MP) algorithm. Finally, we prove that the AIGA is equivalent to the approximate message passing (AMP) algorithm. These intrinsic results offer a new perspective for the AMP algorithm, and clues for understanding and improving stochastic reasoning methods., Comment: 30 pages, 5 figures

Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, also lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks: object classification, understanding spatial arrangement, and ability to delineate individual object instances (through counting), by constructing a series of tests that probe which components of design, specifically, maybe lacking. Importantly, we go significantly beyond the current benchmarks, that simply measure final performance of VLM, by also comparing and contrasting it to performance of probes trained directly on features obtained from visual encoder (image embeddings), as well as intermediate vision-language projection used to bridge image-encoder and LLM-decoder ouput in many SoTA models (e.g., LLaVA, BLIP, InstructBLIP). In doing so, we uncover nascent shortcomings in VLMs response and make a number of important observations which could help train and develop more effective VLM models in future., Comment: Under Submission

Accurate classification of blood cells plays a vital role in hematological analysis as it aids physicians in diagnosing various medical conditions. In this study, we present a novel approach for classifying blood cell images known as BC-SAM. BC-SAM leverages the large-scale foundation model of Segment Anything Model (SAM) and incorporates a fine-tuning technique using LoRA, allowing it to extract general image embeddings from blood cell images. To enhance the applicability of BC-SAM across different blood cell image datasets, we introduce an unsupervised cross-domain autoencoder that focuses on learning intrinsic features while suppressing artifacts in the images. To assess the performance of BC-SAM, we employ four widely used machine learning classifiers (Random Forest, Support Vector Machine, Artificial Neural Network, and XGBoost) to construct blood cell classification models and compare them against existing state-of-the-art methods. Experimental results conducted on two publicly available blood cell datasets (Matek-19 and Acevedo-20) demonstrate that our proposed BC-SAM achieves a new state-of-the-art result, surpassing the baseline methods with a significant improvement. The source code of this paper is available at https://github.com/AnoK3111/BC-SAM.

Using $(2712\pm 14)$ $\times$ 10$^{6}$ $\psi(2S)$ events collected with the BESIII detector at the BEPCII collider, we search for the decays $\eta_{c}(2S)\to\omega\omega$ and $\eta_{c}(2S)\to\omega\phi$ via the process $\psi(2S)\to\gamma\eta_{c}(2S)$. Evidence of $\eta_{c}(2S)\to\omega\omega$ is found with a statistical significance of $3.2\sigma$. The branching fraction is measured to be $\mathcal{B}(\eta_{c}(2S)\to\omega\omega)=(5.65\pm3.77(\rm stat.)\pm5.32(\rm syst.))\times10^{-4}$. No statistically significant signal is observed for the decay $\eta_{c}(2S)\to\omega\phi$. The upper limit of the branching fraction at the 90\% confidence level is determined to be $\mathcal{B}(\psi(2S)\to\gamma\eta_{c}(2S),\eta_{c}(2S)\to\omega\phi)<2.24\times 10^{-7}$. We also update the branching fractions of $\chi_{cJ}\to \omega\omega$ and $\chi_{cJ}\to\omega\phi$ decays via the $\psi(2S)\to\gamma\chi_{cJ}$ transition. The branching fractions are determined to be $\mathcal{B}(\chi_{c0}\to\omega\omega)=(10.63\pm0.11\pm0.46)\times 10^{-4}$, $\mathcal{B}(\chi_{c1}\to\omega\omega)=(6.39\pm0.07\pm0.29)\times 10^{-4}$, $\mathcal{B}(\chi_{c2}\to\omega\omega)=(8.50\pm0.08\pm0.38)\times 10^{-4}$, $\mathcal{B}(\chi_{c0}\to\omega\phi)=(1.18\pm0.03\pm0.05)\times 10^{-4}$, $\mathcal{B}(\chi_{c1}\to\omega\phi)=(2.03\pm0.15\pm0.12)\times 10^{-5}$, and $\mathcal{B}(\chi_{c2}\to\omega\phi)=(9.37\pm1.07\pm0.59)\times 10^{-6}$, where the first uncertainties are statistical and the second are systematic.

In recent years, user-generated content (UGC) has become one of the major video types consumed via streaming networks. Numerous research contributions have focused on assessing its visual quality through subjective tests and objective modeling. In most cases, objective assessments are based on a no-reference scenario, where the corresponding reference content is assumed not to be available. However, full-reference video quality assessment is also important for UGC in the delivery pipeline, particularly associated with the video transcoding process. In this context, we present a new UGC video quality database, BVI-UGC, for user-generated content transcoding, which contains 60 (non-pristine) reference videos and 1,080 test sequences. In this work, we simulated the creation of non-pristine reference sequences (with a wide range of compression distortions), typical of content uploaded to UGC platforms for transcoding. A comprehensive crowdsourced subjective study was then conducted involving more than 3,500 human participants. Based on this collected subjective data, we benchmarked the performance of 10 full-reference and 11 no-reference quality metrics. Our results demonstrate the poor performance (SROCC values are lower than 0.6) of these metrics in predicting the perceptual quality of UGC in two different scenarios (with or without a reference)., Comment: 12 pages, 11 figures

Shifted CholeskyQR3 is designed to address the QR factorization of ill-conditioned matrices. This algorithm introduces a shift parameter $s$ to prevent failure during the initial Cholesky factorization step. The choice of this shift parameter $s$ is critical for the algorithm's effectiveness. Our goal is to identify a smaller $s$ compared to the traditional selection involving $\|X\|_2$. In this research, we propose a new norm $\|X\|_g$, which is based on the column properties of $X$, to obtain a reduced shift parameter $s$ for the Shifted CholeskyQR3 algorithm. We provide rigorous proofs of orthogonality and residuals for the improved algorithm with our proposed $s$. Numerical experiments confirm the enhanced numerical stability of orthogonality and residuals with the reduced $s$. Furthermore, we compare CPU times with other algorithms to assess performance improvements.

Several recent techniques for modifying topological codes with single-qubit Clifford operators have shown high resilience against pure Pauli noise. Paramount to these findings has been the demonstration that several variants exhibit error thresholds often attaining or exceeding the zero-rate hashing bound, a known benchmark for code-capacity noise channels, for biased noise. Additionally, direct comparison with the hashing bound has shown that several topological codes outperform the hashing bound at points of finite Pauli noise biases. Motivated by these observations, we study zero-rate holographic quantum error correction codes, discovering very high threshold values under diverse and finitely-biased noise channels using a tensor-network decoding approach. Our results establish that all codes tested achieve or surpass the hashing bound at various points, ranging from pure 2-Pauli noise ($\eta = 0$) to pure 1-Pauli noise ($\eta = +\infty$), thereby demonstrating that holographic codes exhibit excellent error tolerance in the code-capacity picture. Such findings imply the existence of a structured and systematic method for constructing high-threshold codes suitable for realistically motivated noise channels. To our knowledge, this work is also the first instance of such remarkable threshold behavior in stabilizer quantum codes for the pure 2-Pauli noise regime, as well as for finitely-biased noise channels., Comment: 8 pages, 5 figures, 2 tables

This paper introduces rStar, a self-play mutual reasoning approach that significantly improves reasoning capabilities of small language models (SLMs) without fine-tuning or superior models. rStar decouples reasoning into a self-play mutual generation-discrimination process. First, a target SLM augments the Monte Carlo Tree Search (MCTS) with a rich set of human-like reasoning actions to construct higher quality reasoning trajectories. Next, another SLM, with capabilities similar to the target SLM, acts as a discriminator to verify each trajectory generated by the target SLM. The mutually agreed reasoning trajectories are considered mutual consistent, thus are more likely to be correct. Extensive experiments across five SLMs demonstrate rStar can effectively solve diverse reasoning problems, including GSM8K, GSM-Hard, MATH, SVAMP, and StrategyQA. Remarkably, rStar boosts GSM8K accuracy from 12.51% to 63.91% for LLaMA2-7B, from 36.46% to 81.88% for Mistral-7B, from 74.53% to 91.13% for LLaMA3-8B-Instruct. Code will be available at https://github.com/zhentingqi/rStar.

Neural enhancement through super-resolution (SR) deep neural networks (DNNs) opens up new possibilities for ultra-high-definition (UHD) live streaming over existing encoding and networking infrastructure. Yet, the heavy SR DNN inference overhead leads to severe deployment challenges. To reduce the overhead, existing systems propose to apply DNN-based SR only on carefully selected anchor frames while upscaling non-anchor frames via the lightweight reusing-based SR approach. However, frame-level scheduling is coarse-grained and fails to deliver optimal efficiency. In this work, we propose Palantir, the first neural-enhanced UHD live streaming system with fine-grained patch-level scheduling. Two novel techniques are incorporated into Palantir to select the most beneficial anchor patches and support latency-sensitive UHD live streaming applications. Firstly, under the guidance of our pioneering and theoretical analysis, Palantir constructs a directed acyclic graph (DAG) for lightweight yet accurate SR quality estimation under any possible anchor patch set. Secondly, to further optimize the scheduling latency, Palantir improves parallelizability by refactoring the computation subprocedure of the estimation process into a sparse matrix-matrix multiplication operation. The evaluation results suggest that Palantir incurs a negligible scheduling latency accounting for less than 5.7% of the end-to-end latency requirement. When compared to the naive method of applying DNN-based SR on all the frames, Palantir can reduce the SR DNN inference overhead by 20 times (or 60 times) while preserving 54.0-82.6% (or 32.8-64.0%) of the quality gain. When compared to the state-of-the-art real-time frame-level scheduling strategy, Palantir can reduce the SR DNN inference overhead by 80.1% at most (and 38.4% on average) without sacrificing the video quality.

Despite the rise of digital libraries and online reading platforms, physical libraries still offer unique benefits for education and community engagement. However, due to the convenience of digital resources, physical library visits, especially by college students, have declined. This underscores the need to better engage these users. Augmented Reality (AR) could potentially bridge the gap between the physical and digital worlds. In this paper, we present \textit{Augmented Library}, an HMD-based AR system designed to revitalize the physical library experience. By creating interactive features that enhance book discovery, encourage community engagement, and cater to diverse user needs, \textit{Augmented Library} combines digital convenience with physical libraries' rich experiences. This paper discusses the development of the system and preliminary user feedback on its impact on student engagement in physical libraries., Comment: 5 pages, 3 figures

As large language model (LLM) inference demands ever-greater resources, there is a rapid growing trend of using low-bit weights to shrink memory usage and boost inference efficiency. However, these low-bit LLMs introduce the need for mixed-precision matrix multiplication (mpGEMM), which is a crucial yet under-explored operation that involves multiplying lower-precision weights with higher-precision activations. Unfortunately, current hardware does not natively support mpGEMM, resulting in indirect and inefficient dequantization-based implementations. To address the mpGEMM requirements in low-bit LLMs, we explored the lookup table (LUT)-based approach for mpGEMM. However, a conventional LUT implementation falls short of its potential. To fully harness the power of LUT-based mpGEMM, we introduce LUT Tensor Core, a software-hardware co-design optimized for low-bit LLM inference. Specifically, we introduce software-based operator fusion and table symmetrization techniques to optimize table precompute and table storage, respectively. Then, LUT Tensor Core proposes the hardware design featuring an elongated tiling shape design to enhance table reuse and a bit-serial design to support various precision combinations in mpGEMM. Moreover, we design an end-to-end compilation stack with new instructions for LUT-based mpGEMM, enabling efficient LLM compilation and optimizations. The evaluation on low-bit LLMs (e.g., BitNet, LLAMA) shows that LUT Tensor Core achieves more than a magnitude of improvements on both compute density and energy efficiency.

Electron-positron pair production is investigated in the multiphoton regime under polarized fields. Partial wave analysis can be applied to reveal the momentum spectral structure and identify the positions of valleys/peaks of the multiphoton rings by combining with $CP$ conservation. Moreover, considering the spin states of created pairs in partial wave analysis, the particle orbital angular momentum associated with the valleys/peaks can also be identified from multiphoton rings. It is found that the results for angular distribution by this approximate analytical treatment and by the Dirac-Heisenberg-Wigner formalism are consistent with each other. The present results are helpful for understanding the angular momentum information in momentum spectra, and they also have an implication for revealing the vortex structure near the valleys., Comment: 17 pages, 4 figures, 2 tables

Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties. We here propose a new GFlowNet training framework, with policy-dependent rewards, that bridges keeping flow balance of GFlowNets to optimizing the expected accumulated reward in traditional Reinforcement-Learning (RL). This enables the derivation of new policy-based GFlowNet training methods, in contrast to existing ones resembling value-based RL. It is known that the design of backward policies in GFlowNet training affects efficiency. We further develop a coupled training strategy that jointly solves GFlowNet forward policy training and backward policy design. Performance analysis is provided with a theoretical guarantee of our policy-based GFlowNet training. Experiments on both simulated and real-world datasets verify that our policy-based strategies provide advanced RL perspectives for robust gradient estimation to improve GFlowNet performance.

Time series classification with missing data is a prevalent issue in time series analysis, as temporal data often contain missing values in practical applications. The traditional two-stage approach, which handles imputation and classification separately, can result in sub-optimal performance as label information is not utilized in the imputation process. On the other hand, a one-stage approach can learn features under missing information, but feature representation is limited as imputed errors are propagated in the classification process. To overcome these challenges, this study proposes an end-to-end neural network that unifies data imputation and representation learning within a single framework, allowing the imputation process to take advantage of label information. Differing from previous methods, our approach places less emphasis on the accuracy of imputation data and instead prioritizes classification performance. A specifically designed multi-scale feature learning module is implemented to extract useful information from the noise-imputation data. The proposed model is evaluated on 68 univariate time series datasets from the UCR archive, as well as a multivariate time series dataset with various missing data ratios and 4 real-world datasets with missing information. The results indicate that the proposed model outperforms state-of-the-art approaches for incomplete time series classification, particularly in scenarios with high levels of missing data.

Optical remote sensing and Synthetic Aperture Radar(SAR) remote sensing are crucial for earth observation, offering complementary capabilities. While optical sensors provide high-quality images, they are limited by weather and lighting conditions. In contrast, SAR sensors can operate effectively under adverse conditions. This letter proposes a GAN-based SAR-to-optical image translation method named Seg-CycleGAN, designed to enhance the accuracy of ship target translation by leveraging semantic information from a pre-trained semantic segmentation model. Our method utilizes the downstream task of ship target semantic segmentation to guide the training of image translation network, improving the quality of output Optical-styled images. The potential of foundation-model-annotated datasets in SAR-to-optical translation tasks is revealed. This work suggests broader research and applications for downstream-task-guided frameworks. The code will be available at https://github.com/NPULHH/, Comment: 8 pages, 5 figures

Magnetic Resonance Imaging (MRI) has become essential in clinical diagnosis due to its high resolution and multiple contrast mechanisms. However, the relatively long acquisition time limits its broader application. To address this issue, this study presents an innovative conditional guided diffusion model, named as TC-KANRecon, which incorporates the Multi-Free U-KAN (MF-UKAN) module and a dynamic clipping strategy. TC-KANRecon model aims to accelerate the MRI reconstruction process through deep learning methods while maintaining the quality of the reconstructed images. The MF-UKAN module can effectively balance the tradeoff between image denoising and structure preservation. Specifically, it presents the multi-head attention mechanisms and scalar modulation factors, which significantly enhances the model's robustness and structure preservation capabilities in complex noise environments. Moreover, the dynamic clipping strategy in TC-KANRecon adjusts the cropping interval according to the sampling steps, thereby mitigating image detail loss typically caused by traditional cropping methods and enriching the visual features of the images. Furthermore, the MC-Model module incorporates full-sampling k-space information, realizing efficient fusion of conditional information, enhancing the model's ability to process complex data, and improving the realism and detail richness of reconstructed images. Experimental results demonstrate that the proposed method outperforms other MRI reconstruction methods in both qualitative and quantitative evaluations. Notably, TC-KANRecon method exhibits excellent reconstruction results when processing high-noise, low-sampling-rate MRI data. Our source code is available at https://github.com/lcbkmm/TC-KANRecon., Comment: 10 pages, 3 figures

In this paper, we investigate the existence and uniqueness of global solutions to the Cauchy problem for a coupled stochastic chemotaxis-Navier-Stokes system with multiplicative L\'{e}vy noises in $\mathbb{R}^2$. The existence of global martingale solutions is proved under a framework that is based on the Faedo-Galerkin approximation scheme and stochastic compactness method, where the verification of tightness depends crucially on a novel stochastic version of Lyapunov functional inequality and proper compactness criteria in Fr\'{e}chet spaces. A pathwise uniqueness result is also established with suitable assumption on the jump noises, which indicates that the considered system admits a unique global strong solution.

This paper considers the stochastic Landau-Lifshitz-Baryakhtar (SLLBar) equation with pure jump noise in Marcus canonical form, which describes the dynamics of magnetic spin field in a ferromagnet at elevated temperatures with the effective field $\mathbf{H}_{\textrm{eff}}$ influenced by external random noise. Under the natural assumption that the magnetic body $\mathcal{O}\subset\mathbb{R}^d$ ($d=1,2,3$) is bounded with smooth boundary, we shall prove that the initial-boundary value problem of SLLBar equation possesses a unique global probabilistically strong and analytically weak solution with initial data in the energy space $\mathbb{H}^1(\mathcal{O})$. Then by employing the weak convergence method, we proceed to establish a Freidlin-Wentzell type large deviation principle for pathwise solutions to the SLLBar equation.

Coherent control of wave transmission and reflection is crucial for applications in communication, imaging, and sensing. However, many practical scenarios involve partially coherent waves rather than fully coherent ones. We present a systematic theory for the unitary control of partially coherent wave transmission and reflection. For a linear time-invariant system with an incident partially coherent wave, we derive analytical expressions for the range of attainable total transmittance and reflectance under arbitrary unitary transformations. We also introduce an explicit algorithm to construct a unitary control scheme that achieves any desired transmission or reflection within the attainable range. As applications of our theory, we establish conditions for four novel phenomena: partially coherent perfect transmission, partially coherent perfect reflection, partially coherent zero transmission, and partially coherent zero reflection. We also prove a theorem that relates the degree of coherence of the incident field, quantified by the majorization order, to the resulting transmission and reflection intervals. Furthermore, we demonstrate that reciprocity (or energy conservation) imposes direct symmetry constraints on bilateral transmission (or transmission and reflection) of partially coherent waves under unitary control. Our results provide fundamental insights and practical guidelines for using unitary control to manipulate the transmission and reflection of partially coherent waves. This theory applies to various wave systems, including electromagnetic and acoustic waves., Comment: 31 pages, 5 figures

Prior coarticulation studies focus mainly on limited phonemic sequences and specific articulators, providing only approximate descriptions of the temporal extent and magnitude of coarticulation. This paper is an initial attempt to comprehensively investigate coarticulation. We leverage existing Electromagnetic Articulography (EMA) datasets to develop and train a phoneme-to-articulatory (P2A) model that can generate realistic EMA for novel phoneme sequences and replicate known coarticulation patterns. We use model-generated EMA on 9K minimal word pairs to analyze coarticulation magnitude and extent up to eight phonemes from the coarticulation trigger, and compare coarticulation resistance across different consonants. Our findings align with earlier studies and suggest a longer-range coarticulation effect than previously found. This model-based approach can potentially compare coarticulation between adults and children and across languages, offering new insights into speech production., Comment: To be published in Interspeech 2024

The coherent control of wave absorption has important applications in areas such as energy harvesting, imaging, and sensing. However, most practical scenarios involve the absorption of partially coherent rather than fully coherent waves. Here we present a systematic theory of unitary control over the absorption of partially coherent waves by linear systems. Given an absorbing system and incident partially coherent wave, we provide analytical expressions for the range of attainable absorptivity under arbitrary unitary transformations of the incident field. We also present an explicit algorithm to construct the unitary control scheme that achieves any desired absorptivity within that attainable range. As applications of our theory, we derive the conditions required for achieving two new phenomena - partially coherent perfect absorption and partially coherent zero absorption. Furthermore, we prove a theorem relating the coherence properties of the incident field, as quantified by majorization, to the resulting absorption intervals. Our results provide both fundamental insights and practical prescriptions for exploiting unitary control to shape the absorption of partially coherent waves. The theory applies across the electromagnetic spectrum as well as to other classical wave systems such as acoustic waves., Comment: 26 pages, 4 figures

Controlling wave transmission is crucial for various applications. In this work, we apply the concept of unitary control to manipulate multiport wave transmission. Unitary control aims to control the behaviors of a set of orthogonal waves simultaneously. The approach fully harnesses the capability of wavefront shaping techniques, with promising applications in communication, imaging, and photonic integrated circuits. Here we present a detailed theory of unitary control of wave transmission, focusing on two key characteristics: total (power) transmittance and direct (field) transmission. The total transmittance for an input port represents the fraction of total transmitted power with respect to the input power for wave incident from an input port. The direct transmission for an input port denotes the complex transmission amplitude from that input port to its corresponding output port. We address two main questions: (i) the achievable total transmittance and direct transmission for each port, and (ii) the configuration of unitary control to attain desired transmission values for each port. Our theory illustrates that unitary control enables uniform total transmittance and direct transmission across any medium. Furthermore, we show that reciprocity and energy conservation enforce direct symmetry constraints on wave transmission in both forward and backward directions under unitary control., Comment: 29 pages, 3 figures

Let $G$ be a graph. For $x\in V(G)$, let $N(x)=\{y\in V(G)\colon xy\in E(G)\}$. The minimum common degree of $G$, denoted by $\delta_{2}(G)$, is defined as the minimum of $|N(x)\cap N(y)|$ over all non-edges $xy$ of $G$. In 1982, H\"{a}ggkvist showed that every triangle-free graph with minimum degree greater than $\lfloor\frac{3n}{8}\rfloor$ is homomorphic to a cycle of length 5. In this paper, we prove that every triangle-free graph with minimum common degree greater than $\lfloor\frac{n}{8}\rfloor$ is homomorphic to a cycle of length 5, which implies H\"{a}ggkvist's result. The balanced blow-up of the M\"{o}bius ladder graph shows that it is best possible., Comment: 11 pages, 9 figures

As Artificial Intelligence Generated Content (AIGC) advances, a variety of methods have been developed to generate text, images, videos, and 3D objects from single or multimodal inputs, contributing efforts to emulate human-like cognitive content creation. However, generating realistic large-scale scenes from a single input presents a challenge due to the complexities involved in ensuring consistency across extrapolated views generated by models. Benefiting from recent video generation models and implicit neural representations, we propose Scene123, a 3D scene generation model, that not only ensures realism and diversity through the video generation framework but also uses implicit neural fields combined with Masked Autoencoders (MAE) to effectively ensures the consistency of unseen areas across views. Specifically, we initially warp the input image (or an image generated from text) to simulate adjacent views, filling the invisible areas with the MAE model. However, these filled images usually fail to maintain view consistency, thus we utilize the produced views to optimize a neural radiance field, enhancing geometric consistency. Moreover, to further enhance the details and texture fidelity of generated views, we employ a GAN-based Loss against images derived from the input image through the video generation model. Extensive experiments demonstrate that our method can generate realistic and consistent scenes from a single prompt. Both qualitative and quantitative results indicate that our approach surpasses existing state-of-the-art methods. We show encourage video examples at https://yiyingyang12.github.io/Scene123.github.io/., Comment: arXiv admin note: text overlap with arXiv:2305.11588 by other authors

We investigate the majorization order for comparing wave coherence and reveal its fundamental consequences in transport measurements, including power distribution, absorption, transmission, and reflection. We prove that all these measurements preserve the majorization order under unitary control, enabling direct experimental characterization of the majorization order. Specifically, waves with lower coherence in the majorization order exhibit more restricted ranges of achievable measurement values. Our results deepen the understanding of coherence in transport phenomena., Comment: 11 pages, 3 figures

Laryngo-pharyngeal cancer (LPC) is a highly fatal malignant disease affecting the head and neck region. Previous studies on endoscopic tumor detection, particularly those leveraging dual-branch network architectures, have shown significant advancements in tumor detection. These studies highlight the potential of dual-branch networks in improving diagnostic accuracy by effectively integrating global and local (lesion) feature extraction. However, they are still limited in their capabilities to accurately locate the lesion region and capture the discriminative feature information between the global and local branches. To address these issues, we propose a novel SAM-guided fusion network (SAM-FNet), a dual-branch network for laryngo-pharyngeal tumor detection. By leveraging the powerful object segmentation capabilities of the Segment Anything Model (SAM), we introduce the SAM into the SAM-FNet to accurately segment the lesion region. Furthermore, we propose a GAN-like feature optimization (GFO) module to capture the discriminative features between the global and local branches, enhancing the fusion feature complementarity. Additionally, we collect two LPC datasets from the First Affiliated Hospital (FAHSYSU) and the Sixth Affiliated Hospital (SAHSYSU) of Sun Yat-sen University. The FAHSYSU dataset is used as the internal dataset for training the model, while the SAHSYSU dataset is used as the external dataset for evaluating the model's performance. Extensive experiments on both datasets of FAHSYSU and SAHSYSU demonstrate that the SAM-FNet can achieve competitive results, outperforming the state-of-the-art counterparts. The source code of SAM-FNet is available at the URL of https://github.com/VVJia/SAM-FNet.

A physics-informed neural network (PINN) is used to produce a variety of self-trapped necklace solutions of the (2+1)-dimensional nonlinear Schr\"{o}dinger/Gross-Pitaevskii equation. We elaborate the analysis for the existence and evolution of necklace patterns with integer, half-integer, and fractional reduced orbital angular momenta by means of PINN. The patterns exhibit phenomena similar to rotation of rigid bodies and centrifugal force. Even though the necklaces slowly expand (or shrink), they preserve their structure in the course of the quasi-stable propagation over several diffraction lengths, which is completely different from the ordinary fast diffraction-dominated dynamics. By comparing different ingredients, including the training time, loss value and $\mathbb{L}_{2}$ error, PINN accurately predicts specific nonlinear dynamical properties of the evolving necklace patterns. Furthermore, we perform the data-driven discovery of parameters for both clean and perturbed training data, adding $1\%$ random noise in the latter case. The results reveal that PINN not only effectively emulates the solution of partial differential equations, but also offers applications for predicting the nonlinear dynamics of physically relevant types of patterns., Comment: 19 pages, 9 figures, to be published in Optics Express

With the support of Virtual Reality (VR) and Augmented Reality (AR) technologies, the 3D virtual eyeglasses try-on application is well on its way to becoming a new trending solution that offers a "try on" option to select the perfect pair of eyeglasses at the comfort of your own home. Reconstructing eyeglasses frames from a single image with traditional depth and image-based methods is extremely difficult due to their unique characteristics such as lack of sufficient texture features, thin elements, and severe self-occlusions. In this paper, we propose the first mesh deformation-based reconstruction framework for recovering high-precision 3D full-frame eyeglasses models from a single RGB image, leveraging prior and domain-specific knowledge. Specifically, based on the construction of a synthetic eyeglasses frame dataset, we first define a class-specific eyeglasses frame template with pre-defined keypoints. Then, given an input eyeglasses frame image with thin structure and few texture features, we design a keypoint detector and refiner to detect predefined keypoints in a coarse-to-fine manner to estimate the camera pose accurately. After that, using differentiable rendering, we propose a novel optimization approach for producing correct geometry by progressively performing free-form deformation (FFD) on the template mesh. We define a series of loss functions to enforce consistency between the rendered result and the corresponding RGB input, utilizing constraints from inherent structure, silhouettes, keypoints, per-pixel shading information, and so on. Experimental results on both the synthetic dataset and real images demonstrate the effectiveness of the proposed algorithm.

The decays of the $\chi_{b1}(1P)$, $\chi_{b2}(1P)$, $\chi_{b1}(2P)$ and $\chi_{b2}(2P)$~mesons into the~$\Upsilon(1S)\mu^+\mu^-$ final state are observed with a high significance using proton-proton collision data collected with the LHCb detector and corresponding to an integrated luminosity of 9fb$^{-1}$. The newly observed decays together with the $\Upsilon(2S)\rightarrow \Upsilon(1S)\pi^+\pi^-$ and $\Upsilon(3S)\rightarrow \Upsilon(2S)\pi^+\pi^-$ decay modes are used for precision measurements of the mass and mass splittings for the hidden-beauty states., Comment: All figures and tables, along with any supplementary material and additional information, are available at https://cern.ch/lhcbproject/Publications/p/LHCb-PAPER-2024-025.html

Translating users' natural language queries (NL) into SQL queries (i.e., NL2SQL) can significantly reduce barriers to accessing relational databases and support various commercial applications. The performance of NL2SQL has been greatly enhanced with the emergence of Large Language Models (LLMs). In this survey, we provide a comprehensive review of NL2SQL techniques powered by LLMs, covering its entire lifecycle from the following four aspects: (1) Model: NL2SQL translation techniques that tackle not only NL ambiguity and under-specification, but also properly map NL with database schema and instances; (2) Data: From the collection of training data, data synthesis due to training data scarcity, to NL2SQL benchmarks; (3) Evaluation: Evaluating NL2SQL methods from multiple angles using different metrics and granularities; and (4) Error Analysis: analyzing NL2SQL errors to find the root cause and guiding NL2SQL models to evolve. Moreover, we provide a rule of thumb for developing NL2SQL solutions. Finally, we discuss the research challenges and open problems of NL2SQL in the LLMs era.

Recent advances in video compression have seen significant coding performance improvements with the development of new standards and learning-based video codecs. However, most of these works focus on application scenarios that allow a certain amount of system delay (e.g., Random Access mode in MPEG codecs), which is not always acceptable for live delivery. This paper conducts a comparative study of state-of-the-art conventional and learned video coding methods based on a low delay configuration. Specifically, this study includes two MPEG standard codecs (H.266/VVC VTM and JVET ECM), two AOM codecs (AV1 libaom and AVM), and two recent neural video coding models (DCVC-DC and DCVC-FM). To allow a fair and meaningful comparison, the evaluation was performed on test sequences defined in the AOM and MPEG common test conditions in the YCbCr 4:2:0 color space. The evaluation results show that the JVET ECM codecs offer the best overall coding performance among all codecs tested, with a 16.1% (based on PSNR) average BD-rate saving over AOM AVM, and 11.0% over DCVC-FM. We also observed inconsistent performance with the learned video codecs, DCVC-DC and DCVC-FM, for test content with large background motions.

Bacterial second messengers are crucial for transmitting environmental information to cellular responses. However, quantifying their information transmission capacity remains challenging. Here, we engineer an isolated cAMP signaling channel in Pseudomonas aeruginosa using targeted gene knockouts, optogenetics, and a fluorescent cAMP probe. This design allows precise optical control and real-time monitoring of cAMP dynamics. By integrating experimental data with information theory, we reveal an optimal frequency for light-mediated cAMP signaling that maximizes information transmission, reaching about 40 bits/h. This rate correlates strongly with cAMP degradation kinetics and employs a two-state encoding scheme. Our findings suggest a mechanism for fine-tuned regulation of multiple genes through temporal encoding of second messenger signals, providing new insights into bacterial adaptation strategies. This approach offers a framework for quantifying information processing in cellular signaling systems., Comment: 33 pages, 4 figures

With the increasing demand for practical applications of Large Language Models (LLMs), many attention-efficient models have been developed to balance performance and computational cost. However, the adversarial robustness of these models remains under-explored. In this work, we design a framework to investigate the trade-off between efficiency, performance, and adversarial robustness of LLMs by comparing three prominent models with varying levels of complexity and efficiency -- Transformer++, Gated Linear Attention (GLA) Transformer, and MatMul-Free LM -- utilizing the GLUE and AdvGLUE datasets. The AdvGLUE dataset extends the GLUE dataset with adversarial samples designed to challenge model robustness. Our results show that while the GLA Transformer and MatMul-Free LM achieve slightly lower accuracy on GLUE tasks, they demonstrate higher efficiency and either superior or comparative robustness on AdvGLUE tasks compared to Transformer++ across different attack levels. These findings highlight the potential of simplified architectures to achieve a compelling balance between efficiency, performance, and adversarial robustness, offering valuable insights for applications where resource constraints and resilience to adversarial attacks are critical.

Multi-objective evolutionary algorithms (MOEAs) have emerged as powerful tools for solving complex optimization problems characterized by multiple, often conflicting, objectives. While advancements have been made in computational efficiency as well as diversity and convergence of solutions, a critical challenge persists: the internal evolutionary mechanisms are opaque to human users. Drawing upon the successes of explainable AI in explaining complex algorithms and models, we argue that the need to understand the underlying evolutionary operators and population dynamics within MOEAs aligns well with a visual analytics paradigm. This paper introduces ParetoTracker, a visual analytics framework designed to support the comprehension and inspection of population dynamics in the evolutionary processes of MOEAs. Informed by preliminary literature review and expert interviews, the framework establishes a multi-level analysis scheme, which caters to user engagement and exploration ranging from examining overall trends in performance metrics to conducting fine-grained inspections of evolutionary operations. In contrast to conventional practices that require manual plotting of solutions for each generation, ParetoTracker facilitates the examination of temporal trends and dynamics across consecutive generations in an integrated visual interface. The effectiveness of the framework is demonstrated through case studies and expert interviews focused on widely adopted benchmark optimization problems., Comment: Accepted by IEEE VIS 2024 (will appear in IEEE TVCG)

Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether hybrid RL can improve upon the existing lower bounds established in purely offline and purely online RL without relying on the single-policy concentrability assumption. While Li et al. (2023) provided an affirmative answer to this question in the tabular PAC RL case, the question remains unsettled for both the regret-minimizing RL case and the non-tabular case. In this work, building upon recent advancements in offline RL and reward-agnostic exploration, we develop computationally efficient algorithms for both PAC and regret-minimizing RL with linear function approximation, without single-policy concentrability. We demonstrate that these algorithms achieve sharper error or regret bounds that are no worse than, and can improve on, the optimal sample complexity in offline RL (the first algorithm, for PAC RL) and online RL (the second algorithm, for regret-minimizing RL) in linear Markov decision processes (MDPs), regardless of the quality of the behavior policy. To our knowledge, this work establishes the tightest theoretical guarantees currently available for hybrid RL in linear MDPs.

The branching fraction of $D^+\to K_{S}^{0} \pi^{0}e^+\nu_e$ is measured for the first time using $7.93~\mathrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected at the center-of-mass energy $\sqrt{s}=3.773$~GeV with the BESIII detector operating at the BEPCII collider, and is determined to be ${\mathcal B}$($D^+\to K_S^0\pi^0e^+\nu_e$) = $(0.881~\pm~0.017_{\rm stat.}~\pm~0.016_{\rm syst.})$\%. Based on an analysis of the $D^+\to K_S^0\pi^0e^+\nu_e$ decay dynamics, we observe the $S\text{-}{\rm wave}$ and $P$-wave components with fractions of $f_{S\text{-}{\rm wave}}$ = $(6.13~\pm~0.27_{\rm stat.}~\pm ~0.30_{\rm syst.})\%$ and $f_{\bar K^{*}(892)^0}$ = $(93.88~\pm~0.27_{\rm stat.}~\pm~0.29_{\rm syst.})$\%, respectively. From these results, we obtain the branching fractions ${\mathcal B}$($D^+\to (K_S^0\pi^0)_{S\text{-}{\rm wave}}~e^+\nu_e$) = $(5.41~\pm~0.35_{\rm stat.}~\pm~0.37_{\rm syst.})\times10^{-4}$ and ${\mathcal B}$($D^+\to \bar K^{*}(892)^0e^+\nu_e$) = $(4.97~\pm~0.11_{\rm stat.}~\pm~0.12_{\rm syst.})$\%. In addition, the hadronic form-factor ratios of $D^{+} \to \bar {K}^{*}(892)^0e^+\nu_e$ at $q^2=0$, assuming a single-pole dominance parameterization, are determined to be $r_V=\frac{V(0)}{A_1(0)}= 1.43~\pm~0.07_{\rm stat.}~\pm~0.03_{\rm syst.}$ and $r_2=\frac{A_2(0)}{A_1(0)}=0.72~\pm~0.06_{\rm stat.}~\pm~0.02_{\rm syst.}$.

Slow task detection is a critical problem in cloud operation and maintenance since it is highly related to user experience and can bring substantial liquidated damages. Most anomaly detection methods detect it from a single-task aspect. However, considering millions of concurrent tasks in large-scale cloud computing clusters, it becomes impractical and inefficient. Moreover, single-task slowdowns are very common and do not necessarily indicate a malfunction of a cluster due to its violent fluctuation nature in a virtual environment. Thus, we shift our attention to cluster-wide task slowdowns by utilizing the duration time distribution of tasks across a cluster, so that the computation complexity is not relevant to the number of tasks. The task duration time distribution often exhibits compound periodicity and local exceptional fluctuations over time. Though transformer-based methods are one of the most powerful methods to capture these time series normal variation patterns, we empirically find and theoretically explain the flaw of the standard attention mechanism in reconstructing subperiods with low amplitude when dealing with compound periodicity. To tackle these challenges, we propose SORN (i.e., Skimming Off subperiods in descending amplitude order and Reconstructing Non-slowing fluctuation), which consists of a Skimming Attention mechanism to reconstruct the compound periodicity and a Neural Optimal Transport module to distinguish cluster-wide slowdowns from other exceptional fluctuations. Furthermore, since anomalies in the training set are inevitable in a practical scenario, we propose a picky loss function, which adaptively assigns higher weights to reliable time slots in the training set. Extensive experiments demonstrate that SORN outperforms state-of-the-art methods on multiple real-world industrial datasets., Comment: This paper has been accepted by KDD2024

AI assistants are being increasingly used by students enrolled in higher education institutions. While these tools provide opportunities for improved teaching and education, they also pose significant challenges for assessment and learning outcomes. We conceptualize these challenges through the lens of vulnerability, the potential for university assessments and learning outcomes to be impacted by student use of generative AI. We investigate the potential scale of this vulnerability by measuring the degree to which AI assistants can complete assessment questions in standard university-level STEM courses. Specifically, we compile a novel dataset of textual assessment questions from 50 courses at EPFL and evaluate whether two AI assistants, GPT-3.5 and GPT-4 can adequately answer these questions. We use eight prompting strategies to produce responses and find that GPT-4 answers an average of 65.8% of questions correctly, and can even produce the correct answer across at least one prompting strategy for 85.1% of questions. When grouping courses in our dataset by degree program, these systems already pass non-project assessments of large numbers of core courses in various degree programs, posing risks to higher education accreditation that will be amplified as these models improve. Our results call for revising program-level assessment design in higher education in light of advances in generative AI., Comment: 20 pages, 8 figures

Microwave-optics entanglement plays a crucial role in building hybrid quantum networks with quantum nodes working in the microwave and optical frequency bands. However, there are limited efficient ways to produce such entanglement due to the large frequency mismatch between the two regimes. Here, we present a new mechanism to prepare microwave-optics entanglement based on a hybrid system of two coupled opto- and magnomechanical microspheres, i.e., a YIG sphere and a silica sphere. The YIG sphere holds a magnon mode and a vibration mode induced by magnetostriction, while the silica sphere supports an optical whispering-gallery mode and a mechanical mode coupled via an optomechanical interaction. The two mechanical modes are close in frequency and directly coupled via physical contact of the two microspheres. We show that by simultaneously activating the magnomechanical (optomechanical) Stokes (anti-Stokes) scattering, stationary entanglement can be established between the magnon and optical modes via mechanics-mechanics coupling. This leads to stationary microwave-optics entanglement by further coupling the YIG sphere to a microwave cavity and utilizing the magnon-microwave state swapping. Our protocol is within reach of current technology and may become a promising new approach for preparing microwave-optics entanglement, which finds unique applications in hybrid quantum networks and quantum information processing with hybrid quantum systems.

The doping evolution behaviors of the normal state magnetic excitations (MEs) of the nickelate La3Ni2O7 are theoretically studied in this paper. For a filling of n = 3.0 which corresponds roughly to the material which realizes the superconductivity of about 80 K under moderately high pressures above 14 GPa, the MEs exhibit a square-like pattern centered at (0,0) which originates from the intrapocket particle-hole scatterings. Furthermore, it was found that the MEs show very strong modulations on the interlayer momentum qz. With the increasing of qz, the patterns of the MEs change dramatically. In the large qz regime, they turn to be ruled by the interpocket excitation modes with significantly larger intensity which may play a vital role in the superconducting pairing. This hidden feature of the MEs was not revealed by previous studies. The established features of the MEs are found to be very robust against doping. They persist in the wide hole- or electron-doping regime around n = 3.0. However, in the heavily electron-doped regime, a Lifshitz transition will occur. Consequently, the behaviors of the MEs change qualitatively across this transition. With the absence of the hole pocket, we predict that a strong tendency toward the spin-density-wave (SDW) order will develop due to the perfect nesting between the electron and the hole pockets at n = 4.0. Thus, we have investigated the normal state behaviors of the MEs and their doping evolutions which may shed light on the mechanism of superconductivity in pressurized La3Ni2O7., Comment: 9 pages, 9 figures

Underwater litter is widely spread across aquatic environments such as lakes, rivers, and oceans, significantly impacting natural ecosystems. Current monitoring technologies for detecting underwater litter face limitations in survey efficiency, cost, and environmental conditions, highlighting the need for efficient, consumer-grade technologies for automatic detection. This research introduces the Aerial-Aquatic Speedy Scanner (AASS) combined with Super-Resolution Reconstruction (SRR) and an improved YOLOv8 detection network. AASS enhances data acquisition efficiency over traditional methods, capturing high-quality images that accurately identify underwater waste. SRR improves image-resolution by mitigating motion blur and insufficient resolution, thereby enhancing detection tasks. Specifically, the RCAN model achieved the highest mean average precision (mAP) of 78.6% for detection accuracy on reconstructed images among the tested SRR models. With a magnification factor of 4, the SRR test set shows an improved mAP compared to the conventional bicubic set. These results demonstrate the effectiveness of the proposed method in detecting underwater litter., Comment: The earlier version of this conference paper was accepted at OCEANS 2024-Halifax, Canada and was selected for inclusion in the Student Poster Competition (SPC) Program

Hermit crabs play a crucial role in coastal ecosystems by dispersing seeds, cleaning up debris, and disturbing soil. They serve as vital indicators of marine environmental health, responding to climate change and pollution. Traditional survey methods, like quadrat sampling, are labor-intensive, time-consuming, and environmentally dependent. This study presents an innovative approach combining UAV-based remote sensing with Super-Resolution Reconstruction (SRR) and the CRAB-YOLO detection network, a modification of YOLOv8s, to monitor hermit crabs. SRR enhances image quality by addressing issues such as motion blur and insufficient resolution, significantly improving detection accuracy over conventional low-resolution fuzzy images. The CRAB-YOLO network integrates three improvements for detection accuracy, hermit crab characteristics, and computational efficiency, achieving state-of-the-art (SOTA) performance compared to other mainstream detection models. The RDN networks demonstrated the best image reconstruction performance, and CRAB-YOLO achieved a mean average precision (mAP) of 69.5% on the SRR test set, a 40% improvement over the conventional Bicubic method with a magnification factor of 4. These results indicate that the proposed method is effective in detecting hermit crabs, offering a cost-effective and automated solution for extensive hermit crab monitoring, thereby aiding coastal benthos conservation., Comment: The earlier version of this conference paper was presented at OCEANS 2024-Singapore and was selected for inclusion in the Student Poster Competition (SPC) Program

Multilingual large language models (MLLMs) struggle to answer questions posed in non-dominant languages, even though they have acquired the relevant knowledge from their dominant language corpus. In contrast, human multilinguals can overcome such non-native language context limitations through Positive Native Language Transfer (PNLT). Inspired by the process of PNLT, we analogize the dominant language of MLLMs to the native language of human multilinguals, and propose Native Language Prompting (NatLan) to simulate the PNLT observed in human multilinguals. It explicitly creates native language contexts for MLLMs to facilitate the elicitation of the rich native language knowledge during question-answering, unlocking the limitations imposed by non-native language contexts. By employing multi-MLLM collaboration, NatLan reduces the workload on each MLLM in simulating PNLT and refines semantic transfer. On the C-Eval benchmark, NatLan provides up to a 10.1% average accuracy improvement and up to a 5.0% increase in the hard-level subset across five MLLMs, surpassing all top-notch related methods. Our code is available at https://github.com/AnonyNLP/NatLan.