arXiv subjects

Tao Wang

Publications and source records attributed to Tao Wang.

At least 379 records · Page 21Linked to original sources

arXiv2024

DIffSteISR: Harnessing Diffusion Prior for Superior Real-world Stereo Image Super-Resolution

We introduce DiffSteISR, a pioneering framework for reconstructing real-world stereo images. DiffSteISR utilizes the powerful prior knowledge embedded in pre-trained text-to-image model to efficiently recover the lost texture details in low-resolution stereo images. Specifically, DiffSteISR implements a time-aware stereo cross attention with temperature adapter (TASCATA) to guide the diffusion process, ensuring that the generated left and right views exhibit high texture consistency thereby reducing disparity error between the super-resolved images and the ground truth (GT) images. Additionally, a stereo omni attention control network (SOA ControlNet) is proposed to enhance the consistency of super-resolved images with GT images in the pixel, perceptual, and distribution space. Finally, DiffSteISR incorporates a stereo semantic extractor (SSE) to capture unique viewpoint soft semantic information and shared hard tag semantic information, thereby effectively improving the semantic accuracy and consistency of the generated left and right images. Extensive experimental results demonstrate that DiffSteISR accurately reconstructs natural and precise textures from low-resolution stereo images while maintaining a high consistency of semantic and texture between the left and right views.

cs.CV↗

arXiv2024

CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning

In the fields of computer vision and robotics, accurate pixel-level correspondences are essential for enabling advanced tasks such as structure-from-motion and simultaneous localization and mapping. Recent correspondence pruning methods usually focus on learning local consistency through k-nearest neighbors, which makes it difficult to capture robust context for each correspondence. We propose CorrAdaptor, a novel architecture that introduces a dual-branch structure capable of adaptively adjusting local contexts through both explicit and implicit local graph learning. Specifically, the explicit branch uses KNN-based graphs tailored for initial neighborhood identification, while the implicit branch leverages a learnable matrix to softly assign neighbors and adaptively expand the local context scope, significantly enhancing the model's robustness and adaptability to complex image variations. Moreover, we design a motion injection module to integrate motion consistency into the network to suppress the impact of outliers and refine local context learning, resulting in substantial performance improvements. The experimental results on extensive correspondence-based tasks indicate that our CorrAdaptor achieves state-of-the-art performance both qualitatively and quantitatively. The code and pre-trained models are available at https://github.com/TaoWangzj/CorrAdaptor.

cs.CV↗

arXiv2024

P/D-Serve: Serving Disaggregated Large Language Model at Scale

Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversity (various prefixes and tidal requests), treating all the prompts in a mixed pool is inadequate. To facilitate the similarity per scenario and minimize the inner mismatch on P/D (prefill and decoding) processing, fine-grained organization is required, dynamically adjusting P/D ratios for better performance. 2) Due to inaccurate estimation on workload (queue status or maintained connections), the global scheduler easily incurs unnecessary timeouts in prefill. 3) Block-fixed device-to-device (D2D) KVCache transfer over cluster-level RDMA (remote direct memory access) fails to achieve desired D2D utilization as expected. To overcome previous problems, this paper proposes an end-to-end system P/D-Serve, complying with the paradigm of MLOps (machine learning operations), which models end-to-end (E2E) P/D performance and enables: 1) fine-grained P/D organization, mapping the service with RoCE (RDMA over converged ethernet) as needed, to facilitate similar processing and dynamic adjustments on P/D ratios; 2) on-demand forwarding upon rejections for idle prefill, decoupling the scheduler from regular inaccurate reports and local queues, to avoid timeouts in prefill; and 3) efficient KVCache transfer via optimized D2D access. P/D-Serve is implemented upon Ascend and MindSpore, has been deployed over tens of thousands of NPUs for more than eight months in commercial use, and further achieves 60\%, 42\% and 46\% improvements on E2E throughput, time-to-first-token (TTFT) SLO (service level objective) and D2D transfer time. As the E2E system with optimizations, P/D-Serve achieves 6.7x increase on throughput, compared with aggregated LLMs.

cs.DC↗

arXiv2024

Black holes regulate cool gas accretion in massive galaxies

The nucleus of almost all massive galaxies contains a supermassive black hole (BH). The feedback from the accretion of these BHs is often considered to have crucial roles in establishing the quiescence of massive galaxies, although some recent studies show that even galaxies hosting the most active BHs do not exhibit a reduction in their molecular gas reservoirs or star formation rates. Therefore, the influence of BHs on galaxy star formation remains highly debated and lacks direct evidence. Here, based on a large sample of nearby galaxies with measurements of masses of both BHs and atomic hydrogen (HI), the main component of the interstellar medium, we show that the HI gas mass to stellar masses ratio ($μ_{\rm HI} = M_{\rm HI}/M_{\star}$) is more strongly correlated with BH masses ($M_{\rm BH}$) than with any other galaxy parameters, including stellar mass, stellar mass surface density and bulge masses. Moreover, once the $μ_{\rm HI}-M_{\rm BH}$ correlation is considered, $μ_{\rm HI}$ loses dependence on other galactic parameters, demonstrating that $M_{\rm BH}$ serves as the primary driver of $μ_{\rm HI}$. These findings provide important evidence for how the accumulated energy from BH accretion regulates the cool gas content in galaxies, by ejecting interstellar medium gas and/or suppressing gas cooling from the circumgalactic medium.

astro-ph.GA↗

arXiv2024

Residual Speaker Representation for One-Shot Voice Conversion

Recently, there have been significant advancements in voice conversion, resulting in high-quality performance. However, there are still two critical challenges in this field. Firstly, current voice conversion methods have limited robustness when encountering unseen speakers. Secondly, they also have limited ability to control timbre representation. To address these challenges, this paper presents a novel approach that leverages tokens of multi-layer residual approximations to enhance robustness when dealing with unseen speakers, called the residual speaker module. Introducing multi-layer approximations facilitates the separation of information from the timbre, enabling effective control over timbre in voice conversion. The proposed method outperforms baselines in subjective and objective evaluations, demonstrating superior performance and increased robustness. Our demo page is publicly available.

cs.SD↗

arXiv2024

UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model

Significant advancements has recently been achieved in the field of multi-modal large language models (MLLMs), demonstrating their remarkable capabilities in understanding and reasoning across diverse tasks. However, these models are often trained for specific tasks and rely on task-specific input-output formats, limiting their applicability to a broader range of tasks. This raises a fundamental question: Can we develop a unified approach to represent and handle different multi-modal tasks to maximize the generalizability of MLLMs? In this paper, we propose UnifiedMLLM, a comprehensive model designed to represent various tasks using a unified representation. Our model exhibits strong capabilities in comprehending the implicit intent of user instructions and preforming reasoning. In addition to generating textual responses, our model also outputs task tokens and grounding tokens, serving as indicators of task types and task granularity. These outputs are subsequently routed through the task router and directed to specific expert models for task completion. To train our model, we construct a task-specific dataset and an 100k multi-task dataset encompassing complex scenarios. Employing a three-stage training strategy, we equip our model with robust reasoning and task processing capabilities while preserving its generalization capacity and knowledge reservoir. Extensive experiments showcase the impressive performance of our unified representation approach across various tasks, surpassing existing methodologies. Furthermore, our approach exhibits exceptional scalability and generality. Our code, model, and dataset will be available at \url{https://github.com/lzw-lzw/UnifiedMLLM}.

cs.CL↗

arXiv2024

Uniqueness of positive radial solutions of Choquard type equations

In this paper, we consider the following Choquard type equation \begin{equation} \left\{\begin{aligned} &-Δu+λu=γ(Φ_N(|x|)\ast|u|^p)u \ \ \mbox{in $\mathbb{R}^N$}, \\ &\lim\limits_{|x|\to\infty}u(x)=0,\\ \end{aligned}\right. \end{equation} where $N\geq2,λ>0,γ>0, p\in[1,2]$ and $Φ_N(|x|)$ denotes the fundamental solution of the Laplacian $-Δ$ on $\mathbb{R}^N$. This equation does not have a variational frame when $p\neq 2.$ Instead of variational methods, we prove the existence and uniqueness of positive radial solutions of the above equation via the shooting method by establishing some new differential inequalities. The proofs are based on an analysis of the corresponding system of second-order differential equations, and our results extend the existing ones in the literature from $p=2$ to $p\in[1,2]$.

math.AP↗

arXiv2024

ICAGC 2024: Inspirational and Convincing Audio Generation Challenge 2024

The Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC 2024) is part of the ISCSLP 2024 Competitions and Challenges track. While current text-to-speech (TTS) technology can generate high-quality audio, its ability to convey complex emotions and controlled detail content remains limited. This constraint leads to a discrepancy between the generated audio and human subjective perception in practical applications like companion robots for children and marketing bots. The core issue lies in the inconsistency between high-quality audio generation and the ultimate human subjective experience. Therefore, this challenge aims to enhance the persuasiveness and acceptability of synthesized audio, focusing on human alignment convincing and inspirational audio generation. A total of 19 teams have registered for the challenge, and the results of the competition and the competition are described in this paper.

eess.AS↗

arXiv2024

Phase engineering of giant second harmonic generation in Bi$_2$O$_2$Se

Two-dimensional (2D) materials with remarkable second-harmonic generation (SHG) hold promise for future on-chip nonlinear optics. Relevant materials with both giant SHG response and environmental stability are long-sought targets. Here, we demonstrate the enormous SHG from the phase engineering of a high-performance semiconductor, Bi$_2$O$_2$Se (BOS), under uniaxial strain. SHG signals captured in strained 20 nm-BOS films exceed those of NbOI$_2$ and NbOCl$_2$ of similar thickness by a factor of 10, and are four orders of magnitude higher than monolayer-MoS$_2$, resulting in a significant second-order nonlinear susceptibility on the order of 1 nm V$^{-1}$. Intriguingly, the strain enables continuous adjustment of the ferroelectric phase transition across room temperature. Consequently, an exceptionally large tunability of SHG, approximately six orders of magnitude, is achieved through strain or thermal modulation. This colossal SHG, originating from the geometric phase of Bloch wave functions and coupled with sensitive tunability through multiple approaches in this air-stable 2D semiconductor, opens new possibilities for designing chip-scale, switchable nonlinear optical devices.

cond-mat.mtrl-sci↗

arXiv2024

Continuously Expanding the Response Frequency of Rydberg Atom-Based Microwave Sensor by Using Quantum Mixer

Microwave electric (MW) field measurements utilizing Rydberg atoms have witnessed significant advancements, achieving remarkable sensitivity, albeit limited to discrete MW frequencies resonant with Rydberg states. Recently, various continuous-frequency measurement schemes have emerged. However, when the MW detuning surpasses 1 GHz, the sensitivity degrades by over an order of magnitude compared to resonant measurements. In this paper, we successfully extend the response frequency range by harnessing a controlled driving field in conjunction with a quantum mixer and heterodyne technology, theoretically enabling infinite scalability. Notably, second-order effects stemming from quantum mixing necessitate careful consideration to ensure accurate electric field measurements. In addition, compared to resonant measurements, the sensitivity decline for far-detuned MW fields exceeding 1 GHz is less than twice, representing a significant improvement of several orders of magnitude over alternative schemes. Furthermore, the sensitivity of far-detuned MW fields can be efficiently enhanced by augmenting the intensity and frequency of the controlled field. For detunings ranging from 100 MHz to 2 GHz, we present optimal sensitivity values and the corresponding methods to achieve them. Our findings pave the way for Rydberg atom-based MW receivers characterized by both high sensitivity and an exceptionally broad bandwidth.

quant-ph↗

arXiv2024

Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned

While the field of NL2SQL has made significant advancements in translating natural language instructions into executable SQL scripts for data querying and processing, achieving full automation within the broader data science pipeline - encompassing data querying, analysis, visualization, and reporting - remains a complex challenge. This study introduces SageCopilot, an advanced, industry-grade system system that automates the data science pipeline by integrating Large Language Models (LLMs), Autonomous Agents (AutoAgents), and Language User Interfaces (LUIs). Specifically, SageCopilot incorporates a two-phase design: an online component refining users' inputs into executable scripts through In-Context Learning (ICL) and running the scripts for results reporting & visualization, and an offline preparing demonstrations requested by ICL in the online phase. A list of trending strategies such as Chain-of-Thought and prompt-tuning have been used to augment SageCopilot for enhanced performance. Through rigorous testing and comparative analysis against prompt-based solutions, SageCopilot has been empirically validated to achieve superior end-to-end performance in generating or executing scripts and offering results with visualization, backed by real-world datasets. Our in-depth ablation studies highlight the individual contributions of various components and strategies used by SageCopilot to the end-to-end correctness for data sciences.

cs.AI↗

arXiv2024

OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models

Personalization is an important topic in text-to-image generation, especially the challenging multi-concept personalization. Current multi-concept methods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlusion-friendly personalized generation framework designed to seamlessly integrate multiple concepts within a single image. We propose a novel two-stage sampling solution. The first stage takes charge of layout generation and visual comprehension information collection for handling occlusions. The second one utilizes the acquired visual comprehension information and the designed noise blending to integrate multiple concepts while considering occlusions. We also observe that the initiation denoising timestep for noise blending is the key to identity preservation and layout. Moreover, our method can be combined with various single-concept models, such as LoRA and InstantID without additional tuning. Especially, LoRA models on civitai.com can be exploited directly. Extensive experiments demonstrate that OMG exhibits superior performance in multi-concept personalization.

cs.CV↗

arXiv2024

Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model

Point cloud segmentation is crucial for robotic visual perception and environmental understanding, enabling applications such as robotic navigation and 3D reconstruction. However, handling the sparse and unordered nature of point cloud data presents challenges for efficient and accurate segmentation. Inspired by the Mamba model's success in natural language processing, we propose the Serialized Point Cloud Mamba Segmentation Model (Serialized Point Mamba), which leverages a state-space model to dynamically compress sequences, reduce memory usage, and enhance computational efficiency. Serialized Point Mamba integrates local-global modeling capabilities with linear complexity, achieving state-of-the-art performance on both indoor and outdoor datasets. This approach includes novel techniques such as staged point cloud sequence learning, grid pooling, and Conditional Positional Encoding, facilitating effective segmentation across diverse point cloud tasks. Our method achieved 76.8 mIoU on Scannet and 70.3 mIoU on S3DIS. In Scannetv2 instance segmentation, it recorded 40.0 mAP. It also had the lowest latency and reasonable memory use, making it the SOTA among point semantic segmentation models based on mamba.

cs.CV↗

arXiv2024

An Empirical Extinction Curve Revealed by Gaia XP Spectra and LAMOST

We present a direct measurement of extinction curves using corrected $Gaia$ XP spectra of the common sources in $Gaia$ DR3 and LAMOST DR7. Our analysis of approximately 370 thousand high-quality samples yielded a high-precision average extinction curve for the Milky Way. After incorporating infrared photometric data from 2MASS and WISE, the extinction curve spans wavelengths from 0.336 to 4.6 $μ$m. We determine an average $R_{55}$ of $2.730 \pm 0.007$, corresponding to $R_V= 3.073 \pm 0.009$, and a near-infrared power-law index $α$ of $1.935 \pm 0.037$. Our study confirmed some intermediate-scale structures within the optical range. Two new features were identified at 540 and 769 nm, and their intensities exhibited a correlation with extinction and $R_V$. This extinction curve can be used to investigate the characteristics of dust and enhance the extinction correction of Milky Way stars. A Python package for this extinction curve is available.

astro-ph.GA↗

arXiv2024

A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunities

In this study, we conduct a comprehensive review of smart grid security, exploring system architectures, attack methodologies, defense strategies, and future research opportunities. We provide an in-depth analysis of various attack vectors, focusing on new attack surfaces introduced by advanced components in smart grids. The review particularly includes an extensive analysis of coordinated attacks that incorporate multiple attack strategies and exploit vulnerabilities across various smart grid components to increase their adverse impact, demonstrating the complexity and potential severity of these threats. Following this, we examine innovative detection and mitigation strategies, including game theory, graph theory, blockchain, and machine learning, discussing their advancements in counteracting evolving threats and associated research challenges. In particular, our review covers a thorough examination of widely used machine learning-based mitigation strategies, analyzing their applications and research challenges spanning across supervised, unsupervised, semi-supervised, ensemble, and reinforcement learning. Further, we outline future research directions and explore new techniques and concerns. We first discuss the research opportunities for existing and emerging strategies, and then explore the potential role of new techniques, such as large language models (LLMs), and the emerging threat of adversarial machine learning in the future of smart grid security.

cs.CR↗

arXiv2024

ASRRL-TTS: Agile Speaker Representation Reinforcement Learning for Text-to-Speech Speaker Adaptation

Speaker adaptation, which involves cloning voices from unseen speakers in the Text-to-Speech task, has garnered significant interest due to its numerous applications in multi-media fields. Despite recent advancements, existing methods often struggle with inadequate speaker representation accuracy and overfitting, particularly in limited reference speeches scenarios. To address these challenges, we propose an Agile Speaker Representation Reinforcement Learning strategy to enhance speaker similarity in speaker adaptation tasks. ASRRL is the first work to apply reinforcement learning to improve the modeling accuracy of speaker embeddings in speaker adaptation, addressing the challenge of decoupling voice content and timbre. Our approach introduces two action strategies tailored to different reference speeches scenarios. In the single-sentence scenario, a knowledge-oriented optimal routine searching RL method is employed to expedite the exploration and retrieval of refinement information on the fringe of speaker representations. In the few-sentence scenario, we utilize a dynamic RL method to adaptively fuse reference speeches, enhancing the robustness and accuracy of speaker modeling. To achieve optimal results in the target domain, a multi-scale fusion scoring mechanism based reward model that evaluates speaker similarity, speech quality, and intelligibility across three dimensions is proposed, ensuring that improvements in speaker similarity do not compromise speech quality or intelligibility. The experimental results on the LibriTTS and VCTK datasets within mainstream TTS frameworks demonstrate the extensibility and generalization capabilities of the proposed ASRRL method. The results indicate that the ASRRL method significantly outperforms traditional fine-tuning approaches, achieving higher speaker similarity and better overall speech quality with limited reference speeches.

eess.AS↗

arXiv2024

NOEMA formIng Cluster survEy (NICE): Characterizing eight massive galaxy groups at $1.5 < z < 4$ in the COSMOS field

The NOEMA formIng Cluster survEy (NICE) is a large program targeting 69 massive galaxy group candidates at $z>2$ in six deep fields. We report spectroscopic confirmation of eight groups at $1.65\leq z\leq3.61$ in COSMOS. Homogeneously selected as significant overdensities of red IRAC sources with red Herschel colors, four groups are confirmed by CO and [CI] with NOEMA 3mm observations, three are confirmed with ALMA, and one is confirmed by H$α$ from Subaru/FMOS. We constructed the integrated FIR SEDs for the eight groups, obtaining total IR SFR $=260-1300~{\rm M_\odot}$~yr$^{-1}$. We adopted six methods to estimate the dark matter masses, including stellar mass to halo mass relations, overdensity with galaxy bias, and NFW profile fitting to radial stellar mass density. We found the radial stellar mass density are consistent with a NFW profile, supporting that they are collapsed structures hosted by a single dark matter halo. The best halo mass estimates are $\log(M_{\rm h}/{\rm M_\odot})=12.8-13.7$ with uncertainty of 0.3 dex. From halo mass estimates, we derive baryonic accretion rate ${\rm BAR}=(1-8)\times10^{3}\,{\rm M_{\odot}/yr}$ for this sample. We find a quasi-linear correlation between the integrated SFR/BAR and the theoretical halo mass limit for cold streams, $M_{\rm stream}/M_{\rm h}$, with ${\rm SFR/BAR}=10^{-0.46\pm0.22}\left({M_{\rm stream}/M_{\rm h}}\right)^{0.71\pm0.16}$ with a scatter of $0.40\,{\rm dex}$. Further, we compare halo masses and stellar masses with simulations, and find all structures are consistent with being progenitors of $M_{\rm h}(z=0)>10^{14}\,{\rm M_{\odot}}$ galaxy clusters, and the most massive central galaxies have stellar masses consistent with brightest cluster galaxies (BCGs) progenitors in the TNG300 simulation. The results strongly suggest these structures are forming massive galaxy clusters via baryonic and dark matter accretion.

astro-ph.GA↗

arXiv2024

ADD 2022: the First Audio Deep Synthesis Detection Challenge

Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios. The first Audio Deep synthesis Detection challenge (ADD) was motivated to fill in the gap. The ADD 2022 includes three tracks: low-quality fake audio detection (LF), partially fake audio detection (PF) and audio fake game (FG). The LF track focuses on dealing with bona fide and fully fake utterances with various real-world noises etc. The PF track aims to distinguish the partially fake audio from the real. The FG track is a rivalry game, which includes two tasks: an audio generation task and an audio fake detection task. In this paper, we describe the datasets, evaluation metrics, and protocols. We also report major findings that reflect the recent advances in audio deepfake detection tasks.

cs.SD↗