Search

Investigating the signals of dark matter annihilation is one of the most popular ways to understand the nature of dark matter. In particular, many recent studies are focussing on using radio data to examine the possible signals of dark matter revealed in galaxies and galaxy clusters. In this article, we investigate on the spectral data of the central radio halo of the cool-core cluster RX J1720.1+2638. We show that the radio spectral data can be best accounted by the synchrotron emission due to dark matter annihilation via $\tau$ lepton channel (with dark matter mass $m=15$ GeV) or $b$ quark channel (with dark matter mass $m=110$ GeV), although using the very coarse spectral data with notable errors. Despite the fact that cosmic-ray emission can also provide a good explanation for the observed radio spectrum, our results suggest a possible positive evidence for dark matter annihilation revealed in the form of radio emission in RX J1720.1+2638 cluster., Comment: Accepted in MNRAS

Let $d\geq1$, $\Omega$ be a bounded domain of a smooth complete Riemannian d-manifold M, and $\mu$ be a positive finite Borel measure with compact support in $\overline{\Omega}$. We prove the Courant nodal domain theorem for the eigenfunctions of Kre\u{i}n-Feller operator $\Delta_{\mu}$ under the assumption that such eigenfunctions are continuous on $\overline{\Omega}$. For $d\geq2$, We prove that on a bounded domain $\Omega\subset M$ with smooth boundary and on which the Green's function of the Laplace-Beltrami operator exists, the eigenfunctions of $\Delta_{\mu}$ are continuous on $\Omega$. We also prove that if M is compact and $\partial M=\emptyset$, then the eigenfuctions of $\Delta_{\mu}$ are continuous on M.

Finding optimal solutions to combinatorial optimization problems is pivotal in both scientific and technological domains, within academic research and industrial applications. A considerable amount of effort has been invested in the development of accelerated methods that leverage sophisticated models and harness the power of advanced computational hardware. Despite the advancements, a critical challenge persists, the dual demand for both high efficiency and broad generality in solving problems. In this work, we propose a general method, Free-Energy Machine (FEM), based on the ideas of free-energy minimization in statistical physics, combined with automatic differentiation and gradient-based optimization in machine learning. The algorithm is flexible, solving various combinatorial optimization problems using a unified framework, and is efficient, naturally utilizing massive parallel computational devices such as graph processing units (GPUs) and field-programmable gate arrays (FPGAs). We benchmark our algorithm on various problems including the maximum cut problems, balanced minimum cut problems, and maximum $k$-satisfiability problems, scaled to millions of variables, across both synthetic, real-world, and competition problem instances. The findings indicate that our algorithm not only exhibits exceptional speed but also surpasses the performance of state-of-the-art algorithms tailored for individual problems. This highlights that the interdisciplinary fusion of statistical physics and machine learning opens the door to delivering cutting-edge methodologies that will have broad implications across various scientific and industrial landscapes., Comment: Comments are welcome!

Reconstructing desired objects and scenes has long been a primary goal in 3D computer vision. Single-view point cloud reconstruction has become a popular technique due to its low cost and accurate results. However, single-view reconstruction methods often rely on expensive CAD models and complex geometric priors. Effectively utilizing prior knowledge about the data remains a challenge. In this paper, we introduce hyperbolic space to 3D point cloud reconstruction, enabling the model to represent and understand complex hierarchical structures in point clouds with low distortion. We build upon previous methods by proposing a hyperbolic Chamfer distance and a regularized triplet loss to enhance the relationship between partial and complete point clouds. Additionally, we design adaptive boundary conditions to improve the model's understanding and reconstruction of 3D structures. Our model outperforms most existing models, and ablation studies demonstrate the significance of our model and its components. Experimental results show that our method significantly improves feature extraction capabilities. Our model achieves outstanding performance in 3D reconstruction tasks., Comment: Accepted by AAAI25

Deep-learning based traffic prediction models require vast amounts of data to learn embedded spatial and temporal dependencies. The inherent privacy and commercial sensitivity of such data has encouraged a shift towards decentralised data-driven methods, such as Federated Learning (FL). Under a traditional Machine Learning paradigm, traffic flow prediction models can capture spatial and temporal relationships within centralised data. In reality, traffic data is likely distributed across separate data silos owned by multiple stakeholders. In this work, a cross-silo FL setting is motivated to facilitate stakeholder collaboration for optimal traffic flow prediction applications. This work introduces an FL framework, referred to as FedTPS, to generate synthetic data to augment each client's local dataset by training a diffusion-based trajectory generation model through FL. The proposed framework is evaluated on a large-scale real world ride-sharing dataset using various FL methods and Traffic Flow Prediction models, including a novel prediction model we introduce, which leverages Temporal and Graph Attention mechanisms to learn the Spatio-Temporal dependencies embedded within regional traffic flow data. Experimental results show that FedTPS outperforms multiple other FL baselines with respect to global model performance., Comment: 11 pages, 7 figures, 6 tables, ACM format

The process of galaxy cluster formation likely leaves an imprint on the properties of its individual member galaxies. Understanding this process is essential for uncovering the evolutionary connections between galaxies and cosmic structures. Here we study a sample of ten protoclusters at z~2-3 in different dynamical states that we estimate based on spectroscopic data of their members. We combine the dynamical information with HST imaging to measure galaxy sizes and pair fractions. Our analysis reveals a clear anti-correlation between the velocity dispersion of the protocluster and its galaxy pair fractions (indicative of merger rates). The velocity dispersion also anti-correlates with the dispersion in size among of the member galaxies. These correlations may be explained by protoclusters in colder dynamical states maintaining a velocity dispersion and galaxy number density that boosts galaxy mergers, which in turn contributes to the structural expansion and compaction of galaxies. Our findings offer constraints for cosmological models regarding the evolution of galaxy morphology across different stages in the assembly of protoclusters., Comment: 11 pages, 8 figures, 1 table. Accepted for publication in MNRAS

Document content extraction is crucial in computer vision, especially for meeting the high-quality data needs of large language models (LLMs) and retrieval-augmented generation (RAG) technologies. However, current document parsing methods suffer from significant limitations in terms of diversity and comprehensive evaluation. To address these challenges, we introduce OmniDocBench, a novel multi-source benchmark designed to advance automated document content extraction. OmniDocBench includes a meticulously curated and annotated high-quality evaluation dataset comprising nine diverse document types, such as academic papers, textbooks, slides, among others. Our benchmark provides a flexible and comprehensive evaluation framework with 19 layout category labels and 14 attribute labels, enabling multi-level assessments across entire datasets, individual modules, or specific data types. Using OmniDocBench, we perform an exhaustive comparative analysis of existing modular pipelines and multimodal end-to-end methods, highlighting their limitations in handling document diversity and ensuring fair evaluation. OmniDocBench establishes a robust, diverse, and fair evaluation standard for the document content extraction field, offering crucial insights for future advancements and fostering the development of document parsing technologies. The codes and dataset is available in https://github.com/opendatalab/OmniDocBench.

Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs should be well-suited for processing them. However, when applying SNNs to point clouds, they often exhibit limited performance and fewer application scenarios. We attribute this to inappropriate preprocessing and feature extraction methods. To address this issue, we first introduce the Spike Voxel Coding (SVC) scheme, which encodes the 3D point clouds into a sparse spike train space, reducing the storage requirements and saving time on point cloud preprocessing. Then, we propose a Spike Sparse Convolution (SSC) model for efficiently extracting 3D sparse point cloud features. Combining SVC and SSC, we design an efficient 3D SNN backbone (E-3DSNN), which is friendly with neuromorphic hardware. For instance, SSC can be implemented on neuromorphic chips with only minor modifications to the addressing function of vanilla spike convolution. Experiments on ModelNet40, KITTI, and Semantic KITTI datasets demonstrate that E-3DSNN achieves state-of-the-art (SOTA) results with remarkable efficiency. Notably, our E-3DSNN (1.87M) obtained 91.7\% top-1 accuracy on ModelNet40, surpassing the current best SNN baselines (14.3M) by 3.0\%. To our best knowledge, it is the first direct training 3D SNN backbone that can simultaneously handle various 3D computer vision tasks (e.g., classification, detection, and segmentation) with an event-driven nature. Code is available: https://github.com/bollossom/E-3DSNN/., Comment: Accepted by AAAI 2025

Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions face an inherent tradeoff between noise reduction and motion blur. While short exposures can capture clear motion, they suffer from noise amplification. Long exposures reduce noise but introduce blur. Learning-based single-image enhancers tend to be over-smooth due to the limited information. Multi-image solutions using burst mode avoid this tradeoff by capturing more spatial-temporal information but often struggle with misalignment from camera/scene motion. To address these limitations, we propose a physical-model-based image restoration approach leveraging a novel dual-exposure Quad-Bayer pattern sensor. By capturing pairs of short and long exposures at the same starting point but with varying durations, this method integrates complementary noise-blur information within a single image. We further introduce a Quad-Bayer synthesis method (B2QB) to simulate sensor data from Bayer patterns to facilitate training. Based on this dual-exposure sensor model, we design a hierarchical convolutional neural network called QRNet to recover high-quality RGB images. The network incorporates input enhancement blocks and multi-level feature extraction to improve restoration quality. Experiments demonstrate superior performance over state-of-the-art deblurring and denoising methods on both synthetic and real-world datasets. The code, model, and datasets are publicly available at https://github.com/zhaoyuzhi/QRNet., Comment: accepted by IEEE Transactions on Image Processing (TIP)

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently; however, MoE systems rely on heterogeneous compute and memory resources. These factors collectively influence the system's Cost, Accuracy, and Performance (CAP), creating a challenging trade-off. Current benchmarks often fail to provide precise estimates of these effects, complicating practical considerations for deploying MoE systems. To bridge this gap, we introduce MoE-CAP, a benchmark specifically designed to evaluate MoE systems. Our findings highlight the difficulty of achieving an optimal balance of cost, accuracy, and performance with existing hardware capabilities. MoE systems often necessitate compromises on one factor to optimize the other two, a dynamic we term the MoE-CAP trade-off. To identify the best trade-off, we propose novel performance evaluation metrics - Sparse Memory Bandwidth Utilization (S-MBU) and Sparse Model FLOPS Utilization (S-MFU) - and develop cost models that account for the heterogeneous compute and memory hardware integral to MoE systems. This benchmark is publicly available on HuggingFace: https://huggingface.co/spaces/sparse-generative-ai/open-moe-llm-leaderboard.

Using data from the LAMOST Medium-Resolution Spectroscopic Survey of Nebulae, we create a sample of 17,821 diffuse ionized gas (DIG) spectra in the anti-center region of the Milky Way, by excluding fibers in the directions of H II regions and supernova remnants. We then analyze the radial and vertical distributions of three line ratios ([N II]/H$\alpha$, [S II]/H$\alpha$, and [S II]/[N II]), as well as the oxygen abundance. [N II]/H$\alpha$ and [S II]/H$\alpha$ do not exhibit a consistent, monotonic decrease with increasing Galactocentric distance (R$_{gal}$). Instead, they show enhancement within the interarm region, positioned between the Local Arm and the Perseus Arm. [S II]/[N II] has a radial gradient of 0.1415 $\pm$ 0.0646 kpc$^{-1}$ for the inner disk (8.34 $ < R_{gal} < $ 9.65 kpc), and remains nearly flat for the outer disk ($R_{gal} > $ 9.65 kpc). In the vertical direction, [N II]/H$\alpha$, [S II]/H$\alpha$, and [S II]/[N II] increase with increasing Galactic disk height ($|z|$) in both southern and northern disks. Based on the N2S2H$\alpha$ method, which combines [S II]/[N II] and [N II]/H$\alpha$, we estimate the oxygen abundance. The oxygen abundance exhibits a consistent radial gradient with R$_{gal}$, featuring a slope of -0.0559 $\pm$ 0.0209 dex kpc$^{-1}$ for the inner disk and a similar slope of -0.0429 $\pm$ 0.0599 dex kpc$^{-1}$ for the outer disk. A single linear fitting to the entire disk yields a slope of -0.0317 $\pm$ 0.0124 dex kpc$^{-1}$. In the vertical direction, the oxygen abundance decreases with increasing $|z|$ in both southern and northern disks.

Memecoins, driven by social media engagement and cultural narratives, have rapidly grown within the Web3 ecosystem. Unlike traditional cryptocurrencies, they are shaped by humor, memes, and community sentiment. This paper introduces the Coin-Meme dataset, an open-source collection of visual, textual, community, and financial data from the Pump.fun platform on the Solana blockchain. We also propose a multimodal framework to analyze memecoins, uncovering patterns in cultural themes, community interaction, and financial behavior. Through clustering, sentiment analysis, and word cloud visualizations, we identify distinct thematic groups centered on humor, animals, and political satire. Additionally, we provide financial insights by analyzing metrics such as Market Entry Time and Market Capitalization, offering a comprehensive view of memecoins as both cultural artifacts and financial instruments within Web3. The Coin-Meme dataset is publicly available at https://github.com/hwlongCUHK/Coin-Meme.git., Comment: 4 pages, 2 figures, conference

Recent advances in diffusion models have revolutionized 2D and 3D content creation, yet generating photorealistic dynamic 4D scenes remains a significant challenge. Existing dynamic 4D generation methods typically rely on distilling knowledge from pre-trained 3D generative models, often fine-tuned on synthetic object datasets. Consequently, the resulting scenes tend to be object-centric and lack photorealism. While text-to-video models can generate more realistic scenes with motion, they often struggle with spatial understanding and provide limited control over camera viewpoints during rendering. To address these limitations, we present PaintScene4D, a novel text-to-4D scene generation framework that departs from conventional multi-view generative models in favor of a streamlined architecture that harnesses video generative models trained on diverse real-world datasets. Our method first generates a reference video using a video generation model, and then employs a strategic camera array selection for rendering. We apply a progressive warping and inpainting technique to ensure both spatial and temporal consistency across multiple viewpoints. Finally, we optimize multi-view images using a dynamic renderer, enabling flexible camera control based on user preferences. Adopting a training-free architecture, our PaintScene4D efficiently produces realistic 4D scenes that can be viewed from arbitrary trajectories. The code will be made publicly available. Our project page is at https://paintscene4d.github.io/, Comment: Project page: https://paintscene4d.github.io/

Recent advances in implicit neural representations (INRs) have shown significant promise in modeling visual signals for various low-vision tasks including image super-resolution (ISR). INR-based ISR methods typically learn continuous representations, providing flexibility for generating high-resolution images at any desired scale from their low-resolution counterparts. However, existing INR-based ISR methods utilize multi-layer perceptrons for parameterization in the network; this does not take account of the hierarchical structure existing in local sampling points and hence constrains the representation capability. In this paper, we propose a new \textbf{H}ierarchical encoding based \textbf{I}mplicit \textbf{I}mage \textbf{F}unction for continuous image super-resolution, \textbf{HIIF}, which leverages a novel hierarchical positional encoding that enhances the local implicit representation, enabling it to capture fine details at multiple scales. Our approach also embeds a multi-head linear attention mechanism within the implicit attention network by taking additional non-local information into account. Our experiments show that, when integrated with different backbone encoders, HIIF outperforms the state-of-the-art continuous image super-resolution methods by up to 0.17dB in PSNR. The source code of HIIF will be made publicly available at \url{www.github.com}.

Sustainability development goals (SDGs) are regarded as a universal call to action with the overall objectives of planet protection, ending of poverty, and ensuring peace and prosperity for all people. In order to achieve these objectives, different AI technologies play a major role. Specifically, recommender systems can provide support for organizations and individuals to achieve the defined goals. Recommender systems integrate AI technologies such as machine learning, explainable AI (XAI), case-based reasoning, and constraint solving in order to find and explain user-relevant alternatives from a potentially large set of options. In this article, we summarize the state of the art in applying recommender systems to support the achievement of sustainability development goals. In this context, we discuss open issues for future research.

Multimodal models typically combine a powerful large language model (LLM) with a vision encoder and are then trained on multimodal data via instruction tuning. While this process adapts LLMs to multimodal settings, it remains unclear whether this adaptation compromises their original language reasoning capabilities. In this work, we explore the effects of multimodal instruction tuning on language reasoning performance. We focus on LLaVA, a leading multimodal framework that integrates LLMs such as Vicuna or Mistral with the CLIP vision encoder. We compare the performance of the original LLMs with their multimodal-adapted counterparts across eight language reasoning tasks. Our experiments yield several key insights. First, the impact of multimodal learning varies between Vicuna and Mistral: we observe a degradation in language reasoning for Mistral but improvements for Vicuna across most tasks. Second, while multimodal instruction learning consistently degrades performance on mathematical reasoning tasks (e.g., GSM8K), it enhances performance on commonsense reasoning tasks (e.g., CommonsenseQA). Finally, we demonstrate that a training-free model merging technique can effectively mitigate the language reasoning degradation observed in multimodal-adapted Mistral and even improve performance on visual tasks.

Numerous theories have postulated the existence of exotic spin-dependent interactions beyond the Standard Model of particle physics. Spin-based quantum sensors, which utilize the quantum properties of spins to enhance measurement precision, emerge as powerful tools for probing these exotic interactions. These sensors encompass a wide range of technologies, such as optically pumped magnetometers, atomic comagnetometers, spin masers, nuclear magnetic resonance, spin amplifiers, and nitrogen-vacancy centers. These technologies stand out for their ultrahigh sensitivity, compact tabletop design, and cost-effectiveness, offering complementary approaches to the large-scale particle colliders and astrophysical observations. This article reviews the underlying physical principles of various spin sensors and highlights the recent theoretical and experimental progress in the searches for exotic spin-dependent interactions with these quantum sensors. Investigations covered include the exotic interactions of spins with ultralight dark matter, exotic spin-dependent forces, electric dipole moment, spin-gravity interactions, and among others. Ongoing and forthcoming experiments using advanced spin-based sensors to investigate exotic spin-dependent interactions are discussed., Comment: 32 pages, 13 figures, accepted for publication in Reports on Progress in Physics

Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems for specific tasks remains challenging, often requiring manual interventions like prompt engineering and hyperparameter tuning. Existing automatic optimization methods, such as textual feedback-based techniques (e.g., TextGrad), tend to focus on immediate feedback, analogous to using immediate derivatives in traditional numerical gradient descent. However, relying solely on such feedback can be limited when the adjustments made in response to this feedback are either too small or fluctuate irregularly, potentially slowing down or even stalling the optimization process. To overcome these challenges, more adaptive methods are needed, especially in situations where the system's response is evolving slowly or unpredictably. In this paper, we introduce REVOLVE, an optimization method that tracks how "R"esponses "EVOLVE" across iterations in LLM systems. By focusing on the evolution of responses over time, REVOLVE enables more stable and effective optimization by making thoughtful, progressive adjustments at each step. Experimental results demonstrate that REVOLVE outperforms competitive baselines, achieving a 7.8% improvement in prompt optimization, a 20.72% gain in solution refinement, and a 29.17% increase in code optimization. Additionally, REVOLVE converges in fewer iterations, resulting in significant computational savings. These advantages highlight its adaptability and efficiency, positioning REVOLVE as a valuable tool for optimizing LLM-based systems and accelerating the development of next-generation AI technologies. Code is available at: https://github.com/Peiyance/REVOLVE., Comment: 20 pages, 2 figures

Temporal image analysis in remote sensing has traditionally centered on change detection, which identifies regions of change between images captured at different times. However, change detection remains limited by its focus on visual-level interpretation, often lacking contextual or descriptive information. The rise of Vision-Language Models (VLMs) has introduced a new dimension to remote sensing temporal image analysis by integrating visual information with natural language, creating an avenue for advanced interpretation of temporal image changes. Remote Sensing Temporal VLMs (RSTVLMs) allow for dynamic interactions, generating descriptive captions, answering questions, and providing a richer semantic understanding of temporal images. This temporal vision-language capability is particularly valuable for complex remote sensing applications, where higher-level insights are crucial. This paper comprehensively reviews the progress of RSTVLM research, with a focus on the latest VLM applications for temporal image analysis. We categorize and discuss core methodologies, datasets, and metrics, highlight recent advances in temporal vision-language tasks, and outline key challenges and future directions for research in this emerging field. This survey fills a critical gap in the literature by providing an integrated overview of RSTVLM, offering a foundation for further advancements in remote sensing temporal image understanding. We will keep tracing related works at \url{https://github.com/Chen-Yang-Liu/Awesome-RS-Temporal-VLM}

Emerging superionic conductors Li3InCl6 (LIC) and Li6PS5Cl (LPSC) are very promising for solid-state electrolytes (SSEs) in all-solid-state lithium batteries (ASSLBs). However, unstable lithium-anode interfaces in LIC and LPSC have been observed through experiments and ab initio calculations, while the interphases formed in determining interfacial stability remain unclear. In this study, we investigate the ab initio stability of LIC-Li and LPSC-Li interfaces and interphases. Our ab initio calculations revealed that both interfaces are not chemically or electrochemically thermodynamically stable. Interestingly, the LPSC-Li has a stable interphase, but the LIC-Li doesn't. Moreover, the interlayers were systematically evaluated for the LIC-Li and LPSC-Li interfaces, and the desired interlayer materials are clarified for the two interfaces. This ab initio understanding of the interfaces, interphases and interlayers would help the development of a variety of stable interfaces in ASSLBs.

Quantum computing holds promise across various fields, particularly with the advent of Noisy Intermediate-Scale Quantum (NISQ) devices, which can outperform classical supercomputers in specific tasks. However, challenges such as noise and limited qubit capabilities hinder its practical applications. Variational Quantum Algorithms (VQAs) offer a viable strategy to achieve quantum advantage by combining quantum and classical computing. Leveraging on VQAs, the performance of Variational Quantum Classifiers (VQCs) is competitive with many classical classifiers. This work implements a VQC using a silicon-based quantum photonic microprocessor and a classical computer, demonstrating its effectiveness in nonlinear binary and multi-classification tasks. An efficient gradient free genetic algorithm is employed for training. The VQC's performance was evaluated on three synthetic binary classification tasks with square-, circular-, and sine-shape decision boundaries and a real-world multiclass Iris dataset. The accuracies on the three binary classification tasks were 87.5%, 92.5%, and 85.0%, respectively, and 98.8% on the real world Iris dataset, highlighting the platform's potential to handle complex data patterns.

We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a predefined generation order, RandAR removes this inductive bias, unlocking new capabilities in decoder-only generation. Our essential design enables random order by inserting a "position instruction token" before each image token to be predicted, representing the spatial location of the next image token. Trained on randomly permuted token sequences -- a more challenging task than fixed-order generation, RandAR achieves comparable performance to its conventional raster-order counterpart. More importantly, decoder-only transformers trained from random orders acquire new capabilities. For the efficiency bottleneck of AR models, RandAR adopts parallel decoding with KV-Cache at inference time, enjoying 2.5x acceleration without sacrificing generation quality. Additionally, RandAR supports inpainting, outpainting and resolution extrapolation in a zero-shot manner. We hope RandAR inspires new directions for decoder-only visual generation models and broadens their applications across diverse scenarios. Our project page is at https://rand-ar.github.io/., Comment: Project page: https://rand-ar.github.io/

The recent surge in high-quality visual instruction tuning samples from closed-source vision-language models (VLMs) such as GPT-4V has accelerated the release of open-source VLMs across various model sizes. However, scaling VLMs to improve performance using larger models brings significant computational challenges, especially for deployment on resource-constrained devices like mobile platforms and robots. To address this, we propose VLsI: Verbalized Layers-to-Interactions, a new VLM family in 2B and 7B model sizes, which prioritizes efficiency without compromising accuracy. VLsI leverages a unique, layer-wise distillation process, introducing intermediate "verbalizers" that map features from each layer to natural language space, allowing smaller VLMs to flexibly align with the reasoning processes of larger VLMs. This approach mitigates the training instability often encountered in output imitation and goes beyond typical final-layer tuning by aligning the small VLMs' layer-wise progression with that of the large ones. We validate VLsI across ten challenging vision-language benchmarks, achieving notable performance gains (11.0% for 2B and 17.4% for 7B) over GPT-4V without the need for model scaling, merging, or architectural changes., Comment: Project page: https://byungkwanlee.github.io/VLsI-page/

While Large Vision Language Models (LVLMs) have become masterly capable in reasoning over human prompts and visual inputs, they are still prone to producing responses that contain misinformation. Identifying incorrect responses that are not grounded in evidence has become a crucial task in building trustworthy AI. Explainability methods such as gradient-based relevancy maps on LVLM outputs can provide an insight on the decision process of models, however these methods are often computationally expensive and not suited for on-the-fly validation of outputs. In this work, we propose FastRM, an effective way for predicting the explainable Relevancy Maps of LVLM models. Experimental results show that employing FastRM leads to a 99.8% reduction in compute time for relevancy map generation and an 44.4% reduction in memory footprint for the evaluated LVLM, making explainable AI more efficient and practical, thereby facilitating its deployment in real-world applications.

In condensed matter systems, interactions between collective modes offer avenues for nonlinear coherent manipulation of coupled excitations and quantum phases. Antiferromagnets, with their inherently coupled magnon modes, provide a promising platform for nonlinear control of microscopic spin waves and macroscopic magnetization. However, nonlinear magnon-magnon interactions have been only partially elaborated, leaving key gaps in the prospects for potential ultrahigh-bandwidth magnonic signal processing. Here, we use a pair of intense terahertz pulses to sequentially excite two distinct coherent magnon modes in an antiferromagnet and find that the magnon mode with a lower frequency undergoes amplification when the higher-frequency mode is driven. We unveil the nonlinear excitation pathways of this stimulated parametric downconversion process by using polarization-selective two-dimensional terahertz spectroscopy. Our work provides fundamental insights into nonlinear magnonics in antiferromagnets, laying the groundwork for forthcoming spintronic and magnonic devices based on nonlinear magnon-magnon interactions.

Sodium-ion batteries (SIBs) have garnered significant attention in recent years as a promising alternative to lithium-ion batteries (LIBs) due to their low cost, abundant sodium resources, and excellent cycling performance. Hard carbon materials, characterized by their high specific capacity, outstanding cycling stability, and low cost, have emerged as potential candidates for SIB anodes. However, the sodium storage mechanism in hard carbon anodes remains highly complex, especially in disordered structures, and is yet to be fully understood. To address this, we employed relative machine learning force fields (MLFFs) in conjunction with multiscale simulation techniques to systematically investigate the sodium storage behavior in hard carbon. By integrating simulations, this study provides a detailed exploration of sodium adsorption, intercalation, and filling mechanisms. High-precision, large-scale simulations reveal the dynamic behavior and distribution patterns of sodium ions in hard carbon. The findings not only deepen our understanding of sodium storage mechanisms in hard carbon anodes, but also offer a theoretical foundation for optimizing future SIB designs, while introducing novel simulation methodologies and technical frameworks to enhance battery performance., Comment: 23 pages, 7 figures

With the growing scale and complexity of video data, efficiently processing long video sequences poses significant challenges due to the quadratic increase in memory and computational demands associated with existing transformer-based Large Multi-modal Models (LMMs). To address these issues, we introduce Video-Ma$^2$mba, a novel architecture that incorporates State Space Models (SSMs) within the Mamba-2 framework, replacing the attention mechanisms. This allows the LMMs to scale linearly in terms of time and memory requirements, making it feasible to handle long-duration video content. Furthermore, we enhance the memory efficiency introducing the Multi-Axis Gradient Checkpointing (MA-GC) method, which strategically manages memory by retaining only essential activations across multiple computational axes. Our approach significantly reduces the memory footprint compared to standard gradient checkpointing. Empirical analyses show that Video-Ma$^2$mba can process extensive video sequences-equivalent to millions of tokens or over two hours of continuous sequences at 1 FPS-on a single GPU. By maintaining a detailed capture of temporal dynamics, our model improves the accuracy and relevance of responses in long video understanding tasks, demonstrating substantial advantages over existing frameworks., Comment: Project page: https://ivy-lvlm.github.io/Video-MA2MBA/

We examine a system in which an impurity qubit is immersed in a quasi-two-dimensional dipolar Bose-Einstein condensate whose collective excitations act as a depasing reservoir for the qubit. The relative dipole-dipole interaction strength is estimated by the probe qubit dephasing. The ultimate precision of this estimation is quantified by the quantum Fisher information, which can be obtained by means of measuring quantum coherence of the probe qubit. Our findings indicate that, in the interval where roton excitations appear, the quantum Fisher information oscillates periodically with the encoding time $t$, and the amplitude of these oscillations increases alongside the extension of $t$. Moreover, we analytically determine that the envelope curve formed by the local maximum points satisfies the functional relationship $At+Bt^{1/2}+C$ during long-term encoding scenarios, where $A$, $B$, $C$ are positive numbers. It is also revealed that the highly non-Markovian effects caused by the roton softening of the excitation spectrum allow long encoding time to serve as a resource for enhancing sensing precision. Our work provides a new pathway for enhancing the sensing precision of dephasing qubits., Comment: 9 pages, 8 figures

Identifying defects and anomalies in industrial products is a critical quality control task. Traditional manual inspection methods are slow, subjective, and error-prone. In this work, we propose a novel zero-shot training-free approach for automated industrial image anomaly detection using a multimodal machine learning pipeline, consisting of three foundation models. Our method first uses a large language model, i.e., GPT-3. generate text prompts describing the expected appearances of normal and abnormal products. We then use a grounding object detection model, called Grounding DINO, to locate the product in the image. Finally, we compare the cropped product image patches to the generated prompts using a zero-shot image-text matching model, called CLIP, to identify any anomalies. Our experiments on two datasets of industrial product images, namely MVTec-AD and VisA, demonstrate the effectiveness of this method, achieving high accuracy in detecting various types of defects and anomalies without the need for model training. Our proposed model enables efficient, scalable, and objective quality control in industrial manufacturing settings., Comment: Accepted to APSIPA ASC 2024

Rolling bearings play a crucial role in industrial machinery, directly influencing equipment performance, durability, and safety. However, harsh operating conditions, such as high speeds and temperatures, often lead to bearing malfunctions, resulting in downtime, economic losses, and safety hazards. This paper proposes the Residual Attention Single-Head Vision Transformer Network (RA-SHViT-Net) for fault diagnosis in rolling bearings. Vibration signals are transformed from the time to frequency domain using the Fast Fourier Transform (FFT) before being processed by RA-SHViT-Net. The model employs the Single-Head Vision Transformer (SHViT) to capture local and global features, balancing computational efficiency and predictive accuracy. To enhance feature extraction, the Adaptive Hybrid Attention Block (AHAB) integrates channel and spatial attention mechanisms. The network architecture includes Depthwise Convolution, Single-Head Self-Attention, Residual Feed-Forward Networks (Res-FFN), and AHAB modules, ensuring robust feature representation and mitigating gradient vanishing issues. Evaluation on the Case Western Reserve University and Paderborn University datasets demonstrates the RA-SHViT-Net's superior accuracy and robustness in complex, noisy environments. Ablation studies further validate the contributions of individual components, establishing RA-SHViT-Net as an effective tool for early fault detection and classification, promoting efficient maintenance strategies in industrial settings. Keywords: rolling bearings, fault diagnosis, Vision Transformer, attention mechanism, noisy environments, Fast Fourier Transform (FFT), Comment: 24 pages, 14 figures, 3 tables

In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to non overlapping windows to cut costs and ignore the useful information that exists across channels. To address this issue, this paper introduces a novel model, the Hybrid Attention Aggregation Transformer (HAAT), designed to better leverage feature information. HAAT is constructed by integrating Swin-Dense-Residual-Connected Blocks (SDRCB) with Hybrid Grid Attention Blocks (HGAB). SDRCB expands the receptive field while maintaining a streamlined architecture, resulting in enhanced performance. HGAB incorporates channel attention, sparse attention, and window attention to improve nonlocal feature fusion and achieve more visually compelling results. Experimental evaluations demonstrate that HAAT surpasses state-of-the-art methods on benchmark datasets. Keywords: Image super-resolution, Computer vision, Attention mechanism, Transformer, Comment: 6 pages, 2 figures, 1 table

With the rapid advancements in deep learning, computer vision tasks have seen significant improvements, making two-stream neural networks a popular focus for video based action recognition. Traditional models using RGB and optical flow streams achieve strong performance but at a high computational cost. To address this, we introduce a representation flow algorithm to replace the optical flow branch in the egocentric action recognition model, enabling end-to-end training while reducing computational cost and prediction time. Our model, designed for egocentric action recognition, uses class activation maps (CAMs) to improve accuracy and ConvLSTM for spatio temporal encoding with spatial attention. When evaluated on the GTEA61, EGTEA GAZE+, and HMDB datasets, our model matches the accuracy of the original model on GTEA61 and exceeds it by 0.65% and 0.84% on EGTEA GAZE+ and HMDB, respectively. Prediction runtimes are significantly reduced to 0.1881s, 0.1503s, and 0.1459s, compared to the original model's 101.6795s, 25.3799s, and 203.9958s. Ablation studies were also conducted to study the impact of different parameters on model performance. Keywords: two-stream, egocentric, action recognition, CAM, representation flow, CAM, ConvLSTM, Comment: 6 pages, 3 figures, 9 tables

Multispectral pedestrian detection is a crucial component in various critical applications. However, a significant challenge arises due to the misalignment between these modalities, particularly under real-world conditions where data often appear heavily misaligned. Conventional methods developed on well-aligned or minimally misaligned datasets fail to address these discrepancies adequately. This paper introduces a new framework for multispectral pedestrian detection designed specifically to handle heavily misaligned datasets without the need for costly and complex traditional pre-processing calibration. By leveraging Large-scale Vision-Language Models (LVLM) for cross-modal semantic alignment, our approach seeks to enhance detection accuracy by aligning semantic information across the RGB and thermal domains. This method not only simplifies the operational requirements but also extends the practical usability of multispectral detection technologies in practical applications.

Despite advances in Large Multi-modal Models, applying them to long and untrimmed video content remains challenging due to limitations in context length and substantial memory overhead. These constraints often lead to significant information loss and reduced relevance in the model responses. With the exponential growth of video data across web platforms, understanding long-form video is crucial for advancing generalized intelligence. In this paper, we introduce SALOVA: Segment-Augmented LOng Video Assistant, a novel video-LLM framework designed to enhance the comprehension of lengthy video content through targeted retrieval process. We address two main challenges to achieve it: (i) We present the SceneWalk dataset, a high-quality collection of 87.8K long videos, each densely captioned at the segment level to enable models to capture scene continuity and maintain rich descriptive context. (ii) We develop robust architectural designs integrating dynamic routing mechanism and spatio-temporal projector to efficiently retrieve and process relevant video segments based on user queries. Our framework mitigates the limitations of current video-LMMs by allowing for precise identification and retrieval of relevant video segments in response to queries, thereby improving the contextual relevance of the generated responses. Through extensive experiments, SALOVA demonstrates enhanced capability in processing complex long-form videos, showing significant capability to maintain contextual integrity across extended sequences., Comment: Project page: https://ivy-lvlm.github.io/SALOVA/

The ambition of brain-inspired Spiking Neural Networks (SNNs) is to become a low-power alternative to traditional Artificial Neural Networks (ANNs). This work addresses two major challenges in realizing this vision: the performance gap between SNNs and ANNs, and the high training costs of SNNs. We identify intrinsic flaws in spiking neurons caused by binary firing mechanisms and propose a Spike Firing Approximation (SFA) method using integer training and spike-driven inference. This optimizes the spike firing pattern of spiking neurons, enhancing efficient training, reducing power consumption, improving performance, enabling easier scaling, and better utilizing neuromorphic chips. We also develop an efficient spike-driven Transformer architecture and a spike-masked autoencoder to prevent performance degradation during SNN scaling. On ImageNet-1k, we achieve state-of-the-art top-1 accuracy of 78.5\%, 79.8\%, 84.0\%, and 86.2\% with models containing 10M, 19M, 83M, and 173M parameters, respectively. For instance, the 10M model outperforms the best existing SNN by 7.2\% on ImageNet, with training time acceleration and inference energy efficiency improved by 4.5$\times$ and 3.9$\times$, respectively. We validate the effectiveness and efficiency of the proposed method across various tasks, including object detection, semantic segmentation, and neuromorphic vision tasks. This work enables SNNs to match ANN performance while maintaining the low-power advantage, marking a significant step towards SNNs as a general visual backbone. Code is available at https://github.com/BICLab/Spike-Driven-Transformer-V3.

The widely-used, weight-only quantized large language models (LLMs), which leverage low-bit integer (INT) weights and retain floating-point (FP) activations, reduce storage requirements while maintaining accuracy. However, this shifts the energy and latency bottlenecks towards the FP activations that are associated with costly memory accesses and computations. Existing LLM accelerators focus primarily on computation optimizations, overlooking the potential of jointly optimizing FP computations and data movement, particularly for the dominant FP-INT GeMM operations in LLM inference. To address these challenges, we investigate the sensitivity of activation precision across various LLM modules and its impact on overall model accuracy. Based on our findings, we first propose the Anda data type: an adaptive data format with group-shared exponent bits and dynamic mantissa bit allocation. Secondly, we develop an iterative post-training adaptive precision search algorithm that optimizes the bit-width for different LLM modules to balance model accuracy, energy efficiency, and inference speed. Lastly, a suite of hardware optimization techniques is proposed to maximally exploit the benefits of the Anda format. These include a bit-plane-based data organization scheme, Anda-enhanced processing units with bit-serial computation, and a runtime bit-plane Anda compressor to simultaneously optimize storage, computation, and memory footprints. Our evaluations on FPINT GeMM operations show that Anda achieves a 2.4x speedup, 4.0x area efficiency, and 3.1x energy efficiency improvement on average for popular LLMs including OPT, LLaMA, and LLaMA-2 series over the GPU-like FP-FP baseline. Anda demonstrates strong adaptability across various application scenarios, accuracy requirements, and system performance, enabling efficient LLM inference across a wide range of deployment scenarios., Comment: To appear in 2025 IEEE International Symposium on High-Performance Computer Architecture (HPCA 2025)

Based on the Jacobi polynomial expansion, an arbitrary high-order Discontinuous Galerkin solver for compressible flows on unstructured meshes is proposed in the present work. First, we construct orthogonal polynomials for 2D and 3D isoparametric elements using the 1D Jacobi polynomials. We perform modal expansions of the state variables using the orthogonal polynomials, enabling arbitrary high-order spatial discretization of these variables. Subsequently, the discrete governing equations are derived by considering the orthogonality of the Euler equations' residuals and the test functions. On this basis, we develop a high-order Discontinuous Galerkin solver that supports various element types, including triangles, quadrilaterals, tetrahedra, hexahedra, etc. An improved shock-capturing scheme has been adopted to capture shock discontinuities within the flow field. The variable's gradients at the discontinuous elements are reconstructed by its adjacent elements, and the slope limiter is applied to modify the state variables, smoothing the state variables and enhancing the robustness of the solver. The convergence rates of solvers of different orders have been verified by a benchmark case, and the CPU costs are given to prove that high-precision algorithms have higher computational efficiency under the same error level. Finally, several two- and three-dimensional compressible fluid dynamics problems are studied, compared with literature and experimental results, the effectiveness and accuracy of the solver were verified., Comment: 30 pages, 20 figures

Our understanding of high-lying states within the charmonium family remains incomplete, particularly in light of recent observations of charmonium states at energies above 4 GeV. In this study, we investigate the spectroscopic properties of several high-lying charmonia, focusing on the $D$-, $F$-, and $G$-wave states. A mass spectrum analysis is conducted, incorporating the unquenched effects. We then present a detailed study of the strong decay properties, including partial decay widths for two-body strong decays permitted by the Okubo-Zweig-Iizuka (OZI) rule. Additionally, we explore the primary radiative decay channels associated with these states. Theoretical predictions provided here aim to guide future experimental searches for high-lying charmonium states, particularly at BESIII, Belle II and LHCb., Comment: 13 pages, 5 tables and 1 figure

Anomaly detection (AD) is a machine learning task that identifies anomalies by learning patterns from normal training data. In many real-world scenarios, anomalies vary in severity, from minor anomalies with little risk to severe abnormalities requiring immediate attention. However, existing models primarily operate in a binary setting, and the anomaly scores they produce are usually based on the deviation of data points from normal data, which may not accurately reflect practical severity. In this paper, we address this gap by making three key contributions. First, we propose a novel setting, Multilevel AD (MAD), in which the anomaly score represents the severity of anomalies in real-world applications, and we highlight its diverse applications across various domains. Second, we introduce a novel benchmark, MAD-Bench, that evaluates models not only on their ability to detect anomalies, but also on how effectively their anomaly scores reflect severity. This benchmark incorporates multiple types of baselines and real-world applications involving severity. Finally, we conduct a comprehensive performance analysis on MAD-Bench. We evaluate models on their ability to assign severity-aligned scores, investigate the correspondence between their performance on binary and multilevel detection, and study their robustness. This analysis offers key insights into improving AD models for practical severity alignment. The code framework and datasets used for the benchmark will be made publicly available., Comment: Under review

Large language models have gained widespread popularity for their ability to process natural language inputs and generate insights derived from their training data, nearing the qualities of true artificial intelligence. This advancement has prompted enterprises worldwide to integrate LLMs into their services. So far, this effort is dominated by commercial cloud-based solutions like OpenAI's ChatGPT and Microsoft Azure. As the technology matures, however, there is a strong incentive for independence from major cloud providers through self-hosting "LLM as a Service", driven by privacy, cost, and customization needs. In practice, hosting LLMs independently presents significant challenges due to their complexity and integration issues with existing systems. In this paper, we discuss our vision for a forward-looking middleware system architecture that facilitates the deployment and adoption of LLMs in enterprises, even for advanced use cases in which we foresee LLMs to serve as gateways to a complete application ecosystem and, to some degree, absorb functionality traditionally attributed to the middleware.

Let $\mu$ be a compactly supported positive finite Borel measure on $\R^{d}$. Let $0<\lambda_{1}\leq\lambda_{2}\leq\ldots$ be eigenvalues of the Kre$\breve{{\i}}$n-Feller operator $\Delta_{\mu}$. We prove that, on a bounded domain, the nodal set of a continuous $\lambda_{n}$-eigenfunction of a Kre$\breve{{\i}}$n-Feller operator divides the domain into at least 2 and at most $n+r-1$ subdomains, where $r$ is the multiplicity of $\lambda_{n}$. This work generalizes the nodal set theorem of the classical Laplace operator to Kre$\breve{{\i}}$n-Feller operators on bounded domains. We also prove that on bounded domains on which the classical Green function exists, the eigenfunctions of a Kre$\breve{{\i}}$n-Feller operator are continuous.

While the conducting CuO$_2$ planes in cuprate superconductors have been widely recognized as a crucial component in producing high superconducting $T_\text{c}$, recent experimental and theoretical studies on Ba$_{2-x}$Sr$_x$CuO$_{3+}$$_\delta$ have also drawn much attention to the importance of Cu-O chains in one-dimensional (1D) cuprates. To better understand the cuprates containing Cu-O chains, here we have studied the electronic, magnetic, and phonon properties of Sr$_2$CuO$_3$ bulk and films based on the spin-polarized density functional theory calculations. We first reproduced the typical Mott insulator feature of the cuprate parent compound for bulk Sr$_2$CuO$_3$, and then built a Sr$_2$CuO$_3$ thin film with Cu-O chains exposed on the surface to directly investigate their characteristics. Different from the insulating bulk phase, the Sr$_2$CuO$_3$ surface shows interesting metallic properties. Further electronic structure calculations reveal the existence of spin-polarized electron gas between surface Sr atoms that strongly depends on the interchain coupling of Cu spins. Moreover, the phonon modes that involve the vibrations of in-chain and out-of-chain O atoms can induce strong charge and spin fluctuations in the surface layer of Sr$_2$CuO$_3$ film, which suggests significant multiple degree-of-freedom couplings that may be important for the superconductivity in 1D cuprates. Our work provides a comprehensive viewpoint of the properties of Cu-O chains in Sr$_2$CuO$_3$, facilitating a complete understanding of 1D cuprate superconductors., Comment: 10 pages, 8 figures

Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medical tasks due to their reliance on memorized internet knowledge rather than the nuanced expertise required in healthcare. VLMs are usually trained in three stages: vision pre-training, vision-language pre-training, and instruction fine-tuning (IFT). IFT has been typically applied using a mixture of generic and healthcare data. In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from domain expert models. Domain expert models developed for medical use are crucial because they are specifically trained for certain clinical tasks, e.g. to detect tumors and classify abnormalities through segmentation and classification, which learn fine-grained features of medical data$-$features that are often too intricate for a VLM to capture effectively especially in radiology. This paper introduces a new framework, VILA-M3, for medical VLMs that utilizes domain knowledge via expert models. Through our experiments, we show an improved state-of-the-art (SOTA) performance with an average improvement of ~9% over the prior SOTA model Med-Gemini and ~6% over models trained on the specific tasks. Our approach emphasizes the importance of domain expertise in creating precise, reliable VLMs for medical applications.

The advancements in large language models (LLMs) have propelled the improvement of video understanding tasks by incorporating LLMs with visual models. However, most existing LLM-based models (e.g., VideoLLaMA, VideoChat) are constrained to processing short-duration videos. Recent attempts to understand long-term videos by extracting and compressing visual features into a fixed memory size. Nevertheless, those methods leverage only visual modality to merge video tokens and overlook the correlation between visual and textual queries, leading to difficulties in effectively handling complex question-answering tasks. To address the challenges of long videos and complex prompts, we propose AdaCM$^2$, which, for the first time, introduces an adaptive cross-modality memory reduction approach to video-text alignment in an auto-regressive manner on video streams. Our extensive experiments on various video understanding tasks, such as video captioning, video question answering, and video classification, demonstrate that AdaCM$^2$ achieves state-of-the-art performance across multiple datasets while significantly reducing memory usage. Notably, it achieves a 4.5% improvement across multiple tasks in the LVU dataset with a GPU memory consumption reduction of up to 65%.

Blind image restoration remains a significant challenge in low-level vision tasks. Recently, denoising diffusion models have shown remarkable performance in image synthesis. Guided diffusion models, leveraging the potent generative priors of pre-trained models along with a differential guidance loss, have achieved promising results in blind image restoration. However, these models typically consider data consistency solely in the spatial domain, often resulting in distorted image content. In this paper, we propose a novel frequency-aware guidance loss that can be integrated into various diffusion models in a plug-and-play manner. Our proposed guidance loss, based on 2D discrete wavelet transform, simultaneously enforces content consistency in both the spatial and frequency domains. Experimental results demonstrate the effectiveness of our method in three blind restoration tasks: blind image deblurring, imaging through turbulence, and blind restoration for multiple degradations. Notably, our method achieves a significant improvement in PSNR score, with a remarkable enhancement of 3.72\,dB in image deblurring. Moreover, our method exhibits superior capability in generating images with rich details and reduced distortion, leading to the best visual quality., Comment: 17 pages, 6 figures, has been accepted by the ECCV 2024: AIM workshop

We study the problem of dynamically maintaining the connected components of an undirected graph subject to edge insertions and deletions. We give the first parallel algorithm for the problem which is work-efficient, supports batches of updates, runs in polylogarithmic depth, and uses only linear total space. The existing algorithms for the problem either use super-linear space, do not come with strong theoretical bounds, or are not parallel. On the empirical side, we provide the first implementation of the cluster forest algorithm, the first linear-space and poly-logarithmic update time algorithm for dynamic connectivity. Experimentally, we find that our algorithm uses up to 19.7x less space and is up to 6.2x faster than the level-set algorithm of HDT, arguably the most widely-implemented dynamic connectivity algorithm with strong theoretical guarantees., Comment: This is a preliminary version of a paper that will appear at VLDB'25

Automated machinery design for garment manufacturing is essential for improving productivity, consistency, and quality. This paper focuses on the development of new pulling gear for automated pant bottom hem sewing machines. Traditionally, these machines require manual intervention to guide the bottom hem sewing process, which often leads to inconsistent stitch quality and alignment. While twin-needle sewing machines can create twin lines for the bottom hem, they typically lack sufficient pulling force to adequately handle the fabric of the pants' bottom hem. The innovative design of the pulling gear aims to address this issue by providing the necessary pulling force for the bottom hem of eyelet pants. The research and design discussed in this article seek to solve technical challenges, eliminate the need for skilled manual operators, and enhance overall productivity. This improvement ensures smooth and precise feeding of fabric pieces in the automated twin needle sewing machine, ultimately improving the consistency and quality of the stitching. By integrating this innovation, garment manufacturers can boost productivity, reduce reliance on manual skilful labour, and optimize the output of the production process, thereby reaping the benefits of automation in the garment manufacturing industry., Comment: 9 pages,11 figures, preprint to International Research Journal of Modernization in Engineering Technology and Science

The advances in immersive technologies and 3D reconstruction have enabled the creation of digital replicas of real-world objects and environments with fine details. These processes generate vast amounts of 3D data, requiring more efficient compression methods to satisfy the memory and bandwidth constraints associated with data storage and transmission. However, the development and validation of efficient 3D data compression methods are constrained by the lack of comprehensive and high-quality volumetric video datasets, which typically require much more effort to acquire and consume increased resources compared to 2D image and video databases. To bridge this gap, we present an open multi-view volumetric human dataset, denoted BVI-CR, which contains 18 multi-view RGB-D captures and their corresponding textured polygonal meshes, depicting a range of diverse human actions. Each video sequence contains 10 views in 1080p resolution with durations between 10-15 seconds at 30FPS. Using BVI-CR, we benchmarked three conventional and neural coordinate-based multi-view video compression methods, following the MPEG MIV Common Test Conditions, and reported their rate quality performance based on various quality metrics. The results show the great potential of neural representation based methods in volumetric video compression compared to conventional video coding methods (with an up to 38\% average coding gain in PSNR). This dataset provides a development and validation platform for a variety of tasks including volumetric reconstruction, compression, and quality assessment. The database will be shared publicly at \url{https://github.com/fan-aaron-zhang/bvi-cr}.

Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax attention in Transformer structures. However, the optimal design of these linear models is still an open question. In this work, we attempt to answer this question by finding the best linear approximation to softmax attention from a theoretical perspective. We start by unifying existing linear complexity models as the linear attention form and then identify three conditions for the optimal linear attention design: 1) Dynamic memory ability; 2) Static approximation ability; 3) Least parameter approximation. We find that none of the current linear models meet all three conditions, resulting in suboptimal performance. Instead, we propose Meta Linear Attention (MetaLA) as a solution that satisfies these conditions. Our experiments on Multi-Query Associative Recall (MQAR) task, language modeling, image classification, and Long-Range Arena (LRA) benchmark demonstrate that MetaLA is more effective than the existing linear models.

The stylization of 3D scenes is an increasingly attractive topic in 3D vision. Although image style transfer has been extensively researched with promising results, directly applying 2D style transfer methods to 3D scenes often fails to preserve the structural and multi-view properties of 3D environments, resulting in unpleasant distortions in images from different viewpoints. To address these issues, we leverage the remarkable generative prior of diffusion-based models and propose a novel style transfer method, OSDiffST, based on a pre-trained one-step diffusion model (i.e., SD-Turbo) for rendering diverse styles in multi-view images of 3D scenes. To efficiently adapt the pre-trained model for multi-view style transfer on small datasets, we introduce a vision condition module to extract style information from the reference style image to serve as conditional input for the diffusion model and employ LoRA in diffusion model for adaptation. Additionally, we consider color distribution alignment and structural similarity between the stylized and content images using two specific loss functions. As a result, our method effectively preserves the structural information and multi-view consistency in stylized images without any 3D information. Experiments show that our method surpasses other promising style transfer methods in synthesizing various styles for multi-view images of 3D scenes. Stylized images from different viewpoints generated by our method achieve superior visual quality, with better structural integrity and less distortion. The source code is available at https://github.com/YushenZuo/OSDiffST., Comment: Accepted by ECCV 2024 AI for Visual Arts Workshop and Challenges, 18 pages, 7 figures