Search

Due to the poor adaptability of traditional methods in the cigarette detection task on the automatic cigarette production line, it is difficult to accurately identify whether a cigarette has defects and the types of defects; thus, a cigarette appearance defect detection method based on C-CenterNet is proposed. This detector uses keypoint estimation to locate center points and regresses all other defect properties. Firstly, Resnet50 is used as the backbone feature extraction network, and the convolutional block attention mechanism (CBAM) is introduced to enhance the network's ability to extract effective features and reduce the interference of non-target information. At the same time, the feature pyramid network is used to enhance the feature extraction of each layer. Then, deformable convolution is used to replace part of the common convolution to enhance the learning ability of different shape defects. Finally, the activation function ACON (ActivateOrNot) is used instead of the ReLU activation function, and the activation operation of some neurons is adaptively selected to improve the detection accuracy of the network. The experimental results are mainly acquired via the mean Average Precision (mAP). The experimental results show that the mAP of the C-CenterNet model applied in the cigarette appearance defect detection task is 95.01%. Compared with the original CenterNet model, the model's success rate is increased by 6.14%, so it can meet the requirements of precision and adaptability in cigarette detection tasks on the automatic cigarette production line., Comment: 19 pages, 14 figures

Solar radio observation is a method used to study the Sun. It is very important for space weather early warning and solar physics research to automatically classify solar radio spectrums in real time and judge whether there is a solar radio burst. As the number of solar radio burst spectrums is small and uneven, this paper proposes a classification method for solar radio spectrums based on the Swin transformer. First, the method transfers the parameters of the pretrained model to the Swin transformer model. Then, the hidden layer weights of the Swin transformer are frozen, and the fully connected layer of the Swin transformer is trained on the target dataset. Finally, pa-rameter tuning is performed. The experimental results show that the method can achieve a true positive rate of 100%, which is more accurate than previous methods. Moreover, the number of our model parameters is only 20 million, which is 80% lower than that of the traditional VGG16 con-volutional neural network with more than 130 million parameters.

Automatic object detection by satellite remote sensing images is of great significance for resource exploration and natural disaster assessment. To solve existing problems in remote sensing image detection, this article proposes an improved YOLOX model for satellite remote sensing image automatic detection. This model is named RS-YOLOX. To strengthen the feature learning ability of the network, we used Efficient Channel Attention (ECA) in the backbone network of YOLOX and combined the Adaptively Spatial Feature Fusion (ASFF) with the neck network of YOLOX. To balance the numbers of positive and negative samples in training, we used the Varifocal Loss function. Finally, to obtain a high-performance remote sensing object detector, we combined the trained model with an open-source framework called Slicing Aided Hyper Inference (SAHI). This work evaluated models on three aerial remote sensing datasets (DOTA-v1.5, TGRS-HRRSD, and RSOD). Our comparative experiments demonstrate that our model has the highest accuracy in detecting objects in remote sensing image datasets.

We introduce Deblur-Avatar, a novel framework for modeling high-fidelity, animatable 3D human avatars from motion-blurred monocular video inputs. Motion blur is prevalent in real-world dynamic video capture, especially due to human movements in 3D human avatar modeling. Existing methods either (1) assume sharp image inputs, failing to address the detail loss introduced by motion blur, or (2) mainly consider blur by camera movements, neglecting the human motion blur which is more common in animatable avatars. Our proposed approach integrates a human movement-based motion blur model into 3D Gaussian Splatting (3DGS). By explicitly modeling human motion trajectories during exposure time, we jointly optimize the trajectories and 3D Gaussians to reconstruct sharp, high-quality human avatars. We employ a pose-dependent fusion mechanism to distinguish moving body regions, optimizing both blurred and sharp areas effectively. Extensive experiments on synthetic and real-world datasets demonstrate that Deblur-Avatar significantly outperforms existing methods in rendering quality and quantitative metrics, producing sharp avatar reconstructions and enabling real-time rendering under challenging motion blur conditions.

As we enter the quantum utility era, the computing paradigm shifts toward quantum-centric computing, where multiple quantum processors collaborate with classical computers, exemplified by platforms like IBM Quantum and Amazon Braket. In this paradigm, efficient resource management is crucial; however, unlike classical computing, quantum processors face significant challenges due to noise, which raises fidelity concerns in quantum applications. Compounding this issue, the noise characteristics across different quantum processors are inherently heterogeneous, making resource optimization even more complex. Existing resource management strategies primarily focus on mapping and scheduling jobs to these heterogeneous backends, which leads to some jobs suffering extremely low fidelity. Targeting quantum optimization jobs (e.g., VQC, VQE, QAOA) - one of the most promising quantum applications in the NISQ era, we hypothesize that running the later stages of a job on a high-fidelity quantum processor can significantly enhance overall fidelity. To validate this hypothesis, we use the VQE as a case study and propose a novel and efficient Genetic Algorithm-based scheduling framework with the consideration of job splitting. Experimental results demonstrate that our approach maintains high fidelity across all jobs and significantly improves system throughput. Furthermore, the proposed algorithm shows excellent scalability with respect to the number of quantum processors and the volume of jobs, making it a robust solution for emerging quantum computing platforms.

Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion capture with numerous applications. Despite encouraging progress, current state-of-the-art methods focus on training innovative architectural designs on confined datasets. In this work, we investigate the impact of scaling up EHPS towards a family of generalist foundation models. 1) For data scaling, we perform a systematic investigation on 40 EHPS datasets, encompassing a wide range of scenarios that a model trained on any single dataset cannot handle. More importantly, capitalizing on insights obtained from the extensive benchmarking process, we optimize our training scheme and select datasets that lead to a significant leap in EHPS capabilities. Ultimately, we achieve diminishing returns at 10M training instances from diverse data sources. 2) For model scaling, we take advantage of vision transformers (up to ViT-Huge as the backbone) to study the scaling law of model sizes in EHPS. To exclude the influence of algorithmic design, we base our experiments on two minimalist architectures: SMPLer-X, which consists of an intermediate step for hand and face localization, and SMPLest-X, an even simpler version that reduces the network to its bare essentials and highlights significant advances in the capture of articulated hands. With big data and the large model, the foundation models exhibit strong performance across diverse test benchmarks and excellent transferability to even unseen environments. Moreover, our finetuning strategy turns the generalist into specialist models, allowing them to achieve further performance boosts. Notably, our foundation models consistently deliver state-of-the-art results on seven benchmarks such as AGORA, UBody, EgoBody, and our proposed SynHand dataset for comprehensive hand evaluation. (Code is available at: https://github.com/wqyin/SMPLest-X)., Comment: An extension of SMPLer-X [arXiv:2309.17448]. Homepage: https://caizhongang.com/projects/SMPLer-X/

SDSS J1115+0544 is a unique low-ionization nuclear emission-line region (LINER) galaxy with energetic ultraviolet (UV), optical and mid-infrared outbursts occurring in its nucleus. We present the results from an analysis of multi-wavelength photometric and radio follow-up observations covering a period of ~9 years since its discovery. We find that following a luminosity plateau of ~500 days, the UV/optical emission has decayed back to the pre-outburst level, suggesting that the nuclear outburst might be caused by a stellar tidal disruption event (TDE). In this case, SDSS J1115+0544 could be an unusually slow-evolved optical TDE with longest rise and decline time-scales ever found. Three years later than the optical peak, a delayed radio brightening was found with a 5.5 GHz luminosity as high as ~1.9x10^39 erg/s. Using a standard equipartition analysis, we find the outflow powering the radio emission was launched at t~1260 days with a velocity of beta<~0.1 and kinetic energy of E_K~>10^50 erg. The delayed radio brightening coupled with the disappearing plateau in the UV/optical light curves is consistent with the scenario involving delayed ejection of an outflow from a state transition in the disk. SDSS J1115+0544 is the first TDE displaying both a short-lived UV/optical plateau emission and a late-time radio brightening. Future radio observations of these TDEs in the post-plateau decay phase will help to establish the connection between outflow launching and changes in accretion rate., Comment: 13 pages, 5 figures, comments are welcome

Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small area, making long-range consistent scene generation challenging. To address this, we propose StarGen, a novel framework that employs a pre-trained video diffusion model in an autoregressive manner for long-range scene generation. The generation of each video clip is conditioned on the 3D warping of spatially adjacent images and the temporally overlapping image from previously generated clips, improving spatiotemporal consistency in long-range scene generation with precise pose control. The spatiotemporal condition is compatible with various input conditions, facilitating diverse tasks, including sparse view interpolation, perpetual view generation, and layout-conditioned city generation. Quantitative and qualitative evaluations demonstrate StarGen's superior scalability, fidelity, and pose accuracy compared to state-of-the-art methods.

Recently, the advent of generative AI technologies has made transformational impacts on our daily lives, yet its application in scientific applications remains in its early stages. Data scarcity is a major, well-known barrier in data-driven scientific computing, so physics-guided generative AI holds significant promise. In scientific computing, most tasks study the conversion of multiple data modalities to describe physical phenomena, for example, spatial and waveform in seismic imaging, time and frequency in signal processing, and temporal and spectral in climate modeling; as such, multi-modal pairwise data generation is highly required instead of single-modal data generation, which is usually used in natural images (e.g., faces, scenery). Moreover, in real-world applications, the unbalance of available data in terms of modalities commonly exists; for example, the spatial data (i.e., velocity maps) in seismic imaging can be easily simulated, but real-world seismic waveform is largely lacking. While the most recent efforts enable the powerful diffusion model to generate multi-modal data, how to leverage the unbalanced available data is still unclear. In this work, we use seismic imaging in subsurface geophysics as a vehicle to present ``UB-Diff'', a novel diffusion model for multi-modal paired scientific data generation. One major innovation is a one-in-two-out encoder-decoder network structure, which can ensure pairwise data is obtained from a co-latent representation. Then, the co-latent representation will be used by the diffusion process for pairwise data generation. Experimental results on the OpenFWI dataset show that UB-Diff significantly outperforms existing techniques in terms of Fr\'{e}chet Inception Distance (FID) score and pairwise evaluation, indicating the generation of reliable and useful multi-modal pairwise data., Comment: Accepted at AAAI 2025. This is the preprint version. Keywords: Multi-modal generation, diffuison models, scientific data generation, unbalanced modalities

Raising the order of the multipole expansion is a feasible approach for improving the accuracy of the treecode algorithm. However, a uniform order for the expansion would result in the inefficiency of the implementation, especially when the kernel function is singular. In this paper, a $p$-adaptive treecode algorithm is designed to resolve the efficiency issue for problems defined on a general domain. Such a $p$-adaptive implementation is realized through i). conducting a systematical error analysis for the treecode algorithm, ii). designing a strategy for a non-uniform distribution of the order of multipole expansion towards a given error tolerance, and iii). employing a hierarchy geometry tree structure for coding the algorithm. The proposed $p$-adaptive treecode algorithm is validated by a number of numerical experiments, from which the desired performance is observed successfully, i.e., the computational complexity is reduced dramatically compared with the uniform order case, making our algorithm a competitive one for bottleneck problems such as the demagnetizing field calculation in computational micromagnetics.

Smoke detection using Deep Neural Networks (DNNs) is an effective approach for early wildfire detection. However, because smoke is temporally and spatially anomalous, there are limitations in collecting sufficient training data. This raises overfitting and bias concerns in existing DNN-based wildfire detection models. Thus, we introduce WARP (Wildfire Adversarial Robustness Procedure), the first model-agnostic framework for evaluating the adversarial robustness of DNN-based wildfire detection models. WARP addresses limitations in smoke image diversity using global and local adversarial attack methods. The global attack method uses image-contextualized Gaussian noise, while the local attack method uses patch noise injection, tailored to address critical aspects of wildfire detection. Leveraging WARP's model-agnostic capabilities, we assess the adversarial robustness of real-time Convolutional Neural Networks (CNNs) and Transformers. The analysis revealed valuable insights into the models' limitations. Specifically, the global attack method demonstrates that the Transformer model has more than 70% precision degradation than the CNN against global noise. In contrast, the local attack method shows that both models are susceptible to cloud image injections when detecting smoke-positive instances, suggesting a need for model improvements through data augmentation. WARP's comprehensive robustness analysis contributed to the development of wildfire-specific data augmentation strategies, marking a step toward practicality.

Large language models (LLMs) based on the Transformer architecture usually have their context length limited due to the high training cost. Recent advancements extend the context window by adjusting the scaling factors of RoPE and fine-tuning. However, suboptimal initialization of these factors results in increased fine-tuning costs and reduced performance at target length. To address these challenges, we propose an innovative RoPE-based fine-tuning framework that diverges from conventional scaling factors search. Specifically, we present a Divide-and-Conquer Incremental Search (DCIS) algorithm that strategically determines the better scaling factors. Further fine-tuning with the identified scaling factors effectively extends the context window of LLMs. Empirical results demonstrate that our methodology not only mitigates performance decay at extended target lengths but also allows the model to fine-tune on short contexts and generalize to long contexts, thereby reducing the cost of fine-tuning. The scaling factors obtained through DCIS can even perform effectively without fine-tuning. Further analysis of the search space reveals that DCIS achieves twice the search efficiency compared to other methods. We also examine the impact of the non-strictly increasing scaling factors utilized in DCIS and evaluate the general capabilities of LLMs across various context lengths.

We propose a beam-dump experiment (BDE) at the upcoming facility of China initiative Accelerator Driven System (CiADS), called CiADS-BDE, in order to search for long-lived particles (LLPs) predicted in various beyond-the-Standard-Model (BSM) theories. The experiment is to be located in the forward direction of the incoming low-energy proton beam at CiADS, leveraging the strong forward boost of the produced particles at the beam dump in general. The space between the dump and the detector is largely available, allowing for installation of veto materials and hence low levels of background events. We elaborate on the detector setup, and choose dark photon as a benchmark model for sensitivity study. We restrict ourselves to the signature of an electron-positron pair, and find that with 5 years' operation, unique, currently unexcluded parts of the parameter space for $\mathcal{O}(100)$ MeV dark-photon masses and $\mathcal{O}(10^{-9}\text{--}10^{-8})$ kinetic mixing can be probed at the CiADS-BDE. Furthermore, considering that there is no need to set up a proton beam specifically for this experiment and that the detector system requires minimal instrumentation, the experiment is supposed to be relatively cost-effective. Therefore, we intend this work to promote studies on the sensitivity reach of the proposed experiment to additional LLP scenarios, and in the end, the realization of the experiment. Incidentally, we study the sensitivity of the same BDE setups at the High Intensity Heavy-ion Accelerator Facility (HIAF), presently under construction near the CiADS program site, and conclude that HIAF-BDE could probe new parameter regions, too.

Graph neural networks (GNNs) are powerful machine learning models designed to handle irregularly structured data. However, their generic design often proves inadequate for analyzing brain connectomes in Alzheimer's Disease (AD), highlighting the need to incorporate domain knowledge for optimal performance. Infusing AD-related knowledge into GNNs is a complicated task. Existing methods typically rely on collaboration between computer scientists and domain experts, which can be both time-intensive and resource-demanding. To address these limitations, this paper presents a novel self-guided, knowledge-infused multimodal GNN that autonomously incorporates domain knowledge into the model development process. Our approach conceptualizes domain knowledge as natural language and introduces a specialized multimodal GNN capable of leveraging this uncurated knowledge to guide the learning process of the GNN, such that it can improve the model performance and strengthen the interpretability of the predictions. To evaluate our framework, we curated a comprehensive dataset of recent peer-reviewed papers on AD and integrated it with multiple real-world AD datasets. Experimental results demonstrate the ability of our method to extract relevant domain knowledge, provide graph-based explanations for AD diagnosis, and improve the overall performance of the GNN. This approach provides a more scalable and efficient alternative to inject domain knowledge for AD compared with the manual design from the domain expert, advancing both prediction accuracy and interpretability in AD diagnosis.

While motion generation has made substantial progress, its practical application remains constrained by dataset diversity and scale, limiting its ability to handle out-of-distribution scenarios. To address this, we propose a simple and effective baseline, RMD, which enhances the generalization of motion generation through retrieval-augmented techniques. Unlike previous retrieval-based methods, RMD requires no additional training and offers three key advantages: (1) the external retrieval database can be flexibly replaced; (2) body parts from the motion database can be reused, with an LLM facilitating splitting and recombination; and (3) a pre-trained motion diffusion model serves as a prior to improve the quality of motions obtained through retrieval and direct combination. Without any training, RMD achieves state-of-the-art performance, with notable advantages on out-of-distribution data.

Recent advancements in deep learning have significantly revolutionized the field of clinical diagnosis and treatment, offering novel approaches to improve diagnostic precision and treatment efficacy across diverse clinical domains, thus driving the pursuit of precision medicine. The growing availability of multi-organ and multimodal datasets has accelerated the development of large-scale Medical Multimodal Foundation Models (MMFMs). These models, known for their strong generalization capabilities and rich representational power, are increasingly being adapted to address a wide range of clinical tasks, from early diagnosis to personalized treatment strategies. This review offers a comprehensive analysis of recent developments in MMFMs, focusing on three key aspects: datasets, model architectures, and clinical applications. We also explore the challenges and opportunities in optimizing multimodal representations and discuss how these advancements are shaping the future of healthcare by enabling improved patient outcomes and more efficient clinical workflows.

Causal inference in the presence of intermediate variables is a challenging problem in many applications. Principal stratification (PS) provides a framework to estimate principal causal effects (PCE) in such settings. However, existing PS methods primarily focus on settings with binary intermediate variables. We propose a novel approach to estimate PCE with continuous intermediate variables in the context of stepped wedge cluster randomized trials (SW-CRTs). Our method leverages the time-varying treatment assignment in SW-CRTs to calibrate sensitivity parameters and identify the PCE under realistic assumptions. We demonstrate the application of our approach using data from a cohort SW-CRT evaluating the effect of a crowdsourcing intervention on HIV testing uptake among men who have sex with men in China, with social norms as a continuous intermediate variable. The proposed methodology expands the scope of PS to accommodate continuous variables and provides a practical tool for causal inference in SW-CRTs.

Human beings are social animals. How to equip 3D autonomous characters with similar social intelligence that can perceive, understand and interact with humans remains an open yet foundamental problem. In this paper, we introduce SOLAMI, the first end-to-end Social vision-Language-Action (VLA) Modeling framework for Immersive interaction with 3D autonomous characters. Specifically, SOLAMI builds 3D autonomous characters from three aspects: (1) Social VLA Architecture: We propose a unified social VLA framework to generate multimodal response (speech and motion) based on the user's multimodal input to drive the character for social interaction. (2) Interactive Multimodal Data: We present SynMSI, a synthetic multimodal social interaction dataset generated by an automatic pipeline using only existing motion datasets to address the issue of data scarcity. (3) Immersive VR Interface: We develop a VR interface that enables users to immersively interact with these characters driven by various architectures. Extensive quantitative experiments and user studies demonstrate that our framework leads to more precise and natural character responses (in both speech and motion) that align with user expectations with lower latency.

Simulating long-term human-scene interaction is a challenging yet fascinating task. Previous works have not effectively addressed the generation of long-term human scene interactions with detailed narratives for physics-based animation. This paper introduces a novel framework for the planning and controlling of long-horizon physical plausible human-scene interaction. On the one hand, films and shows with stylish human locomotions or interactions with scenes are abundantly available on the internet, providing a rich source of data for script planning. On the other hand, Large Language Models (LLMs) can understand and generate logical storylines. This motivates us to marry the two by using an LLM-based pipeline to extract scripts from videos, and then employ LLMs to imitate and create new scripts, capturing complex, time-series human behaviors and interactions with environments. By leveraging this, we utilize a dual-aware policy that achieves both language comprehension and scene understanding to guide character motions within contextual and spatial constraints. To facilitate training and evaluation, we contribute a comprehensive planning dataset containing diverse motion sequences extracted from real-world videos and expand them with large language models. We also collect and re-annotate motion clips from existing kinematic datasets to enable our policy learn diverse skills. Extensive experiments demonstrate the effectiveness of our framework in versatile task execution and its generalization ability to various scenarios, showing remarkably enhanced performance compared with existing methods. Our code and data will be publicly available soon.

Recent advancements in video generation have been greatly driven by video diffusion models, with camera motion control emerging as a crucial challenge in creating view-customized visual content. This paper introduces trajectory attention, a novel approach that performs attention along available pixel trajectories for fine-grained camera motion control. Unlike existing methods that often yield imprecise outputs or neglect temporal correlations, our approach possesses a stronger inductive bias that seamlessly injects trajectory information into the video generation process. Importantly, our approach models trajectory attention as an auxiliary branch alongside traditional temporal attention. This design enables the original temporal attention and the trajectory attention to work in synergy, ensuring both precise motion control and new content generation capability, which is critical when the trajectory is only partially available. Experiments on camera motion control for images and videos demonstrate significant improvements in precision and long-range consistency while maintaining high-quality generation. Furthermore, we show that our approach can be extended to other video motion control tasks, such as first-frame-guided video editing, where it excels in maintaining content consistency over large spatial and temporal ranges., Comment: Project Page: xizaoqu.github.io/trajattn/

Inexact proximal augmented Lagrangian methods (pALMs) are particularly appealing for tackling convex constrained optimization problems because of their elegant convergence properties and strong practical performance. To solve the associated pALM subproblems, efficient methods such as Newton-type methods are essential. Consequently, the effectiveness of the inexact pALM hinges on the error criteria used to control the inexactness when solving these subproblems. However, existing inexact pALMs either rely on absolute-type error criteria (which may complicate implementation by necessitating the pre-specification of an infinite sequence of error tolerance parameters) or require an additional correction step when using relative error criteria (which can potentially slow down the convergence of the pALM). To address this deficiency, this paper proposes ripALM, a relative-type inexact pALM, which can simplify practical implementation while preserving the appealing convergence properties of the classical absolute-type inexact pALM. We emphasize that ripALM is the first relative-type inexact version of the vanilla pALM with provable convergence guarantees. Numerical experiments on quadratically regularized optimal transport (OT) problems demonstrate the competitive efficiency of the proposed method compared to existing methods. As our analysis can be extended to a more general convex constrained problem setting, including other regularized OT problems, the proposed ripALM may provide broad applicability and has the potential to serve as a basic optimization tool.

Modern autonomous vehicle perception systems often struggle with occlusions and limited perception range. Previous studies have demonstrated the effectiveness of cooperative perception in extending the perception range and overcoming occlusions, thereby improving the safety of autonomous driving. In recent years, a series of cooperative perception datasets have emerged. However, these datasets only focus on camera and LiDAR, overlooking 4D Radar, a sensor employed in single-vehicle autonomous driving for robust perception in adverse weather conditions. In this paper, to bridge the gap of missing 4D Radar datasets in cooperative perception, we present V2X-Radar, the first large real-world multi-modal dataset featuring 4D Radar. Our V2X-Radar dataset is collected using a connected vehicle platform and an intelligent roadside unit equipped with 4D Radar, LiDAR, and multi-view cameras. The collected data includes sunny and rainy weather conditions, spanning daytime, dusk, and nighttime, as well as typical challenging scenarios. The dataset comprises 20K LiDAR frames, 40K camera images, and 20K 4D Radar data, with 350K annotated bounding boxes across five categories. To facilitate diverse research domains, we establish V2X-Radar-C for cooperative perception, V2X-Radar-I for roadside perception, and V2X-Radar-V for single-vehicle perception. We further provide comprehensive benchmarks of recent perception algorithms on the above three sub-datasets. The dataset and benchmark codebase will be available at \url{http://openmpd.com/column/V2X-Radar}., Comment: 11 pages, 5 figures

Reducing the scanning time of very-low field (VLF) magnetic resonance imaging (MRI) scanners, commonly employed for stroke diagnosis, can enhance patient comfort and operational efficiency. The conventional parallel imaging (PI) technique for high-field MRI should be tailored to apply here, considering the differences in the direction of the main magnetic field and the presence of noise. A VLF-specific PI algorithm and phased-array coil are proposed, marking the first application of PI in VLF MRI. Reconstruction quality is enhanced by denoising undersampled k-space data using a linear-prediction based Kalman filter. Subsequently, the denoised k-space data are nonlinearly mapped from the original space onto a high-dimensional feature space, utilizing a polynomial feature mapping defined nonlinear frame. Frame parameters are calculated using auto-calibration signals (ACS) from the center k-space, and missing phase-encoding lines in the original space are estimated using acquired lines in the feature space. An 8-channel phased-array coil, designed for a vertical main magnetic field, is decoupled using geometric overlap and a low input impedance (LII) preamplifier. Healthy volunteer head imaging experiments using the proposed PI technique exhibit the lowest mean-squared-error (MSE) value and the highest peak-signal-to-noise (PSNR) and structural similarity index (SSIM) values compared to two widely used PI methods. The proposed PI technique enables the VLF MRI scanner to achieve similar image quality and a 72.5% improvement in signal-to-noise ratio (SNR) compared to fully sampled images while requiring less than 50% of the scan time. We present a PI technique tailored for VLF MRI scanner for the first time, along with potential research direction to achieve greater reduction factor., Comment: Submitted to IEEE Transactions on Instrumentation and Measurement

This paper investigates the information-theoretic energy efficiency of intelligent reflecting surface (IRS)-aided wireless communication systems, taking into account the statistical quality-of-service (QoS) constraints on delay violation probabilities. Specifically, effective capacity is adopted to capture the maximum constant arrival rate that can be supported by a time-varying service process while fulfilling these statistical QoS requirements. We derive the minimum bit energy required for the IRS-aided wireless communication system under QoS constraints and analyze the spectral efficiency and energy efficiency tradeoff at low but nonzero signal-to-noise ratio (SNR) levels by also characterizing the wideband slope values. Our analysis demonstrates that the energy efficiency for the considered system under statistical QoS constraints can approach that for a system without QoS limitations in the low-SNR regime. Additionally, deploying a sufficiently large number of practical IRS reflecting elements can substantially reduce energy consumption required to achieve desired spectral efficiency performance in the low-power regime, even with limited bit-resolution phase shifters. Besides, we reveal that compared with the results applied to the low-power regime, higher effective capacity performance can be achieved in scenarios with sparse multipath fading while achieving the same minimum bit energy in the wideband regime.

Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV levels, it has become possible to generate muons in laser laboratories. In this work, we show the first proof of principle experiment for novel muon production with an ultra-short, high-intensity laser device through GeV electron beam bombardment on a lead converter target. The muon physical signal is confirmed by measuring its lifetime which is the first clear demonstration of laser-produced muons. Geant4 simulations were employed to investigate the photo-production, electro-production, and Bethe-Heitler processes response for muon generation and their subsequent detection. The results show that the dominant contributions of muons are attributed to the photo-production/electro-production and a significant yield of muons up to 0.01 $\mu$/$e^-$ out of the converter target could be achieved. This laser muon source features compact, ultra-short pulse and high flux. Moreover, its implementation in a small laser laboratory is relatively straightforward, significantly reducing the barriers to entry for research in areas such as muonic X-ray elemental analysis, muon spin spectroscopy and so on.

The spin correlation of back-to-back dihadron emerges in unpolarized high-energy collision, empowering unpolarized experiments to shed light on the spin-dependent fragmentation functions. This work investigates the transverse spin correlation of back-to-back dihadron in unpolarized $e^+e^-$, $pp$, and $\gamma p$ collisions, which serves as a novel probe of the chiral-odd fragmentation function $H_{1T}(z)$. We compute the transverse spin correlation at the partonic level and establish a connection with helicity amplitudes. Measuring this observable in future experiments can reveal valuable information on the hadronization of transversely polarized quarks., Comment: 13 pages, 6 figures

We report the discovery of a peculiar X-ray transient, EP240408a, by Einstein Probe (EP) and follow-up studies made with EP, Swift, NICER, GROND, ATCA and other ground-based multi-wavelength telescopes. The new transient was first detected with Wide-field X-ray Telescope (WXT) on board EP on April 8th, 2024, manifested in an intense yet brief X-ray flare lasting for 12 seconds. The flare reached a peak flux of 3.9x10^(-9) erg/cm2/s in 0.5-4 keV, about 300 times brighter than the underlying X-ray emission detected throughout the observation. Rapid and more precise follow-up observations by EP/FXT, Swift and NICER confirmed the finding of this new transient. Its X-ray spectrum is non-thermal in 0.5-10 keV, with a power-law photon index varying within 1.8-2.5. The X-ray light curve shows a plateau lasting for about 4 days, followed by a steep decay till becoming undetectable about 10 days after the initial detection. Based on its temporal property and constraints from previous EP observations, an unusual timescale in the range of 7-23 days is found for EP240408a, which is intermediate between the commonly found fast and long-term transients. No counterparts have been found in optical and near-infrared, with the earliest observation at 17 hours after the initial X-ray detection, suggestive of intrinsically weak emission in these bands. We demonstrate that the remarkable properties of EP240408a are inconsistent with any of the transient types known so far, by comparison with, in particular, jetted tidal disruption events, gamma-ray bursts, X-ray binaries and fast blue optical transients. The nature of EP240408a thus remains an enigma. We suggest that EP240408a may represent a new type of transients with intermediate timescales of the order of about 10 days. The detection and follow-ups of more of such objects are essential for revealing their origin., Comment: 25 pages, 11 figures

With the rapid development of Large language models (LLMs), understanding the capabilities of LLMs in identifying unsafe content has become increasingly important. While previous works have introduced several benchmarks to evaluate the safety risk of LLMs, the community still has a limited understanding of current LLMs' capability to recognize illegal and unsafe content in Chinese contexts. In this work, we present a Chinese safety benchmark (ChineseSafe) to facilitate research on the content safety of large language models. To align with the regulations for Chinese Internet content moderation, our ChineseSafe contains 205,034 examples across 4 classes and 10 sub-classes of safety issues. For Chinese contexts, we add several special types of illegal content: political sensitivity, pornography, and variant/homophonic words. Moreover, we employ two methods to evaluate the legal risks of popular LLMs, including open-sourced models and APIs. The results reveal that many LLMs exhibit vulnerability to certain types of safety issues, leading to legal risks in China. Our work provides a guideline for developers and researchers to facilitate the safety of LLMs. Our results are also available at https://huggingface.co/spaces/SUSTech/ChineseSafe-Benchmark.

Current exploration methods struggle to search for shops in unknown open-world environments due to a lack of prior knowledge and text recognition capabilities. Venue maps offer valuable information that can aid exploration planning by correlating scene signage with map data. However, the arbitrary shapes and styles of the text on signage, along with multi-view inconsistencies, pose significant challenges for accurate recognition by robots. Additionally, the discrepancies between real-world environments and venue maps hinder the incorporation of text information into planners. This paper introduces a novel signage-aware exploration system to address these challenges, enabling the robot to utilize venue maps effectively. We propose a signage understanding method that accurately detects and recognizes the text on signage using a diffusion-based text instance retrieval method combined with a 2D-to-3D semantic fusion strategy. Furthermore, we design a venue map-guided exploration-exploitation planner that balances exploration in unknown regions using a directional heuristic derived from venue maps with exploitation to get close and adjust orientation for better recognition. Experiments in large-scale shopping malls demonstrate our method's superior signage recognition accuracy and coverage efficiency, outperforming state-of-the-art scene text spotting methods and traditional exploration methods., Comment: 8 pages, 9 figures, 4 tables, under review

We report the discovery of a second optical flare that occurred in September 2021 in IRAS F01004-2237, where the first flare occurred in 2010 has been reported, and present a detailed analysis of multi-band data. The position of the flare coincides with the galaxy centre with a precision of 650 pc. The flare peaks in $\sim50$ days with an absolute magnitude of $\sim-21$ and fades in two years roughly following $L\propto t^{-5/3}$. It maintains a nearly constant blackbody temperature of $\sim$22,000 K in the late time. Its optical and UV spectra show hydrogen and helium broad emission lines with full width at half maxima of 7,000--21,000 km s$^{-1}$ and He II/H$\alpha$ ratio of 0.3--2.3. It shows weak X-ray emission relative to UV emission, with X-ray flares lasting for $<2-3$ weeks, during which the spectrum is soft with a power-law index $\Gamma=4.4^{+1.4}_{-1.3}$. These characters are consistent with a tidal disruption event (TDE), ruling out the possibilities of a supernova or an active galactic nuclei flare. With a TDE model, we infer a peak UV luminosity of $3.3\pm0.2\times10^{44}$ erg s$^{-1}$ and an energy budget of $4.5\pm0.2\times10^{51}$ erg. The two optical flares separated by $10.3\pm0.3$ years can be interpreted as repeating partial TDEs, double TDEs, or two independent TDEs. Although no definitive conclusion can be drawn, the partial TDEs interpretation predicts a third flare around 2033, and the independent TDEs interpretation predicts a high TDE rate of $\gtrsim10^{-2}$ yr$^{-1}$ in F01004-2237, both of which can be tested by future observations., Comment: 22 pages, 16 figures, 9 tables, accepted for publication in A&A

Galaxy clusters identified in optical imaging surveys suffer from projection effects: physically unassociated galaxies along a cluster's line of sight can be counted as its members and boost the observed richness (the number of cluster members). To model the impact projection on cluster cosmology analyses, we apply a halo occupation distribution model to N-body simulations to simulate the red galaxies contributing to cluster members, and we use the number of galaxies in a cylinder along the line-of-sight (counts-in-cylinders) to model the impact of projection on cluster richness. We compare three projection models: uniform, quadratic, and Gaussian, and we convert between them by matching their effective cylinder volumes. We validate our mock catalogs using SDSS redMaPPer data vectors, including cluster abundance vs. richness, stacked lensing signal, spectroscopic redshift distribution of member galaxies, and richness re-measured on a redshift grid. We find the former two are insensitive to the projection model, while the latter two favor a quadratic projection model with a width of 180 Mpc/h (equivalent to the volume of a uniform model with a width of 100 Mpc/h and a Gaussian model with a width of 110 Mpc/h, or a Gaussian redshift error of 0.04). Our framework provides an efficient and flexible way to model optical cluster data vectors, paving the way for a simulation-based joint analysis for clusters, galaxies, and shear., Comment: 12 pages, 9 figures

We present \textbf{Disco4D}, a novel Gaussian Splatting framework for 4D human generation and animation from a single image. Different from existing methods, Disco4D distinctively disentangles clothings (with Gaussian models) from the human body (with SMPL-X model), significantly enhancing the generation details and flexibility. It has the following technical innovations. \textbf{1)} Disco4D learns to efficiently fit the clothing Gaussians over the SMPL-X Gaussians. \textbf{2)} It adopts diffusion models to enhance the 3D generation process, \textit{e.g.}, modeling occluded parts not visible in the input image. \textbf{3)} It learns an identity encoding for each clothing Gaussian to facilitate the separation and extraction of clothing assets. Furthermore, Disco4D naturally supports 4D human animation with vivid dynamics. Extensive experiments demonstrate the superiority of Disco4D on 4D human generation and animation tasks. Our visualizations can be found in \url{https://disco-4d.github.io/}.

We construct a geometric realization of representations for $\text{PSL}(2, \mathbb{F}_p)$ by the defining ideals of rational models $\mathcal{L}(X(p))$ of modular curves $X(p)$ over $\mathbb{Q}$. Hence, for the irreducible representations of $\text{PSL}(2, \mathbb{F}_p)$, whose geometric realizations can be formulated in three different scenarios in the framework of Weil's Rosetta stone: number fields, curves over $\mathbb{F}_q$ and Riemann surfaces. In particular, we show that there exists a correspondence among the defining ideals of modular curves over $\mathbb{Q}$, reducible $\mathbb{Q}(\zeta_p)$-rational representations $\pi_p: \text{PSL}(2, \mathbb{F}_p) \rightarrow \text{Aut}(\mathcal{L}(X(p)))$ of $\text{PSL}(2, \mathbb{F}_p)$, and $\mathbb{Q}(\zeta_p)$-rational Galois representations $\rho_p: \text{Gal}(\overline{\mathbb{Q}}/\mathbb{Q}) \rightarrow \text{Aut}(\mathcal{L}(X(p)))$ as well as their modular and surjective realization. This leads to a new viewpoint on the last mathematical testament of Galois by Galois representations arising from the defining ideals of modular curves, which leads to a connection with Klein's elliptic modular functions. It is a nonlinear and anabelian counterpart of the global Langlands correspondence among the $\ell$-adic \'{e}tale cohomology of modular curves over $\mathbb{Q}$, i.e., Grothendieck motives ($\ell$-adic system), automorphic representations of $\text{GL}(2, \mathbb{Q})$ and $\ell$-adic representations., Comment: 304 pages

Graph representation learning has shown superior performance in numerous real-world applications, such as finance and social networks. Nevertheless, most existing works might make discriminatory predictions due to insufficient attention to fairness in their decision-making processes. This oversight has prompted a growing focus on fair representation learning. Among recent explorations on fair representation learning, prior works based on adversarial learning usually induce unstable or counterproductive performance. To achieve fairness in a stable manner, we present the design and implementation of GRAFair, a new framework based on a variational graph auto-encoder. The crux of GRAFair is the Conditional Fairness Bottleneck, where the objective is to capture the trade-off between the utility of representations and sensitive information of interest. By applying variational approximation, we can make the optimization objective tractable. Particularly, GRAFair can be trained to produce informative representations of tasks while containing little sensitive information without adversarial training. Experiments on various real-world datasets demonstrate the effectiveness of our proposed method in terms of fairness, utility, robustness, and stability.

Large language models (LLMs) have demonstrated prowess in a wide range of tasks. However, many LLMs exhibit significant performance discrepancies between high- and low-resource languages. To mitigate this challenge, we present FuxiTranyu, an open-source multilingual LLM, which is designed to satisfy the need of the research community for balanced and high-performing multilingual capabilities. The base model, FuxiTranyu-8B, features 8 billion parameters and is trained from scratch on meticulously balanced multilingual data that contains 600 billion tokens covering 43 natural languages and 16 programming languages. We also develop two instruction-tuned models: FuxiTranyu-8B-SFT which is fine-tuned on a diverse multilingual instruction dataset, and FuxiTranyu-8B-DPO which is further refined with DPO on a preference dataset for enhanced alignment ability. Extensive experiments on a wide range of multilingual benchmarks demonstrate the competitive performance of FuxiTranyu against existing multilingual LLMs, e.g., BLOOM-7B, PolyLM-13B, and Mistral-7B-Instruct. Both neuron and representation interpretability analyses reveal that FuxiTranyu achieves consistent multilingual representations across languages. To promote further research into multilingual LLMs, we release both the base and instruction-tuned FuxiTranyu models together with 58 pre-training checkpoints at HuggingFace (see https://huggingface.co/TJUNLP/FuxiTranyu-8B) and Github (see https://github.com/tjunlp-lab/FuxiTranyu)., Comment: Accepted to EMNLP 2024 Industry Track

Proof-of-stake (PoS) blockchains require validators to lock their tokens as collateral, slashing these tokens if they are identified as protocol violators. PoS chains have mostly been secured by their native tokens. However, using only the native token upper-bounds the value eligible for staking by the market capitalization of the native token. In contrast, the remote staking of another crypto asset from a provider chain provides an avenue to improve the consumer chain's economic security. In this paper, we present the first known remote staking protocols with guaranteed optimal economic safety: whenever there is a safety violation on the consumer chain, at least one third of the provider's stake securing the consumer chain is slashed. To achieve this goal for a broad range of provider and consumer chains, two independent contributions are made: 1) a cryptographic protocol to slash stake even without smart contracts on the provider chain; 2) a secure unbonding protocol that ensures slashing before the stake is unbonded on the provider chain if there is safety violation on the consumer chain. A major use case of this work is when the provider chain is Bitcoin, making available an asset worth more than 1.7 trillion USD to secure PoS chains. Such a Bitcoin staking protocol has been launched on the Mainnet in August 2024 and has accumulated 2.1 billion USD worth of stake thus far.

Audio-driven 3D facial animation aims to map input audio to realistic facial motion. Despite significant progress, limitations arise from inconsistent 3D annotations, restricting previous models to training on specific annotations and thereby constraining the training scale. In this work, we present UniTalker, a unified model featuring a multi-head architecture designed to effectively leverage datasets with varied annotations. To enhance training stability and ensure consistency among multi-head outputs, we employ three training strategies, namely, PCA, model warm-up, and pivot identity embedding. To expand the training scale and diversity, we assemble A2F-Bench, comprising five publicly available datasets and three newly curated datasets. These datasets contain a wide range of audio domains, covering multilingual speech voices and songs, thereby scaling the training data from commonly employed datasets, typically less than 1 hour, to 18.5 hours. With a single trained UniTalker model, we achieve substantial lip vertex error reductions of 9.2% for BIWI dataset and 13.7% for Vocaset. Additionally, the pre-trained UniTalker exhibits promise as the foundation model for audio-driven facial animation tasks. Fine-tuning the pre-trained UniTalker on seen datasets further enhances performance on each dataset, with an average error reduction of 6.3% on A2F-Bench. Moreover, fine-tuning UniTalker on an unseen dataset with only half the data surpasses prior state-of-the-art models trained on the full dataset. The code and dataset are available at the project page https://github.com/X-niper/UniTalker.

This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines non-differentiable computation of hyperplane intersection through duality transform with differentiable optimization for vertex positioning with three-plane intersection, enabling gradient-based optimization without the need for 3D implicit fields. This allows for efficient shape representation across a range of applications, from shape parsing to compact mesh reconstruction. This work not only overcomes the challenges of previous approaches but also sets a new standard for representing shapes with convex polyhedra., Comment: ECCV2024 https://github.com/kimren227/DiffConvex

Ultrasound computed tomography (USCT) is a promising technique that achieves superior medical imaging reconstruction resolution by fully leveraging waveform information, outperforming conventional ultrasound methods. Despite its advantages, high-quality USCT reconstruction relies on extensive data acquisition by a large number of transducers, leading to increased costs, computational demands, extended patient scanning times, and manufacturing complexities. To mitigate these issues, we propose a new USCT method called APS-USCT, which facilitates imaging with sparse data, substantially reducing dependence on high-cost dense data acquisition. Our APS-USCT method consists of two primary components: APS-wave and APS-FWI. The APS-wave component, an encoder-decoder system, preprocesses the waveform data, converting sparse data into dense waveforms to augment sample density prior to reconstruction. The APS-FWI component, utilizing the InversionNet, directly reconstructs the speed of sound (SOS) from the ultrasound waveform data. We further improve the model's performance by incorporating Squeeze-and-Excitation (SE) Blocks and source encoding techniques. Testing our method on a breast cancer dataset yielded promising results. It demonstrated outstanding performance with an average Structural Similarity Index (SSIM) of 0.8431. Notably, over 82% of samples achieved an SSIM above 0.8, with nearly 61% exceeding 0.85, highlighting the significant potential of our approach in improving USCT image reconstruction by efficiently utilizing sparse data., Comment: MICCAI

As Artificial Intelligence (AI) increasingly integrates into our daily lives, fairness has emerged as a critical concern, particularly in medical AI, where datasets often reflect inherent biases due to social factors like the underrepresentation of marginalized communities and socioeconomic barriers to data collection. Traditional approaches to mitigating these biases have focused on data augmentation and the development of fairness-aware training algorithms. However, this paper argues that the architecture of neural networks, a core component of Machine Learning (ML), plays a crucial role in ensuring fairness. We demonstrate that addressing fairness effectively requires a holistic approach that simultaneously considers data, algorithms, and architecture. Utilizing Automated ML (AutoML) technology, specifically Neural Architecture Search (NAS), we introduce a novel framework, BiaslessNAS, designed to achieve fair outcomes in analyzing skin lesion datasets. BiaslessNAS incorporates fairness considerations at every stage of the NAS process, leading to the identification of neural networks that are not only more accurate but also significantly fairer. Our experiments show that BiaslessNAS achieves a 2.55% increase in accuracy and a 65.50% improvement in fairness compared to traditional NAS methods, underscoring the importance of integrating fairness into neural network architecture for better outcomes in medical AI applications., Comment: MICCAI

Enabling robotic agents to perform complex long-horizon tasks has been a long-standing goal in robotics and artificial intelligence (AI). Despite the potential shown by large language models (LLMs), their planning capabilities remain limited to short-horizon tasks and they are unable to replace the symbolic planning approach. Symbolic planners, on the other hand, may encounter execution errors due to their common assumption of complete domain knowledge which is hard to manually prepare for an open-world setting. In this paper, we introduce a Language-Augmented Symbolic Planner (LASP) that integrates pre-trained LLMs to enable conventional symbolic planners to operate in an open-world environment where only incomplete knowledge of action preconditions, objects, and properties is initially available. In case of execution errors, LASP can utilize the LLM to diagnose the cause of the error based on the observation and interact with the environment to incrementally build up its knowledge base necessary for accomplishing the given tasks. Experiments demonstrate that LASP is proficient in solving planning problems in the open-world setting, performing well even in situations where there are multiple gaps in the knowledge., Comment: Accepted by Robotics: Science and Systems (RSS) 2024

Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods mainly address one or several classes of specific safety requirement scenario problems and cannot be applied to arbitrary safety requirement scenarios. In addition, the optimization objectives of existing reinforcement learning algorithms are misaligned with the task requirements. Based on the need to address these issues, we propose $\mathrm{E^{2}CFD}$, an effective and efficient cost function design framework. $\mathrm{E^{2}CFD}$ leverages the capabilities of a large language model (LLM) to comprehend various safety scenarios and generate corresponding cost functions. It incorporates the \textit{fast performance evaluation (FPE)} method to facilitate rapid and iterative updates to the generated cost function. Through this iterative process, $\mathrm{E^{2}CFD}$ aims to obtain the most suitable cost function for policy training, tailored to the specific tasks within the safety scenario. Experiments have proven that the performance of policies trained using this framework is superior to traditional safe reinforcement learning algorithms and policies trained with carefully designed cost functions.

Fabric manipulation dynamically is commonly seen in manufacturing and domestic settings. While dynamically manipulating a fabric piece to reach a target state is highly efficient, this task presents considerable challenges due to the varying properties of different fabrics, complex dynamics when interacting with environments, and meeting required goal conditions. To address these challenges, we present \textit{One Fling to Goal}, an algorithm capable of handling fabric pieces with diverse shapes and physical properties across various scenarios. Our method learns a graph-based dynamics model equipped with environmental awareness. With this dynamics model, we devise a real-time controller to enable high-speed fabric manipulation in one attempt, requiring less than 3 seconds to finish the goal-conditioned task. We experimentally validate our method on a goal-conditioned manipulation task in five diverse scenarios. Our method significantly improves this goal-conditioned task, achieving an average error of 13.2mm in complex scenarios. Our method can be seamlessly transferred to real-world robotic systems and generalized to unseen scenarios in a zero-shot manner.

LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the features of a single central voxel as an object proxy, or treat an aggregated cluster of foreground points as an object proxy. However, the former lacks the ability to aggregate contextual information, resulting in insufficient information expression in object proxies. The latter relies on multi-stage pipelines and auxiliary tasks, which reduce the inference speed. To maintain the efficiency of the sparse framework while fully aggregating contextual information, in this work, we propose SparseDet which designs sparse queries as object proxies. It introduces two key modules, the Local Multi-scale Feature Aggregation (LMFA) module and the Global Feature Aggregation (GFA) module, aiming to fully capture the contextual information, thereby enhancing the ability of the proxies to represent objects. Where LMFA sub-module achieves feature fusion across different scales for sparse key voxels %which does this through via coordinate transformations and using nearest neighbor relationships to capture object-level details and local contextual information, GFA sub-module uses self-attention mechanisms to selectively aggregate the features of the key voxels across the entire scene for capturing scene-level contextual information. Experiments on nuScenes and KITTI demonstrate the effectiveness of our method. Specifically, on nuScene, SparseDet surpasses the previous best sparse detector VoxelNeXt by 2.2\% mAP with 13.5 FPS, and on KITTI, it surpasses VoxelNeXt by 1.12\% $\mathbf{AP_{3D}}$ on hard level tasks with 17.9 FPS., Comment: arXiv admin note: text overlap with arXiv:2401.02702

Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because these assets always need to be converted to meshes for 3D industry applications, and the meshes produced by current mesh extraction methods are significantly inferior to Artist-Created Meshes (AMs), i.e., meshes created by human artists. Specifically, current mesh extraction methods rely on dense faces and ignore geometric features, leading to inefficiencies, complicated post-processing, and lower representation quality. To address these issues, we introduce MeshAnything, a model that treats mesh extraction as a generation problem, producing AMs aligned with specified shapes. By converting 3D assets in any 3D representation into AMs, MeshAnything can be integrated with various 3D asset production methods, thereby enhancing their application across the 3D industry. The architecture of MeshAnything comprises a VQ-VAE and a shape-conditioned decoder-only transformer. We first learn a mesh vocabulary using the VQ-VAE, then train the shape-conditioned decoder-only transformer on this vocabulary for shape-conditioned autoregressive mesh generation. Our extensive experiments show that our method generates AMs with hundreds of times fewer faces, significantly improving storage, rendering, and simulation efficiencies, while achieving precision comparable to previous methods., Comment: Project Page: https://buaacyw.github.io/mesh-anything/ Code: https://github.com/buaacyw/MeshAnything

In this paper, we consider a class of difference-of-convex (DC) optimization problems, where the global Lipschitz gradient continuity assumption on the smooth part of the objective function is not required. Such problems are prevalent in many contemporary applications such as compressed sensing, statistical regression, and machine learning, and can be solved by a general Bregman proximal DC algorithm (BPDCA). However, the existing BPDCA is developed based on the stringent requirement that the involved subproblems must be solved exactly, which is often impractical and limits the applicability of the BPDCA. To facilitate the practical implementations and wider applications of the BPDCA, we develop an inexact Bregman proximal difference-of-convex algorithm (iBPDCA) by incorporating two types of relative-type stopping criteria for solving the subproblems. The proposed inexact framework has considerable flexibility to encompass many existing exact and inexact methods, and can accommodate different types of errors that may occur when solving the subproblem. This enables the potential application of our inexact framework across different DC decompositions to facilitate the design of a more efficient DCA scheme in practice. The global subsequential convergence and the global sequential convergence of our iBPDCA are established under suitable conditions including the Kurdyka-{\L}ojasiewicz property. Some numerical experiments on the $\ell_{1-2}$ regularized least squares problem and the constrained $\ell_{1-2}$ sparse optimization problem are conducted to show the superior performance of our iBPDCA in comparison to existing algorithms. These results also empirically verify the necessity of developing different types of stopping criteria to facilitate the efficient computation of the subproblem in each iteration of our iBPDCA.