arXiv subjects

Xin Wang

Publications and source records attributed to Xin Wang.

At least 919 records · Page 51Linked to original sources

arXiv2024

Qibo: A Large Language Model for Traditional Chinese Medicine

Large Language Models (LLMs) has made significant progress in a number of professional fields, including medicine, law, and finance. However, in traditional Chinese medicine (TCM), there are challenges such as the essential differences between theory and modern medicine, the lack of specialized corpus resources, and the fact that relying only on supervised fine-tuning may lead to overconfident predictions. To address these challenges, we propose a two-stage training approach that combines continuous pre-training and supervised fine-tuning. A notable contribution of our study is the processing of a 2GB corpus dedicated to TCM, constructing pre-training and instruction fine-tuning datasets for TCM, respectively. In addition, we have developed Qibo-Benchmark, a tool that evaluates the performance of LLM in the TCM on multiple dimensions, including subjective, objective, and three TCM NLP tasks. The medical LLM trained with our pipeline, named $\textbf{Qibo}$, exhibits significant performance boosts. Compared to the baselines, the average subjective win rate is 63%, the average objective accuracy improved by 23% to 58%, and the Rouge-L scores for the three TCM NLP tasks are 0.72, 0.61, and 0.55. Finally, we propose a pipline to apply Qibo to TCM consultation and demonstrate the model performance through the case study.

cs.CL↗

arXiv2024

Towards Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach

Federated learning (FL) is a viable technique to train a shared machine learning model without sharing data. Hierarchical FL (HFL) system has yet to be studied regrading its multiple levels of energy, computation, communication, and client scheduling, especially when it comes to clients relying on energy harvesting to power their operations. This paper presents a new two-phase deep deterministic policy gradient (DDPG) framework, referred to as ``TP-DDPG'', to balance online the learning delay and model accuracy of an FL process in an energy harvesting-powered HFL system. The key idea is that we divide optimization decisions into two groups, and employ DDPG to learn one group in the first phase, while interpreting the other group as part of the environment to provide rewards for training the DDPG in the second phase. Specifically, the DDPG learns the selection of participating clients, and their CPU configurations and the transmission powers. A new straggler-aware client association and bandwidth allocation (SCABA) algorithm efficiently optimizes the other decisions and evaluates the reward for the DDPG. Experiments demonstrate that with substantially reduced number of learnable parameters, the TP-DDPG can quickly converge to effective polices that can shorten the training time of HFL by 39.4% compared to its benchmarks, when the required test accuracy of HFL is 0.9.

cs.LG↗

arXiv2024

Modeling and Analysis of Application Interference on Dragonfly+

Dragonfly class of networks are considered as promising interconnects for next-generation supercomputers. While Dragonfly+ networks offer more path diversity than the original Dragonfly design, they are still prone to performance variability due to their hierarchical architecture and resource sharing design. Event-driven network simulators are indispensable tools for navigating complex system design. In this study, we quantitatively evaluate a variety of application communication interactions on a 3,456-node Dragonfly+ system by using the CODES toolkit. This study looks at the impact of communication interference from a user's perspective. Specifically, for a given application submitted by a user, we examine how this application will behave with the existing workload running in the system under different job placement policies. Our simulation study considers hundreds of experiment configurations including four target applications with representative communication patterns under a variety of network traffic conditions. Our study shows that intra-job interference can cause severe performance degradation for communication-intensive applications. Inter-job interference can generally be reduced for applications with one-to-one or one-to-many communication patterns through job isolation. Application with one-to-all communication pattern is resilient to network interference.

cs.NI↗

arXiv2024

Achieving Cooling Without Repump Lasers Through Ion Motional Heating

Laser cooling typically requires one or more repump lasers to clear dark states and enable recycling transitions. Here, we have achieved cooling of Be+ ions using a single laser beam, facilitated by one-dimensional heating through micromotion. By manipulating the displacement from the trap's nodal line, we precisely controlled the ion micromotion direction and speed, reaching up to 3144 m/s, which corresponds to a 7.1 GHz Doppler frequency shift in our experiment. This approach eliminates the necessity of a 1.25 GHz offset repump laser while keeping the Be+ ions cold in the perpendicular direction. Measurements were taken using cooling laser detuning and imaging of ion trajectories. Molecular dynamics simulations, based on machine learned time-dependent electric field E(X, Y, Z, t) inside the trap, accurately reproduced the experimental observation, illuminating the relationship between the direction of micromotion and the trapping electric filed vector. This work not only provides a robust method for managing the micromotion velocity of ions but also sheds light on laser cooling complex systems that require multiple repumping lasers. Additionally, it offers a method for controlling energy in the context of ion-molecule collision investigations.

physics.atom-ph↗

arXiv2024

Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models

Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation. However, SAM requires two sequential gradient computations during the optimization of each step: one to obtain the perturbation gradient and the other to obtain the updating gradient. Compared with the base optimizer (e.g., Adam), SAM doubles the time overhead due to the additional perturbation gradient. By dissecting the theory of SAM and observing the training gradient of the molecular graph transformer, we propose a new algorithm named GraphSAM, which reduces the training cost of SAM and improves the generalization performance of graph transformer models. There are two key factors that contribute to this result: (i) \textit{gradient approximation}: we use the updating gradient of the previous step to approximate the perturbation gradient at the intermediate steps smoothly (\textbf{increases efficiency}); (ii) \textit{loss landscape approximation}: we theoretically prove that the loss landscape of GraphSAM is limited to a small range centered on the expected loss of SAM (\textbf{guarantees generalization performance}). The extensive experiments on six datasets with different tasks demonstrate the superiority of GraphSAM, especially in optimizing the model update process. The code is in:https://github.com/YL-wang/GraphSAM/tree/graphsam

cs.LG↗

arXiv2024

MOStream: A Modular and Self-Optimizing Data Stream Clustering Algorithm

Data stream clustering is a critical operation in various real-world applications, ranging from the Internet of Things (IoT) to social media and financial systems. Existing data stream clustering algorithms, while effective to varying extents, often lack the flexibility and self-optimization capabilities needed to adapt to diverse workload characteristics such as outlier, cluster evolution and changing dimensions in data points. These limitations manifest in suboptimal clustering accuracy and computational inefficiency. In this paper, we introduce MOStream, a modular and self-optimizing data stream clustering algorithm designed to dynamically balance clustering accuracy and computational efficiency at runtime. MOStream distinguishes itself by its adaptivity, clearly demarcating four pivotal design dimensions: the summarizing data structure, the window model for handling data temporality, the outlier detection mechanism, and the refinement strategy for improving cluster quality. This clear separation facilitates flexible adaptation to varying design choices and enhances its adaptability to a wide array of application contexts. We conduct a rigorous performance evaluation of MOStream, employing diverse configurations and benchmarking it against 9 representative data stream clustering algorithms on 4 real-world datasets and 3 synthetic datasets. Our empirical results demonstrate that MOStream consistently surpasses competing algorithms in terms of clustering accuracy, processing throughput, and adaptability to varying data stream characteristics.

cs.DB↗

arXiv2024

Disk Assembly of the Milky Way Suggested from the Time-resolved Chemical Abundance

Both simulations and observations suggest that the disk assembly of galaxies is governed by the interplay between coplanar gas inflow, ex-planar gas outflow and in-situ star formation on the disk, known as the leaky accretion disk. This scenario predicts a strong connection between radial distributions of star formation and chemical abundances. The Milky Way, being the sole galaxy where we can reliably measure star formation histories and the corresponding temporally-resolved chemical abundances with individual stars, provides a unique opportunity to scrutinize this scenario. Based on the recent large spectroscopic and photometric surveys of Milky Way stars, we obtain the radial profiles of magnesium abundance ([Mg/H]) and star formation rate (SFR) surface density at different lookback time. We find the radial profiles of [Mg/H] can be well-reproduced using the leaky accretion disk model with only two free parameters for stars formed within 4 Gyr, as well as the flattening at large radii of metallicity profiles traced by HII regions and Cepheids. Furthermore, the constraint effective yield of the Milky Way and nearby galaxies show broad consistency with the theoretical predictions from stellar chemical evolution model with a mass-loading factor of 0-2. These results support that the recent assembly of the Milky Way adheres to the leaky accretion disk scenario, bridging the disk formation of our home galaxy to the big picture of disk formation in the Universe.

astro-ph.GA↗

arXiv2024

Interaction and entanglement engineering in driven giant atoms setup with coupled resonator waveguide

We investigate the coherent interactions mediated by the coupled resonator waveguide between two types of giant atoms. We find that the effective coupling and collective dissipation can be controlled on demand by adjusting the configuration of the giant atoms. As a result, the external driving gives birth to a substantial entanglement between two giant atoms, which exhibits a Rabi splitting character. {In the three giant atom setup, we find that the nonzero next neighbour atomic entanglement can surpass the neighbour ones, and is able to be adjust by tuning the driving phase, which serves as an artificial magnetic field. The enhancement of next neighbour atomic entanglement can not be realized in the small atom setup.} We hope these controllable interactions in giant atom array are of great applications in the quantum information process.

quant-ph↗

arXiv2024

An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios

Self-supervised learning (SSL) representations from massively multilingual models offer a promising solution for low-resource language speech tasks. Despite advancements, language adaptation in TTS systems remains an open problem. This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system proposed in our previous work. We conducted experiments on 12 languages using limited data with various fine-tuning configurations. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance. Additionally, we find that the fine-tuning dataset size and number of speakers influence adaptability. Surprisingly, we also observed that using paired data for fine-tuning is not always optimal compared to audio-only data. Beyond speech intelligibility, our analysis covers speaker similarity, language identification, and predicted MOS.

cs.CL↗

arXiv2024

The VoicePrivacy 2024 Challenge Evaluation Plan

The task of the challenge is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting linguistic content and emotional states. The organizers provide development and evaluation datasets and evaluation scripts, as well as baseline anonymization systems and a list of training resources formed on the basis of the participants' requests. Participants apply their developed anonymization systems, run evaluation scripts and submit evaluation results and anonymized speech data to the organizers. Results will be presented at a workshop held in conjunction with Interspeech 2024 to which all participants are invited to present their challenge systems and to submit additional workshop papers.

eess.AS↗

arXiv2024

Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio

This paper defines Spoof Diarization as a novel task in the Partial Spoof (PS) scenario. It aims to determine what spoofed when, which includes not only locating spoof regions but also clustering them according to different spoofing methods. As a pioneering study in spoof diarization, we focus on defining the task, establishing evaluation metrics, and proposing a benchmark model, namely the Countermeasure-Condition Clustering (3C) model. Utilizing this model, we first explore how to effectively train countermeasures to support spoof diarization using three labeling schemes. We then utilize spoof localization predictions to enhance the diarization performance. This first study reveals the high complexity of the task, even in restricted scenarios where only a single speaker per audio file and an oracle number of spoofing methods are considered. Our code is available at https://github.com/nii-yamagishilab/PartialSpoof.

eess.AS↗

arXiv2024

Event-Triggered Optimal Tracking Control for Strict-Feedback Nonlinear Systems With Non-Affine Nonlinear Faults

This article studies the control ideas of the optimal backstepping technique, proposing an event-triggered optimal tracking control scheme for a class of strict-feedback nonlinear systems with non-affine and nonlinear faults. A simplified identifier-critic-actor framework is employed in the reinforcement learning algorithm to achieve optimal control. The identifier estimates the unknown dynamic functions, the critic evaluates the system performance, and the actor implements control actions, enabling modeling and control of anonymous systems for achieving optimal control performance. In this paper, a simplified reinforcement learning algorithm is designed by deriving update rules from the negative gradient of a simple positive function related to the Hamilton-Jacobi-Bellman equation, and it also releases the stringent persistent excitation condition. Then, a fault-tolerant control method is developed by applying filtered signals for controller design. Additionally, to address communication resource reduction, an event-triggered mechanism is employed for designing the actual controller. Finally, the proposed scheme's feasibility is validated through theoretical analysis and simulation.

math.OC↗

arXiv2024

Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning

In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for both image visualization and subsequent analysis tasks, which often require isotropic voxel spacing. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. However, most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios. In this work, we propose a self-supervised super-resolution framework for inter-slice super-resolution of MR images. Our framework is first featured by pre-training on video dataset, as temporal correlation of videos is found beneficial for modeling the spatial relation among MR slices. Then, we use public high-quality MR dataset to fine-tune our pre-trained model, for enhancing awareness of our model to medical data. Finally, given a target dataset at hand, we utilize self-supervised fine-tuning to further ensure our model works well with user-specific super-resolution tasks. The proposed method demonstrates superior performance compared to other self-supervised methods and also holds the potential to benefit various downstream applications.

eess.IV↗

arXiv2024

In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging

Dual-Camera Compressed Hyperspectral Imaging (DCCHI) offers the capability to reconstruct 3D Hyperspectral Image (HSI) by fusing compressive and Panchromatic (PAN) image, which has shown great potential for snapshot hyperspectral imaging in practice. In this paper, we introduce a novel DCCHI reconstruction network, the Intra-Inter Similarity Exploiting Transformer (In2SET). Our key insight is to make full use of the PAN image to assist the reconstruction. To this end, we propose using the intra-similarity within the PAN image as a proxy for approximating the intra-similarity in the original HSI, thereby offering an enhanced content prior for more accurate HSI reconstruction. Furthermore, we aim to align the features from the underlying HSI with those of the PAN image, maintaining semantic consistency and introducing new contextual information for the reconstruction process. By integrating In2SET into a PAN-guided unrolling framework, our method substantially enhances the spatial-spectral fidelity and detail of the reconstructed images, providing a more comprehensive and accurate depiction of the scene. Extensive experiments conducted on both real and simulated datasets demonstrate that our approach consistently outperforms existing state-of-the-art methods in terms of reconstruction quality and computational complexity. Code will be released.

eess.IV↗

arXiv2024

Attribute-Aware Implicit Modality Alignment for Text Attribute Person Search

Text attribute person search aims to find specific pedestrians through given textual attributes, which is very meaningful in the scene of searching for designated pedestrians through witness descriptions. The key challenge is the significant modality gap between textual attributes and images. Previous methods focused on achieving explicit representation and alignment through unimodal pre-trained models. Nevertheless, the absence of inter-modality correspondence in these models may lead to distortions in the local information of intra-modality. Moreover, these methods only considered the alignment of inter-modality and ignored the differences between different attribute categories. To mitigate the above problems, we propose an Attribute-Aware Implicit Modality Alignment (AIMA) framework to learn the correspondence of local representations between textual attributes and images and combine global representation matching to narrow the modality gap. Firstly, we introduce the CLIP model as the backbone and design prompt templates to transform attribute combinations into structured sentences. This facilitates the model's ability to better understand and match image details. Next, we design a Masked Attribute Prediction (MAP) module that predicts the masked attributes after the interaction of image and masked textual attribute features through multi-modal interaction, thereby achieving implicit local relationship alignment. Finally, we propose an Attribute-IoU Guided Intra-Modal Contrastive (A-IoU IMC) loss, aligning the distribution of different textual attributes in the embedding space with their IoU distribution, achieving better semantic arrangement. Extensive experiments on the Market-1501 Attribute, PETA, and PA100K datasets show that the performance of our proposed method significantly surpasses the current state-of-the-art methods.

cs.CV↗

arXiv2024

Skew Knörrer's periodicity Theorem

In this paper, we introduce a class of twisted matrix algebras of $M_2(E)$ and twisted direct products of $E\times E$ for an algebra $E$. Let $A$ be a noetherian Koszul Artin-Schelter regular algebra, $z\in A_2$ be a regular central element of $A$ and $B=A_P[y_1,y_2;σ]$ be a graded double Ore extension of $A$. We use the Clifford deformation $C_{A^!}(z)$ of Koszul dual $A^!$ to study the noncommutative quadric hypersurface $B/(z+y_1^2+y_2^2)$. We prove that the stable category of graded maximal Cohen-Macaulay modules over $B/(z+y_1^2+y_2^2)$ is equivalent to certain bounded derived categories, which involve a twisted matrix algebra of $M_2(C_{A^!}(z))$ or a twisted direct product of $C_{A^!}(z)\times C_{A^!}(z)$ depending on the values of $P$. These results are presented as skew versions of Knörrer's periodicity theorem. Moreover, we show $B/(z+y_1^2+y_2^2)$ may not be a noncommutative graded isolated singularity even if $A/(z)$ is.

math.RA↗

arXiv2024

Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named $\text{Seed-TTS}_\text{DiT}$, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, $\text{Seed-TTS}_\text{DiT}$ does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at \url{https://bytedancespeech.github.io/seedtts_tech_report}.

eess.AS↗

arXiv2024

Precise Analysis of Covariance Identifiability for Activity Detection in Grant-Free Random Access

We consider the identifiability issue of maximum likelihood based activity detection in massive MIMO based grant-free random access. A prior work by Chen et al. indicates that the identifiability undergoes a phase transition for commonly-used random signatures. In this paper, we provide an analytical characterization of the boundary of the phase transition curve. Our theoretical results agree well with the numerical experiments.

eess.SP↗