arXiv subjects

Xi Yang

Publications and source records attributed to Xi Yang.

At least 127 records · Page 7Linked to original sources

arXiv2024

Diagonal and normal with Toeplitz-block splitting iteration method for space fractional coupled nonlinear Schrödinger equations with repulsive nonlinearities

By applying the linearly implicit conservative difference scheme proposed in [D.-L. Wang, A.-G. Xiao, W. Yang. J. Comput. Phys. 2014;272:670-681], the system of repulsive space fractional coupled nonlinear Schrödinger equations leads to a sequence of linear systems with complex symmetric and Toeplitz-plus-diagonal structure. In this paper, we propose the diagonal and normal with Toeplitz-block splitting iteration method to solve the above linear systems. The new iteration method is proved to converge unconditionally, and the optimal iteration parameter is deducted. Naturally, this new iteration method leads to a diagonal and normal with circulant-block preconditioner which can be executed efficiently by fast algorithms. In theory, we provide sharp bounds for the eigenvalues of the discrete fractional Laplacian and its circulant approximation, and further analysis indicates that the spectral distribution of the preconditioned system matrix is tight. Numerical experiments show that the new preconditioner can significantly improve the computational efficiency of the Krylov subspace iteration methods. Moreover, the behavior of the corresponding preconditioned GMRES method exhibits a linear dependence on the space mesh size, which weakens as the fractional order parameter decreases.

math.NA↗

arXiv2024

Gamification of virtual museum curation: a case study of Chinese bronze wares

Museums, which are among the most popular science institutions outside schools, are usually used to display and introduce historical culture and cultural relics to tourists. Text and audio explanations are used by traditional museums to popularize historical knowledge and science for tourists, and general interactive systems are based on desktops. This learning method is relatively boring in terms of experience. As a result, tourists have no desire or interest in actively exploring and learning about bronze ware, so they only have a basic understanding about bronze ware. Since most tourists are familiar with games, they are more likely to be attracted by game content and will actively explore and interact with it. In addition, a certain degree of reality is created by virtual reality technology and an immersive experience through head-mounted devices is provided to users. In this paper, we take Chinese bronzes as the research objects. We first use laser scanners to obtain bronze models ; then, we build a virtual museum environment, and we finally design a virtual reality curation game based on this bronze digital museum. This game offers visitors an immersive museum roaming and bronze ware interactive experience. Through a combination of text, video learning, and games, visitors' curiosity and desire to explore bronze ware are stimulated, and their understanding and ability to remember bronze ware knowledge can be deepened. In terms of cultural heritage, this game is also conducive to the spread of traditional Chinese bronze culture throughout the world.

cs.CY↗

arXiv2024

Sine-transform-based fast solvers for Riesz fractional nonlinear Schrödinger equations with attractive nonlinearities

This paper presents fast solvers for linear systems arising from the discretization of fractional nonlinear Schrödinger equations with Riesz derivatives and attractive nonlinearities. These systems are characterized by complex symmetry, indefiniteness, and a $d$-level Toeplitz-plus-diagonal structure. We propose a Toeplitz-based anti-symmetric and normal splitting iteration method for the equivalent real block linear systems, ensuring unconditional convergence. The derived optimal parameter is approximately equal to 1. By combining this iteration method with sine-transform-based preconditioning, we introduce a novel preconditioner that enhances the convergence rate of Krylov subspace methods. Both theoretical and numerical analyses demonstrate that the new preconditioner exhibits a parameter-free property (allowing the iteration parameter to be fixed at 1). The eigenvalues of the preconditioned system matrix are nearly clustered in a small neighborhood around 1, and the convergence rate of the corresponding preconditioned GMRES method is independent of the spatial mesh size and the fractional order of the Riesz derivatives.

math.NA↗

arXiv2024

Recording dynamic facial micro-expressions with a multi-focus camera array

We present an approach of utilizing a multi-camera array system for capturing dynamic high-resolution videos of the human face, with improved imaging performance as compared to traditional single-camera configurations. Employing an array of 54 individual high-resolution cameras, each with its own 13 megapixel sensor (709 megapixels total), we uniquely focus each camera to a different plane across the curved surface of the human face in order to capture dynamic facial expressions. Post-processing methods then stitch together each synchronized set of 54 images into a composite video frame. Our multi-focus strategy overcomes the resolution and depth-of-field (DOF) limitations for capturing macroscopically curved surfaces such as the human face, while maintaining high lateral resolution. Specifically we demonstrate how our setup achieves a generally uniform lateral resolution of 26.75 +/- 8.8 micrometer across a composite DOF of ~43mm that covers the entire face (85 cm^2 + FOV). Compared to a single-focus configuration this is almost a 10-fold increase in effective DOF. We believe that our new approach for multi-focus camera array video sets the stage for future video capture of a variety of dynamic and macroscopically curved surfaces at microscopic resolution.

physics.optics↗

arXiv2024

Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment

Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents an even more difficult scenario. To cope with this challenge, knowledge distillation has emerged as one promising strategy. However, recent efforts typically overlook the modality gaps and thus fail to learn invariant feature representations across different modalities. Such drawback consequently leads to limited performance for both teachers and students. To ameliorate these problems, in this paper, we propose a novel paradigm that aligns latent features of involved modalities to a well-defined distribution anchor. As a major contribution, we prove that our novel training paradigm ensures a tight evidence lower bound, thus theoretically certifying its effectiveness. Extensive experiments on different backbones validate that the proposed paradigm can enable invariant feature representations and produce a teacher with narrowed modality gaps. This further offers superior guidance for missing modality students, achieving an average improvement of 1.75 on dice score.

eess.IV↗

arXiv2024

Emu3: Next-Token Prediction is All You Need

While next-token prediction is considered a promising path towards artificial general intelligence, it has struggled to excel in multimodal tasks, which are still dominated by diffusion models (e.g., Stable Diffusion) and compositional approaches (e.g., CLIP combined with LLMs). In this paper, we introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction. By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences. Emu3 outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship models such as SDXL and LLaVA-1.6, while eliminating the need for diffusion or compositional architectures. Emu3 is also capable of generating high-fidelity video via predicting the next token in a video sequence. We simplify complex multimodal model designs by converging on a singular focus: tokens, unlocking great potential for scaling both during training and inference. Our results demonstrate that next-token prediction is a promising path towards building general multimodal intelligence beyond language. We open-source key techniques and models to support further research in this direction.

cs.CV↗

arXiv2024

CathAction: A Benchmark for Endovascular Intervention Understanding

Real-time visual feedback from catheterization analysis is crucial for enhancing surgical safety and efficiency during endovascular interventions. However, existing datasets are often limited to specific tasks, small scale, and lack the comprehensive annotations necessary for broader endovascular intervention understanding. To tackle these limitations, we introduce CathAction, a large-scale dataset for catheterization understanding. Our CathAction dataset encompasses approximately 500,000 annotated frames for catheterization action understanding and collision detection, and 25,000 ground truth masks for catheter and guidewire segmentation. For each task, we benchmark recent related works in the field. We further discuss the challenges of endovascular intentions compared to traditional computer vision tasks and point out open research questions. We hope that CathAction will facilitate the development of endovascular intervention understanding methods that can be applied to real-world applications. The dataset is available at https://airvlab.github.io/cathaction/.

cs.CV↗

arXiv2024

DIPR: Efficient Point Cloud Registration via Dynamic Iteration

Point cloud registration (PCR) is an essential task in 3D vision. Existing methods achieve increasingly higher accuracy. However, a large proportion of non-overlapping points in point cloud registration consume a lot of computational resources while negatively affecting registration accuracy. To overcome this challenge, we introduce a novel Efficient Point Cloud Registration via Dynamic Iteration framework, DIPR, that makes the neural network interactively focus on overlapping points based on sparser input points. We design global and local registration stages to achieve efficient course-tofine processing. Beyond basic matching modules, we propose the Refined Nodes to narrow down the scope of overlapping points by using adopted density-based clustering to significantly reduce the computation amount. And our SC Classifier serves as an early-exit mechanism to terminate the registration process in time according to matching accuracy. Extensive experiments on multiple datasets show that our proposed approach achieves superior registration accuracy while significantly reducing computational time and GPU memory consumption compared to state-of-the-art methods.

cs.CV↗

arXiv2024

MedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment

Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents a more difficult scenario. To cope with this challenge, Knowledge Distillation, Domain Adaption, and Shared Latent Space have emerged as commonly promising strategies. However, recent efforts typically overlook the modality gaps and thus fail to learn important invariant feature representations across different modalities. Such drawback consequently leads to limited performance for missing modality models. To ameliorate these problems, pre-trained models are used in natural visual segmentation tasks to minimize the gaps. However, promising pre-trained models are often unavailable in medical image segmentation tasks. Along this line, in this paper, we propose a novel paradigm that aligns latent features of involved modalities to a well-defined distribution anchor as the substitution of the pre-trained model}. As a major contribution, we prove that our novel training paradigm ensures a tight evidence lower bound, thus theoretically certifying its effectiveness. Extensive experiments on different backbones validate that the proposed paradigm can enable invariant feature representations and produce models with narrowed modality gaps. Models with our alignment paradigm show their superior performance on both BraTS2018 and BraTS2020 datasets.

cs.CV↗

arXiv2024

Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution

Real-world low-resolution (LR) videos have diverse and complex degradations, imposing great challenges on video super-resolution (VSR) algorithms to reproduce their high-resolution (HR) counterparts with high quality. Recently, the diffusion models have shown compelling performance in generating realistic details for image restoration tasks. However, the diffusion process has randomness, making it hard to control the contents of restored images. This issue becomes more serious when applying diffusion models to VSR tasks because temporal consistency is crucial to the perceptual quality of videos. In this paper, we propose an effective real-world VSR algorithm by leveraging the strength of pre-trained latent diffusion models. To ensure the content consistency among adjacent frames, we exploit the temporal dynamics in LR videos to guide the diffusion process by optimizing the latent sampling path with a motion-guided loss, ensuring that the generated HR video maintains a coherent and continuous visual flow. To further mitigate the discontinuity of generated details, we insert temporal module to the decoder and fine-tune it with an innovative sequence-oriented loss. The proposed motion-guided latent diffusion (MGLD) based VSR algorithm achieves significantly better perceptual quality than state-of-the-arts on real-world VSR benchmark datasets, validating the effectiveness of the proposed model design and training strategies.

cs.CV↗

arXiv2024

Beneath the Surface: Revealing Deep-Tissue Blood Flow in Human Subjects with Massively Parallelized Diffuse Correlation Spectroscopy

Diffuse Correlation Spectroscopy (DCS) allows the label-free investigation of microvascular dynamics deep within living tissue. However, common implementations of DCS are currently limited to measurement depths of $\sim 1-1.5cm$, which can limit the accuracy of cerebral hemodynamics measurement. Here we present massively parallelized DCS (pDCS) using novel single photon avalanche detector (SPAD) arrays with up to 500x500 individual channels. The new SPAD array technology can boost the signal-to-noise ratio by a factor of up to 500 compared to single-pixel DCS, or by more than 15-fold compared to the most recent state-of-the-art pDCS demonstrations. Our results demonstrate the first in vivo use of this massively parallelized DCS system to measure cerebral blood flow changes at $\sim 2cm$ depth in human adults. We compared different modes of operation and applied a dual detection strategy, where a secondary SPAD array is used to simultaneously assess the superficial blood flow as a built-in reference measurement. While the blood flow in the superficial scalp tissue showed no significant change during cognitive activation, the deep pDCS measurement showed a statistically significant increase in the derived blood flow index of 8-12% when compared to the control rest state.

physics.med-ph↗

arXiv2024

Dedicated beam position monitor pair for model-independent lattice characterization at NSLS-II

This paper reports recent lattice characterization results obtained at the National Synchrotron Light Source II (NSLS-II) storage ring, conducted without reliance on a lattice model. A pair of beam position monitors (BPMs) with bunch-by-bunch (B$\times$B) resolution, were recently installed in a section of the storage ring free of magnetic fields. The new BPM pair measured the beam, or bunch's transverse Poincaré map precisely after the beam was excited. Linear one-turn-matrices (OTM) were then derived, and from these, the 4-dimensional coupled Twiss parameters were extracted at the locations of the BPM pair. By normalizing beam oscillation amplitudes with the Twiss parameters, the global action-variables were obtained. These action-variables facilitated the measurement of the local Twiss parameters observed by other BPMs independent on lattice model. This method is general, and particularly useful in certain scenarios such as a round beam mode in a diffraction-limited light source ring. We applied it to assess both weakly and strongly coupled lattices at the NSLS-II ring. Through analysis of the strongly coupled lattice, the quadrupole tilt errors were estimated to be less than 400 \siμrad. Utilizing the BPMs' B$\times$B resolution, for the first time we observed the variations of the linear lattice along a long bunch-train.

physics.acc-ph↗

arXiv2024

A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems

Accurate channel state information (CSI) is essential for downlink precoding in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems with orthogonal frequency-division multiplexing (OFDM). However, obtaining CSI through feedback from the user equipment (UE) becomes challenging with the increasing scale of antennas and subcarriers and leads to extremely high CSI feedback overhead. Deep learning-based methods have emerged for compressing CSI but these methods generally require substantial collected samples and thus pose practical challenges. Moreover, existing deep learning methods also suffer from dramatically growing feedback overhead owing to their focus on full-dimensional CSI feedback. To address these issues, we propose a low-overhead Incorporation-Extrapolation based Few-Shot CSI feedback Framework (IEFSF) for massive MIMO systems. An incorporation-extrapolation scheme for eigenvector-based CSI feedback is proposed to reduce the feedback overhead. Then, to alleviate the necessity of extensive collected samples and enable few-shot CSI feedback, we further propose a knowledge-driven data augmentation (KDDA) method and an artificial intelligence-generated content (AIGC) -based data augmentation method by exploiting the domain knowledge of wireless channels and by exploiting a novel generative model, respectively. Experimental results based on the DeepMIMO dataset demonstrate that the proposed IEFSF significantly reduces CSI feedback overhead by 64 times compared with existing methods while maintaining higher feedback accuracy using only several hundred collected samples.

cs.IT↗

arXiv2024

DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection

Large language models (LLMs) have the potential to generate texts that pose risks of misuse, such as plagiarism, planting fake reviews on e-commerce platforms, or creating inflammatory false tweets. Consequently, detecting whether a text is generated by LLMs has become increasingly important. Existing high-quality detection methods usually require access to the interior of the model to extract the intrinsic characteristics. However, since we do not have access to the interior of the black-box model, we must resort to surrogate models, which impacts detection quality. In order to achieve high-quality detection of black-box models, we would like to extract deep intrinsic characteristics of the black-box model generated texts. We view the generation process as a coupled process of prompt and intrinsic characteristics of the generative model. Based on this insight, we propose to decouple prompt and intrinsic characteristics (DPIC) for LLM-generated text detection method. Specifically, given a candidate text, DPIC employs an auxiliary LLM to reconstruct the prompt corresponding to the candidate text, then uses the prompt to regenerate text by the auxiliary LLM, which makes the candidate text and the regenerated text align with their prompts, respectively. Then, the similarity between the candidate text and the regenerated text is used as a detection feature, thus eliminating the prompt in the detection process, which allows the detector to focus on the intrinsic characteristics of the generative model. Compared to the baselines, DPIC has achieved an average improvement of 6.76\% and 2.91\% in detecting texts from different domains generated by GPT4 and Claude3, respectively.

cs.CL↗

arXiv2024

HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation

Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), achieving remarkable performance across diverse tasks and enabling widespread real-world applications. However, LLMs are prone to hallucination, generating content that either conflicts with established knowledge or is unfaithful to the original sources. Existing hallucination benchmarks primarily focus on sentence- or passage-level hallucination detection, neglecting dialogue-level evaluation, hallucination localization, and rationale provision. They also predominantly target factuality hallucinations while underestimating faithfulness hallucinations, often relying on labor-intensive or non-specialized evaluators. To address these limitations, we propose HalluDial, the first comprehensive large-scale benchmark for automatic dialogue-level hallucination evaluation. HalluDial encompasses both spontaneous and induced hallucination scenarios, covering factuality and faithfulness hallucinations. The benchmark includes 4,094 dialogues with a total of 146,856 samples. Leveraging HalluDial, we conduct a comprehensive meta-evaluation of LLMs' hallucination evaluation capabilities in information-seeking dialogues and introduce a specialized judge language model, HalluJudge. The high data quality of HalluDial enables HalluJudge to achieve superior or competitive performance in hallucination evaluation, facilitating the automatic assessment of dialogue-level hallucinations in LLMs and providing valuable insights into this phenomenon. The dataset and the code are available at https://github.com/FlagOpen/HalluDial.

cs.CL↗

arXiv2024

A Generalized Apprenticeship Learning Framework for Modeling Heterogeneous Student Pedagogical Strategies

A key challenge in e-learning environments like Intelligent Tutoring Systems (ITSs) is to induce effective pedagogical policies efficiently. While Deep Reinforcement Learning (DRL) often suffers from sample inefficiency and reward function design difficulty, Apprenticeship Learning(AL) algorithms can overcome them. However, most AL algorithms can not handle heterogeneity as they assume all demonstrations are generated with a homogeneous policy driven by a single reward function. Still, some AL algorithms which consider heterogeneity, often can not generalize to large continuous state space and only work with discrete states. In this paper, we propose an expectation-maximization(EM)-EDM, a general AL framework to induce effective pedagogical policies from given optimal or near-optimal demonstrations, which are assumed to be driven by heterogeneous reward functions. We compare the effectiveness of the policies induced by our proposed EM-EDM against four AL-based baselines and two policies induced by DRL on two different but related tasks that involve pedagogical action prediction. Our overall results showed that, for both tasks, EM-EDM outperforms the four AL baselines across all performance metrics and the two DRL baselines. This suggests that EM-EDM can effectively model complex student pedagogical decision-making processes through the ability to manage a large, continuous state space and adapt to handle diverse and heterogeneous reward functions with very few given demonstrations.

cs.LG↗

arXiv2024

Revisiting Mutual Information Maximization for Generalized Category Discovery

Generalized category discovery presents a challenge in a realistic scenario, which requires the model's generalization ability to recognize unlabeled samples from known and unknown categories. This paper revisits the challenge of generalized category discovery through the lens of information maximization (InfoMax) with a probabilistic parametric classifier. Our findings reveal that ensuring independence between known and unknown classes while concurrently assuming a uniform probability distribution across all classes, yields an enlarged margin among known and unknown classes that promotes the model's performance. To achieve the aforementioned independence, we propose a novel InfoMax-based method, Regularized Parametric InfoMax (RPIM), which adopts pseudo labels to supervise unlabeled samples during InfoMax, while proposing a regularization to ensure the quality of the pseudo labels. Additionally, we introduce novel semantic-bias transformation to refine the features from the pre-trained model instead of direct fine-tuning to rescue the computational costs. Extensive experiments on six benchmark datasets validate the effectiveness of our method. RPIM significantly improves the performance regarding unknown classes, surpassing the state-of-the-art method by an average margin of 3.5%.

cs.CV↗

arXiv2024

SCMix: Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentation

Open compound domain adaptation (OCDA) aims to transfer knowledge from a labeled source domain to a mix of unlabeled homogeneous compound target domains while generalizing to open unseen domains. Existing OCDA methods solve the intra-domain gaps by a divide-and-conquer strategy, which divides the problem into several individual and parallel domain adaptation (DA) tasks. Such approaches often contain multiple sub-networks or stages, which may constrain the model's performance. In this work, starting from the general DA theory, we establish the generalization bound for the setting of OCDA. Built upon this, we argue that conventional OCDA approaches may substantially underestimate the inherent variance inside the compound target domains for model generalization. We subsequently present Stochastic Compound Mixing (SCMix), an augmentation strategy with the primary objective of mitigating the divergence between source and mixed target distributions. We provide theoretical analysis to substantiate the superiority of SCMix and prove that the previous methods are sub-groups of our methods. Extensive experiments show that our method attains a lower empirical risk on OCDA semantic segmentation tasks, thus supporting our theories. Combining the transformer architecture, SCMix achieves a notable performance boost compared to the SoTA results.

cs.CV↗