Search

Large Language Models (LLMs), with gradually improving reading comprehension and reasoning capabilities, are being applied to a range of complex language tasks, including the automatic generation of language data for various purposes. However, research on applying LLMs for automatic data generation in low-resource languages like Vietnamese is still underdeveloped and lacks comprehensive evaluation. In this paper, we explore the use of LLMs for automatic data generation for the Vietnamese fact-checking task, which faces significant data limitations. Specifically, we focus on fact-checking data where claims are synthesized from multiple evidence sentences to assess the information synthesis capabilities of LLMs. We develop an automatic data construction process using simple prompt techniques on LLMs and explore several methods to improve the quality of the generated data. To evaluate the quality of the data generated by LLMs, we conduct both manual quality assessments and performance evaluations using language models. Experimental results and manual evaluations illustrate that while the quality of the generated data has significantly improved through fine-tuning techniques, LLMs still cannot match the data quality produced by humans.

In this letter, we consider effective field theories for light fields transforming under the fundamental or adjoint representation of a continuous group. We demonstrate that in the presence of gravity, crossing symmetry combined with two subtraction sum rules, leads to stringent constraints on the spectrum of its ultraviolet (UV) completion. Such constraints come in the form of necessary conditions on the symmetry group irreps of the UV states. This is in sharp contrast with non-gravitational theories where anything goes. Beautifully, the graviton pole is the anchor of our argument, not an obstruction. Using numerical methods, we also demonstrate that the massless spin-2 must be a singlet under said symmetry group., Comment: 5 pages + appendix, 1 figure

In this paper we define absorptive Compton amplitudes, which captures the absorption factor for waves of spin-weight-$s$ scattering in black hole perturbation theory. At the leading order, in the $G M \omega$ expansion, such amplitudes are purely imaginary and expressible as contact terms. Equipped with these amplitudes we compute the mass change in black hole scattering events via Kosower-Maybee-O'Connell formalism, where the rest mass of Schwarzschild/Kerr black hole is modified due to absorption of gravitational, electromagnetic, or scalar fields sourced by other compact object. We reproduced the power loss previously computed in the post-Newtonian expansion. The results presented here hold for similar mass ratios and generic spin orientation, while keeping the Kerr spin parameter to lie in the physical region $\chi \le 1$., Comment: 25 pages, 3 figures

We present a novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases. Our method is adaptable to any odometry input and leverages GPU-accelerated processes for planar extraction, enabling the rapid generation of globally consistent semantic maps. We utilize an anisotropic diffusion filter on depth images to effectively minimize noise from gradient jumps while preserving essential edge details, enhancing normal vector images' accuracy and smoothness. Both the anisotropic diffusion and the RANSAC-based plane extraction processes are optimized for parallel processing on GPUs, significantly enhancing computational efficiency. Our approach achieves real-time performance, processing single frames at rates exceeding $30~Hz$, which facilitates detailed plane extraction and map management swiftly and efficiently. Extensive testing underscores the algorithm's capabilities in real-time scenarios and demonstrates its practical application in humanoid robot gait planning, significantly improving its ability to navigate dynamic environments., Comment: Accepted by The 2024 IEEE-RAS International Conference on Humanoid Robots. The code: https://github.com/BTFrontier/polygon_mapping

Updates of extensive Internet of Things (IoT) data are critical to the immersion of vehicular metaverse services. However, providing high-quality and sustainable data in unstable and resource-constrained vehicular networks remains a significant challenge. To address this problem, we put forth a novel immersion-aware model trading framework that incentivizes metaverse users (MUs) to contribute learning models trained by their latest local data for augmented reality (AR) services in the vehicular metaverse, while preserving their privacy through federated learning. To comprehensively evaluate the contribution of locally trained learning models provided by MUs to AR services, we design a new immersion metric that captures service immersion by considering the freshness and accuracy of learning models, as well as the amount and potential value of raw data used for training. We model the trading interactions between metaverse service providers (MSPs) and MUs as an equilibrium problem with equilibrium constraints (EPEC) to analyze and balance their costs and gains. Moreover, considering dynamic network conditions and privacy concerns, we formulate the reward decisions of MSPs as a multi-agent Markov decision process. Then, a fully distributed dynamic reward method based on deep reinforcement learning is presented, which operates without any private information about MUs and other MSPs. Experimental results demonstrate that the proposed framework can effectively provide higher-value models for object detection and classification in AR services on real AR-related vehicle datasets compared to benchmark schemes.

This paper conducts a comprehensive study of the learning curves of kernel ridge regression (KRR) under minimal assumptions. Our contributions are three-fold: 1) we analyze the role of key properties of the kernel, such as its spectral eigen-decay, the characteristics of the eigenfunctions, and the smoothness of the kernel; 2) we demonstrate the validity of the Gaussian Equivalent Property (GEP), which states that the generalization performance of KRR remains the same when the whitened features are replaced by standard Gaussian vectors, thereby shedding light on the success of previous analyzes under the Gaussian Design Assumption; 3) we derive novel bounds that improve over existing bounds across a broad range of setting such as (in)dependent feature vectors and various combinations of eigen-decay rates in the over/underparameterized regimes.

We develop an on-shell approach to study black hole mergers. Since, asymptotically, the initial and final states can be described by point-like spinning particles, we propose a massive three-point amplitude for the merger of two Schwarzschild black holes into a Kerr black hole. This three-point amplitude and the spectral function of the final state are fully determined by kinematics and the model-independent input about the black hole merger which is described by a complete absorption process. Using the Kosower-Maybee-O'Connell (KMOC) formalism, we then reproduce the classical conservation laws for momentum and angular momentum after the merger. As an application, we use the proposed three-point to compute the graviton emission amplitude, from which we extract the merger waveform to all orders in spin but leading in gravitational coupling. Up to sub-subleading order in spin, this matches the classical soft graviton theorem. We conclude with a comparison to black hole perturbation theory, which gives complementary amplitudes which are non-perturbative in the gravitational coupling but to leading order in the extreme mass ratio limit. This also highlights how boundary conditions on a Schwarzschild background can be used to rederive the proposed on-shell amplitudes for merger processes., Comment: 44 pages

Diffusion models have achieved unprecedented performance in image generation, yet they suffer from slow inference due to their iterative sampling process. To address this, early-exiting has recently been proposed, where the depth of the denoising network is made adaptive based on the (estimated) difficulty of each sampling step. Here, we discover an interesting "phase transition" in the sampling process of current adaptive diffusion models: the denoising network consistently exits early during the initial sampling steps, until it suddenly switches to utilizing the full network. Based on this, we propose accelerating generation by employing a shallower denoising network in the initial sampling steps and a deeper network in the later steps. We demonstrate empirically that our dual-backbone approach, DuoDiff, outperforms existing early-exit diffusion methods in both inference speed and generation quality. Importantly, DuoDiff is easy to implement and complementary to existing approaches for accelerating diffusion., Comment: Accepted to NeurIPS, see https://openreview.net/forum?id=G7E4tNmmHD

The novel series of hole-doped quadruple manganite perovskites Hg$_{1-x}$Na$_x$Mn$_3$Mn$_4$O$_{12}$ (HNMO) has been synthesized and its charge and orbital order behavior investigated through high-resolution synchrotron powder x-ray diffraction techniques. Through careful Rietveld refinements of structural models $via$ symmetry-motivated approaches, we show that the ground state of HNMO compositions adopts a polar $G$-type charge and orbital ordered state, which is rare in manganite perovskites, and is robust as a sole phase up to a critical doping level. Upon this critical doping, coincident with that in which colossal magnetoresistance (CMR) is maximal in canonical manganite perovskites, electronic phase separation occurs between $G$-type and orbital order with charge disorder-type states. The latter state has recently been identified in Ca$_{1-x}$Na$_x$Mn$_3$Mn$_4$O$_{12}$ perovskites, and proposed to be the competing insulating state from which CMR phenomena emerges. We show the mechanism for the formation of the $G$-type state is due to charge transfer processes which may occur through a coupling of distortions involving structural and charge and orbital degrees of freedom, ultimately driving the polar ground state through an improper-like ferroelectric polarization mechanism. These results will act as an important recipe for designing novel ferroelectric-active materials, in addition to expanding the richness of charge and orbital ordered states in manganite perovskites., Comment: 11 pages, 8 figures

Lean Methodology for Garment Modernization. This article presents the lean methodology for modernizing garment manufacturing, focusing on lean thinking, lean practices, automation development, VSM, and CRP, and how to integrate them effectively. While isolated automation of specific operations can improve efficiency and reduce cycle time, it does not necessarily enhance overall garment output and efficiency. To achieve these broader improvements, it is essential to consider the entire production line and process using VSM and CRP to optimize production and center balance. This approach can increase efficiency, and reduce manufacturing costs, labor time, and lead time, ultimately adding value to the company and factory., Comment: 11 pages,7 Figures

This research investigates the classification of Environmental, Social, and Governance (ESG) information within textual disclosures. The aim is to develop and evaluate binary classification models capable of accurately identifying and categorizing E, S and G-related content respectively. The motivation for this research stems from the growing importance of ESG considerations in investment decisions and corporate accountability. Accurate and efficient classification of ESG information is crucial for stakeholders to understand the impact of companies on sustainability and to make informed decisions. The research uses a quantitative approach involving data collection, data preprocessing, and the development of ESG-focused Large Language Models (LLMs) and traditional machine learning (Support Vector Machines, XGBoost) classifiers. Performance evaluation guides iterative refinement until satisfactory metrics are achieved. The research compares traditional machine learning techniques (Support Vector Machines, XGBoost), state-of-the-art language model (FinBERT-ESG) and fine-tuned LLMs like Llama 2, by employing standard Natural Language Processing performance metrics such as accuracy, precision, recall, F1-score. A novel fine-tuning method, Qlora, is applied to LLMs, resulting in significant performance improvements across all ESG domains. The research also develops domain-specific fine-tuned models, such as EnvLlama 2-Qlora, SocLlama 2-Qlora, and GovLlama 2-Qlora, which demonstrate impressive results in ESG text classification., Comment: 56 pages, 9 figures

Underwater images often suffer from quality degradation due to absorption and scattering effects. Most existing underwater image enhancement algorithms produce a single, fixed-color image, limiting user flexibility and application. To address this limitation, we propose a method called \textit{ColorCode}, which enhances underwater images while offering a range of controllable color outputs. Our approach involves recovering an underwater image to a reference enhanced image through supervised training and decomposing it into color and content codes via self-reconstruction and cross-reconstruction. The color code is explicitly constrained to follow a Gaussian distribution, allowing for efficient sampling and interpolation during inference. ColorCode offers three key features: 1) color enhancement, producing an enhanced image with a fixed color; 2) color adaptation, enabling controllable adjustments of long-wavelength color components using guidance images; and 3) color interpolation, allowing for the smooth generation of multiple colors through continuous sampling of the color code. Quantitative and visual evaluations on popular and challenging benchmark datasets demonstrate the superiority of ColorCode over existing methods in providing diverse, controllable, and color-realistic enhancement results. The source code is available at https://github.com/Xiaofeng-life/ColorCode.

Adversarial training has achieved remarkable advancements in defending against adversarial attacks. Among them, fast adversarial training (FAT) is gaining attention for its ability to achieve competitive robustness with fewer computing resources. Existing FAT methods typically employ a uniform strategy that optimizes all training data equally without considering the influence of different examples, which leads to an imbalanced optimization. However, this imbalance remains unexplored in the field of FAT. In this paper, we conduct a comprehensive study of the imbalance issue in FAT and observe an obvious class disparity regarding their performances. This disparity could be embodied from a perspective of alignment between clean and robust accuracy. Based on the analysis, we mainly attribute the observed misalignment and disparity to the imbalanced optimization in FAT, which motivates us to optimize different training data adaptively to enhance robustness. Specifically, we take disparity and misalignment into consideration. First, we introduce self-knowledge guided regularization, which assigns differentiated regularization weights to each class based on its training state, alleviating class disparity. Additionally, we propose self-knowledge guided label relaxation, which adjusts label relaxation according to the training accuracy, alleviating the misalignment and improving robustness. By combining these methods, we formulate the Self-Knowledge Guided FAT (SKG-FAT), leveraging naturally generated knowledge during training to enhance the adversarial robustness without compromising training efficiency. Extensive experiments on four standard datasets demonstrate that the SKG-FAT improves the robustness and preserves competitive clean accuracy, outperforming the state-of-the-art methods., Comment: 13 pages

Current speech-based LLMs are predominantly trained on extensive ASR and TTS datasets, excelling in tasks related to these domains. However, their ability to handle direct speech-to-speech conversations remains notably constrained. These models often rely on an ASR-to-TTS chain-of-thought pipeline, converting speech into text for processing before generating audio responses, which introduces latency and loses audio features. We propose a method that implicitly internalizes ASR chain of thought into a speech LLM, enhancing its native speech understanding capabilities. Our approach reduces latency and improves the model's native understanding of speech, paving the way for more efficient and natural real-time audio interactions. We also release a large-scale synthetic conversational dataset to facilitate further research., Comment: Updated for reviewer comments

Ultrasound curve angle (UCA) measurement provides a radiation-free and reliable evaluation for scoliosis based on ultrasound imaging. However, degraded image quality, especially in difficult-to-image patients, can prevent clinical experts from making confident measurements, even leading to misdiagnosis. In this paper, we propose a multi-stage image enhancement framework that models high-quality image distribution via a diffusion-based model. Specifically, we integrate the underlying morphological information from images taken at different depths of the 3D volume to calibrate the reverse process toward high-quality and high-fidelity image generation. This is achieved through a fusion operation with a learnable tuner module that learns the multi-to-one mapping from multi-depth to high-quality images. Moreover, the separate learning of the high-quality image distribution and the spinal features guarantees the preservation of consistent spinal pose descriptions in the generated images, which is crucial in evaluating spinal deformities. Remarkably, our proposed enhancement algorithm significantly outperforms other enhancement-based methods on ultrasound images in terms of image quality. Ultimately, we conduct the intra-rater and inter-rater measurements of UCA and higher ICC (0.91 and 0.89 for thoracic and lumbar angles) on enhanced images, indicating our method facilitates the measurement of ultrasound curve angles and offers promising prospects for automated scoliosis diagnosis.

Thanks to advancements in deep learning, speech generation systems now power a variety of real-world applications, such as text-to-speech for individuals with speech disorders, voice chatbots in call centers, cross-linguistic speech translation, etc. While these systems can autonomously generate human-like speech and replicate specific voices, they also pose risks when misused for malicious purposes. This motivates the research community to develop models for detecting synthesized speech (e.g., fake speech) generated by deep-learning-based models, referred to as the Deepfake Speech Detection task. As the Deepfake Speech Detection task has emerged in recent years, there are not many survey papers proposed for this task. Additionally, existing surveys for the Deepfake Speech Detection task tend to summarize techniques used to construct a Deepfake Speech Detection system rather than providing a thorough analysis. This gap motivated us to conduct a comprehensive survey, providing a critical analysis of the challenges and developments in Deepfake Speech Detection. Our survey is innovatively structured, offering an in-depth analysis of current challenge competitions, public datasets, and the deep-learning techniques that provide enhanced solutions to address existing challenges in the field. From our analysis, we propose hypotheses on leveraging and combining specific deep learning techniques to improve the effectiveness of Deepfake Speech Detection systems. Beyond conducting a survey, we perform extensive experiments to validate these hypotheses and propose a highly competitive model for the task of Deepfake Speech Detection. Given the analysis and the experimental results, we finally indicate potential and promising research directions for the Deepfake Speech Detection task., Comment: Journal preprint

Finger vein recognition technology has become one of the primary solutions for high-security identification systems. However, it still has information leakage problems, which seriously jeopardizes users privacy and anonymity and cause great security risks. In addition, there is no work to consider a fully integrated secure finger vein recognition system. So, different from the previous systems, we integrate preprocessing and template protection into an integrated deep learning model. We propose an end-to-end cancelable finger vein network (CFVNet), which can be used to design an secure finger vein recognition system.It includes a plug-and-play BWR-ROIAlign unit, which consists of three sub-modules: Localization, Compression and Transformation. The localization module achieves automated localization of stable and unique finger vein ROI. The compression module losslessly removes spatial and channel redundancies. The transformation module uses the proposed BWR method to introduce unlinkability, irreversibility and revocability to the system. BWR-ROIAlign can directly plug into the model to introduce the above features for DCNN-based finger vein recognition systems. We perform extensive experiments on four public datasets to study the performance and cancelable biometric attributes of the CFVNet-based recognition system. The average accuracy, EERs and Dsys on the four datasets are 99.82%, 0.01% and 0.025, respectively, and achieves competitive performance compared with the state-of-the-arts.

Learning-based methods for underwater image enhancement (UWIE) have undergone extensive exploration. However, learning-based models are usually vulnerable to adversarial examples so as the UWIE models. To the best of our knowledge, there is no comprehensive study on the adversarial robustness of UWIE models, which indicates that UWIE models are potentially under the threat of adversarial attacks. In this paper, we propose a general adversarial attack protocol. We make a first attempt to conduct adversarial attacks on five well-designed UWIE models on three common underwater image benchmark datasets. Considering the scattering and absorption of light in the underwater environment, there exists a strong correlation between color correction and underwater image enhancement. On the basis of that, we also design two effective UWIE-oriented adversarial attack methods Pixel Attack and Color Shift Attack targeting different color spaces. The results show that five models exhibit varying degrees of vulnerability to adversarial attacks and well-designed small perturbations on degraded images are capable of preventing UWIE models from generating enhanced results. Further, we conduct adversarial training on these models and successfully mitigated the effectiveness of adversarial attacks. In summary, we reveal the adversarial vulnerability of UWIE models and propose a new evaluation dimension of UWIE models.

We show that if $\mathcal{A} \subset {[n] \choose n/2}$ with measure bounded away from zero and from one, then the $\Omega(\sqrt{n})$-iterated upper shadows of $\mathcal{A}$ and $\mathcal{A}^c$ intersect in a set of positive measure. This confirms (in a strong form) a conjecture of Friedgut. It can be seen as a stability result for the Kruskal--Katona theorem., Comment: Minor corrections. 8 pages

Objective. (1) To assess whether neural tissue structure and biomechanics could predict functional loss in glaucoma; (2) To evaluate the importance of biomechanics in making such predictions. Design, Setting and Participants. We recruited 238 glaucoma subjects. For one eye of each subject, we imaged the optic nerve head (ONH) using spectral-domain OCT under the following conditions: (1) primary gaze and (2) primary gaze with acute IOP elevation. Main Outcomes: We utilized automatic segmentation of optic nerve head (ONH) tissues and digital volume correlation (DVC) analysis to compute intraocular pressure (IOP)-induced neural tissue strains. A robust geometric deep learning approach, known as Point-Net, was employed to predict the full Humphrey 24-2 pattern standard deviation (PSD) maps from ONH structural and biomechanical information. For each point in each PSD map, we predicted whether it exhibited no defect or a PSD value of less than 5%. Predictive performance was evaluated using 5-fold cross-validation and the F1-score. We compared the model's performance with and without the inclusion of IOP-induced strains to assess the impact of biomechanics on prediction accuracy. Results: Integrating biomechanical (IOP-induced neural tissue strains) and structural (tissue morphology and neural tissues thickness) information yielded a significantly better predictive model (F1-score: 0.76+-0.02) across validation subjects, as opposed to relying only on structural information, which resulted in a significantly lower F1-score of 0.71+-0.02 (p < 0.05). Conclusion: Our study has shown that the integration of biomechanical data can significantly improve the accuracy of visual field loss predictions. This highlights the importance of the biomechanics-function relationship in glaucoma, and suggests that biomechanics may serve as a crucial indicator for the development and progression of glaucoma., Comment: 19 pages, 2 figures

Vacuum Suction Grabbing Technology. The primary objective of this study was to design the grabbing technique used to determine the vacuum suction gripper and its design parameters for the pocket welting operation in apparel manufacturing. It presents the application of vacuum suction in grabbing technology, a technique that has revolutionized the handling and manipulation to grasp the various fabric materials in a range of garment industries. Vacuum suction, being non-intrusive and non-invasive, offers several advantages compared to traditional grabbing methods. It is particularly useful in scenarios where soft woven fabric and air-impermeable fabric items need to be handled with utmost care. The paper delves into the working principles of vacuum suction, its various components, and the underlying physics involved. Furthermore, it explores the various applications of vacuum suction in the garment industry into the automation exploration. The paper also highlights the challenges and limitations of vacuum suction technology and suggests potential areas for further research and development., Comment: 9 Pages, 3 figures, 6 diagrams, 1 table

A data analyst might worry about generalization if dropping a very small fraction of data points from a study could change its substantive conclusions. Finding the worst-case data subset to drop poses a combinatorial optimization problem. To overcome this intractability, recent works propose using additive approximations, which treat the contribution of a collection of data points as the sum of their individual contributions, and greedy approximations, which iteratively select the point with the highest impact to drop and re-run the data analysis without that point [Broderick et al., 2020, Kuschnig et al., 2021]. We identify that, even in a setting as simple as OLS linear regression, many of these approximations can break down in realistic data arrangements. Several of our examples reflect masking, where one outlier may hide or conceal the effect of another outlier. Based on the failures we identify, we provide recommendations for users and suggest directions for future improvements., Comment: 39 pages

If the conclusion of a data analysis is sensitive to dropping very few data points, that conclusion might hinge on the particular data at hand rather than representing a more broadly applicable truth. How could we check whether this sensitivity holds? One idea is to consider every small subset of data, drop it from the dataset, and re-run our analysis. But running MCMC to approximate a Bayesian posterior is already very expensive; running multiple times is prohibitive, and the number of re-runs needed here is combinatorially large. Recent work proposes a fast and accurate approximation to find the worst-case dropped data subset, but that work was developed for problems based on estimating equations -- and does not directly handle Bayesian posterior approximations using MCMC. We make two principal contributions in the present work. We adapt the existing data-dropping approximation to estimators computed via MCMC. Observing that Monte Carlo errors induce variability in the approximation, we use a variant of the bootstrap to quantify this uncertainty. We demonstrate how to use our approximation in practice to determine whether there is non-robustness in a problem. Empirically, our method is accurate in simple models, such as linear regression. In models with complicated structure, such as hierarchical models, the performance of our method is mixed., Comment: Shorter version appeared in ICML 2024 Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance, the underlying cause and explanation remain underexplored. In this paper, we first theoretically demonstrate that steering forget representations in the intermediate layer reduces token confidence, causing LLMs to generate wrong or nonsense responses. Second, we investigate how the coefficient influences the alignment of forget-sample representations with the random direction and hint at the optimal coefficient values for effective unlearning across different network layers. Third, we show that RMU unlearned models are robust against adversarial jailbreak attacks. Last, our empirical analysis shows that RMU is less effective when applied to the middle and later layers in LLMs. To resolve this drawback, we propose Adaptive RMU -- a simple yet effective alternative method that makes unlearning effective with most layers. Extensive experiments demonstrate that Adaptive RMU significantly improves the unlearning performance compared to prior art while incurring no additional computational cost., Comment: 15 pages, 5 figures, 8 tables

Knowing accurate joint positions is crucial for safe and precise control of laparoscopic surgical robots, especially for the automation of surgical sub-tasks. These robots have often been designed with cable-driven arms and tools because cables allow for larger motors to be placed at the base of the robot, further from the operating area where space is at a premium. However, by connecting the joint to its motor with a cable, any stretch in the cable can lead to errors in kinematic estimation from encoders at the motor, which can result in difficulties for accurate control of the surgical tool. In this work, we propose an efficient data-driven calibration of positioning joints of such robots, in this case the RAVEN-II surgical robotics research platform. While the calibration takes only 8-21 minutes, the accuracy of the calibrated joints remains high during a 6-hour heavily loaded operation, suggesting desirable feasibility in real practice. The calibration models take original robot states as input and are trained using zig-zag trajectories within a desired sparsity, requiring no additional sensors after training. Compared to fixed offset compensation, the Deep Neural Network calibration model can further reduce 76 percent of error and achieve accuracy of 0.104 deg, 0.120 deg, and 0.118 mm in joints 1, 2, and 3, respectively. In contrast to end-to-end models, experiments suggest that the DNN model achieves better accuracy and faster convergence when outputting the error to correct original inaccurate joint positions. Furthermore, a linear regression model is shown to have 160 times faster inference speed than DNN models for application within the 1000 Hz servo control loop, with slightly compromised accuracy.

Type Ia supernovae arise from thermonuclear explosions of white dwarfs accreting from a binary companion. Following the explosion, the surviving donor star leaves at roughly its orbital velocity. The discovery of the runaway helium subdwarf star US 708, and seven hypervelocity stars from Gaia data, all with spatial velocities $\gtrsim 900$ km/s, strongly support a scenario in which the donor is a low-mass helium star, or a white dwarf. Motivated by these discoveries, we perform three-dimensional hydrodynamical simulations with the $\texttt{Athena++}$ code modeling the hydrodynamical interaction between a helium star or helium white dwarf, and the supernova ejecta. We find that $\approx 0.01-0.02\,M_{\odot}$ of donor material is stripped, and explain the location of the stripped material within the expanding supernova ejecta. We continue the post-explosion evolution of the shocked donor stars with the $\texttt{MESA}$ code. As a result of entropy deposition, they remain luminous and expanded for $\approx 10^{5}-10^{6}$ yrs. We show that the post-explosion properties of our helium white dwarf donor agree reasonably with one of the best-studied hypervelocity stars, D6-2., Comment: 18 pages, 11 figures; Accepted to ApJ

The exploration of neural network quantum states has become widespread in the studies of complicated quantum many-body systems. However, achieving high precision remains challenging due to the exponential growth of Hilbert space size and the intricate sign structures. Utilizing symmetries of the physical system, we propose a method to evaluate and sample the variational ansatz within a symmetric subspace. This approach isolates different symmetry sectors, reducing the relevant Hilbert space size by a factor approximately proportional to the size of the symmetry group. It is inspired by exact diagonalization techniques and the work of Choo et al. in Phys. Rev. Lett. 121, 167204 (2018). We validate our method using the frustrated spin-1/2 $J_1$-$J_2$ antiferromagnetic Heisenberg chain and compare its performance to the case without symmetrization. The results indicate that our symmetric subspace approach achieves a substantial improvement over the full Hilbert space on optimizing the ansatz, reducing the energy error by orders of magnitude. We also compare the results on degenerate eigenstates with different quantum numbers, highlighting the advantage of operating within a smaller Hilbert subspace., Comment: 7 pages, 3 figs

We describe a general formalism based on the partial-wave decomposition to compute the iterative $s$-channel discontinuity of four-point amplitudes at any loop order. As an application, we focus on the low-energy expansions of type I and II superstring amplitudes. Besides providing new results for their leading and sub-leading logarithmic contributions beyond genus one, our approach elucidates the general structure of non-analytic threshold terms. In the case of open strings, the use of orthogonal colour projectors allows us to efficiently compute all contributions from different worldsheet topologies at a given loop order., Comment: 36 pages and 1 ancillary file; v2: minor improvements, typos fixed

Optical Coherence Tomography (OCT) imaging is pivotal in diagnosing ophthalmic conditions by providing detailed cross-sectional images of the anterior and posterior segments of the eye. Nonetheless, speckle noise and other imaging artifacts inherent to OCT impede the accuracy of diagnosis significantly. In this study, we proposed an enhanced denoising model using a Residual U-Net architecture that effectively diminishes noise and improves image clarity across both Anterior Segment OCT (ASOCT) and polarization-sensitive OCT (PSOCT) images. Our approach demonstrated substantial improvements in image quality metrics: the Peak Signal Noise Ratio (PSNR) was 34.343 $\pm$ 1.113 for PSOCT images, and Structural Similarity Index Measure (SSIM) values were 0.885 $\pm$ 0.030, indicating enhanced preservation of tissue integrity and textural details. For ASOCT images, we observed the PSNR to be 23.525 $\pm$ 0.872 dB and SSIM 0.407 $\pm$ 0.044, reflecting significant enhancements in visual quality and structural accuracy. These metrics substantiate the models efficacy in not only reducing noise but also in maintaining crucial anatomical features, thereby enabling more precise and efficient clinical evaluations. The dual functionality across both ASOCT and PSOCT modalities underscores the versatility and potential for broad application in clinical settings, optimizing diagnostic processes and reducing the necessity for prolonged imaging sessions.

Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these systems significantly hinder their effectiveness and scalability in multilingual settings. In this paper, we propose a cluster-based speaker diarization system designed for multilingual telephone call applications. Our proposed system supports multiple languages and eliminates the need for large-scale annotated data during training by utilizing the multilingual Whisper model to extract speaker embeddings. Additionally, we introduce a network architecture called Mixture of Sparse Autoencoders (Mix-SAE) for unsupervised speaker clustering. Experimental results on the evaluation dataset derived from two-speaker subsets of benchmark CALLHOME and CALLFRIEND telephonic speech corpora demonstrate the superior performance of the proposed Mix-SAE network to other autoencoder-based clustering methods. The overall performance of our proposed system also highlights the promising potential for developing unsupervised, multilingual speaker diarization systems within the context of limited annotated data. It also indicates the system's capability for integration into multi-task speech analysis applications based on general-purpose models such as those that combine speech-to-text, language detection, and speaker diarization., Comment: Preprint, 14 pages, 6 figures

The development of Natural Language Processing (NLI) datasets and models has been inspired by innovations in annotation design. With the rapid development of machine learning models today, the performance of existing machine learning models has quickly reached state-of-the-art results on a variety of tasks related to natural language processing, including natural language inference tasks. By using a pre-trained model during the annotation process, it is possible to challenge current NLI models by having humans produce premise-hypothesis combinations that the machine model cannot correctly predict. To remain attractive and challenging in the research of natural language inference for Vietnamese, in this paper, we introduce the adversarial NLI dataset to the NLP research community with the name ViANLI. This data set contains more than 10K premise-hypothesis pairs and is built by a continuously adjusting process to obtain the most out of the patterns generated by the annotators. ViANLI dataset has brought many difficulties to many current SOTA models when the accuracy of the most powerful model on the test set only reached 48.4%. Additionally, the experimental results show that the models trained on our dataset have significantly improved the results on other Vietnamese NLI datasets.

Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural networks (EENNs) offer a promising solution: they accelerate inference by allowing intermediate layers to exit and produce a prediction early. Yet a fundamental issue with EENNs is how to determine when to exit without severely degrading performance. In other words, when is it 'safe' for an EENN to go 'fast'? To address this issue, we investigate how to adapt frameworks of risk control to EENNs. Risk control offers a distribution-free, post-hoc solution that tunes the EENN's exiting mechanism so that exits only occur when the output is of sufficient quality. We empirically validate our insights on a range of vision and language tasks, demonstrating that risk control can produce substantial computational savings, all the while preserving user-specified performance goals., Comment: 27 pages, 13 figures, 4 tables (incl. appendix)

In this letter, we consider a positive geometry conjectured to encode the loop integrand of four-point stress-energy correlators in planar $\mathcal{N}=4$ super Yang-Mills. Beginning with four lines in twistor space, we characterize a positive subspace to which an $\ell$-loop geometry is attached. The loop geometry then consists of $\ell$ lines in twistor space satisfying positivity conditions among themselves and with respect to the base. Consequently, the $\textit{loop geometry}$ can be viewed as fibration over a $\textit{tree geometry}$. The fibration naturally dissects the base into chambers, in which the degree-$4 \ell$ loop form is unique and distinct for each chamber. Interestingly, up to three loops, the chambers are simply organized by the six ordering of $x^2_{1,2}x^2_{3,4}$, $x^2_{1,4}x^2_{2,3}$ and $x^2_{1,3}x^2_{2,4}$. We explicitly verify our conjecture by computing the loop-forms in terms of a basis of planar conformal integrals up to $\ell=3$, which indeed yield correct loop integrands for the four-point correlator., Comment: 7 pages + 2 figures, version accepted in PRD

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and effective strategy is to merge token representations within Transformer models, aiming to reduce computational and memory requirements while maintaining accuracy. Prior works have proposed algorithms based on Bipartite Soft Matching (BSM), which divides tokens into distinct sets and merges the top k similar tokens. However, these methods have significant drawbacks, such as sensitivity to token-splitting strategies and damage to informative tokens in later layers. This paper presents a novel paradigm called PiToMe, which prioritizes the preservation of informative tokens using an additional metric termed the energy score. This score identifies large clusters of similar tokens as high-energy, indicating potential candidates for merging, while smaller (unique and isolated) clusters are considered as low-energy and preserved. Experimental findings demonstrate that PiToMe saved from 40-60\% FLOPs of the base models while exhibiting superior off-the-shelf performance on image classification (0.5\% average performance drop of ViT-MAE-H compared to 2.6\% as baselines), image-text retrieval (0.3\% average performance drop of CLIP on Flickr30k compared to 4.5\% as others), and analogously in visual questions answering with LLaVa-7B. Furthermore, PiToMe is theoretically shown to preserve intrinsic spectral properties of the original token space under mild conditions, Comment: Accepted at NeurIPS 2024

Coordinate network or implicit neural representation (INR) is a fast-emerging method for encoding natural signals (such as images and videos) with the benefits of a compact neural representation. While numerous methods have been proposed to increase the encoding capabilities of an INR, an often overlooked aspect is the inference efficiency, usually measured in multiply-accumulate (MAC) count. This is particularly critical in use cases where inference throughput is greatly limited by hardware constraints. To this end, we propose the Activation-Sharing Multi-Resolution (ASMR) coordinate network that combines multi-resolution coordinate decomposition with hierarchical modulations. Specifically, an ASMR model enables the sharing of activations across grids of the data. This largely decouples its inference cost from its depth which is directly correlated to its reconstruction capability, and renders a near O(1) inference complexity irrespective of the number of layers. Experiments show that ASMR can reduce the MAC of a vanilla SIREN model by up to 500x while achieving an even higher reconstruction quality than its SIREN baseline., Comment: ICLR 2024 (v3: 21 pages, 11 figures, Project Page: https://github.com/stevolopolis/asmr.git)

We investigate the learning of implicit neural representation (INR) using an overparameterized multilayer perceptron (MLP) via a novel nonparametric teaching perspective. The latter offers an efficient example selection framework for teaching nonparametrically defined (viz. non-closed-form) target functions, such as image functions defined by 2D grids of pixels. To address the costly training of INRs, we propose a paradigm called Implicit Neural Teaching (INT) that treats INR learning as a nonparametric teaching problem, where the given signal being fitted serves as the target function. The teacher then selects signal fragments for iterative training of the MLP to achieve fast convergence. By establishing a connection between MLP evolution through parameter-based gradient descent and that of function evolution through functional gradient descent in nonparametric teaching, we show for the first time that teaching an overparameterized MLP is consistent with teaching a nonparametric learner. This new discovery readily permits a convenient drop-in of nonparametric teaching algorithms to broadly enhance INR training efficiency, demonstrating 30%+ training time savings across various input modalities., Comment: ICML 2024 (24 pages, 13 figures)

The current clinical gold standard for evaluating adolescent idiopathic scoliosis (AIS) is X-ray radiography, using Cobb angle measurement. However, the frequent monitoring of the AIS progression using X-rays poses a challenge due to the cumulative radiation exposure. Although 3D ultrasound has been validated as a reliable and radiation-free alternative for scoliosis assessment, the process of measuring spinal curvature is still carried out manually. Consequently, there is a considerable demand for a fully automatic system that can locate bony landmarks and perform angle measurements. To this end, we introduce an estimation model for automatic ultrasound curve angle (UCA) measurement. The model employs a dual-branch network to detect candidate landmarks and perform vertebra segmentation on ultrasound coronal images. An affinity clustering strategy is utilized within the vertebral segmentation area to illustrate the affinity relationship between candidate landmarks. Subsequently, we can efficiently perform line delineation from a clustered affinity map for UCA measurement. As our method is specifically designed for UCA calculation, this method outperforms other state-of-the-art methods for landmark and line detection tasks. The high correlation between the automatic UCA and Cobb angle (R$^2$=0.858) suggests that our proposed method can potentially replace manual UCA measurement in ultrasound scoliosis assessment.

Recently, many studies have shown the efficiency of using Bidirectional Encoder Representations from Transformers (BERT) in various Natural Language Processing (NLP) tasks. Specifically, English spelling correction task that uses Encoder-Decoder architecture and takes advantage of BERT has achieved state-of-the-art result. However, to our knowledge, there is no implementation in Vietnamese yet. Therefore, in this study, a combination of Transformer architecture (state-of-the-art for Encoder-Decoder model) and BERT was proposed to deal with Vietnamese spelling correction. The experiment results have shown that our model outperforms other approaches as well as the Google Docs Spell Checking tool, achieves an 86.24 BLEU score on this task., Comment: 13 pages

Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security-crucial applications. However, adversarial samples, which are undetectable to the human eye, pose a serious threat that can cause the model to misbehave and compromise the performance of such applications. Addressing the robustness of DL models has become crucial to understanding and defending against adversarial attacks. In this study, we perform comprehensive experiments to examine the effect of adversarial attacks and defenses on various model architectures across well-known datasets. Our research focuses on black-box attacks such as SimBA, HopSkipJump, MGAAttack, and boundary attacks, as well as preprocessor-based defensive mechanisms, including bits squeezing, median smoothing, and JPEG filter. Experimenting with various models, our results demonstrate that the level of noise needed for the attack increases as the number of layers increases. Moreover, the attack success rate decreases as the number of layers increases. This indicates that model complexity and robustness have a significant relationship. Investigating the diversity and robustness relationship, our experiments with diverse models show that having a large number of parameters does not imply higher robustness. Our experiments extend to show the effects of the training dataset on model robustness. Using various datasets such as ImageNet-1000, CIFAR-100, and CIFAR-10 are used to evaluate the black-box attacks. Considering the multiple dimensions of our analysis, e.g., model complexity and training dataset, we examined the behavior of black-box attacks when models apply defenses. Our results show that applying defense strategies can significantly reduce attack effectiveness. This research provides in-depth analysis and insight into the robustness of DL models against various attacks, and defenses.

In this paper, we present a toolchain for a comprehensive audio/video analysis by leveraging deep learning based multimodal approach. To this end, different specific tasks of Speech to Text (S2T), Acoustic Scene Classification (ASC), Acoustic Event Detection (AED), Visual Object Detection (VOD), Image Captioning (IC), and Video Captioning (VC) are conducted and integrated into the toolchain. By combining individual tasks and analyzing both audio \& visual data extracted from input video, the toolchain offers various audio/video-based applications: Two general applications of audio/video clustering, comprehensive audio/video summary and a specific application of riot or violent context detection. Furthermore, the toolchain presents a flexible and adaptable architecture that is effective to integrate new models for further audio/video-based applications.

During the use of Advanced Driver Assistance Systems (ADAS), drivers can intervene in the active function and take back control due to various reasons. However, the specific reasons for driver-initiated takeovers in naturalistic driving are still not well understood. In order to get more information on the reasons behind these takeovers, a test group study was conducted. There, 17 participants used a predictive longitudinal driving function for their daily commutes and annotated the reasons for their takeovers during active function use. In this paper, the recorded takeovers are analyzed and the different reasons for them are highlighted. The results show that the reasons can be divided into three main categories. The most common category consists of takeovers which aim to adjust the behavior of the ADAS within its Operational Design Domain (ODD) in order to better match the drivers' personal preferences. Other reasons include takeovers due to leaving the ADAS's ODD and corrections of incorrect sensing state information. Using the questionnaire results of the test group study, it was found that the number and frequency of takeovers especially within the ADAS's ODD have a significant negative impact on driver satisfaction. Therefore, the driver satisfaction with the ADAS could be increased by adapting its behavior to the drivers' wishes and thereby lowering the number of takeovers within the ODD. The information contained in the takeover behavior of the drivers could be used as feedback for the ADAS. Finally, it is shown that there are considerable differences in the takeover behavior of different drivers, which shows a need for ADAS individualization.

In this paper we would have a brief overview of several proposals of quasilocal mass which are based on Hamiltonian formulation. We also show the positivity of the Wang-Yau energy under a more general condition. We then further study the quasilocal mass and DEC fill-ins defined by the author in terms of completeness and shields., Comment: 17 pages, comments are welcome. arXiv admin note: text overlap with arXiv:2109.11070