arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 703 records · Page 39Linked to original sources

arXiv2024

Spatial Variations of Dust Opacity and Grain Growth in Dark Clouds: L1689, L1709 and L1712

The far-infrared (FIR) opacity of dust in dark clouds within the Ophiuchus molecular cloud is investigated through multi-wavelength infrared observations from UKIDSS, Spitzer and Herschel. Employing the infrared color excess technique with both near-infrared (NIR) and mid-infrared (MIR) photometric data, a high-resolution extinction map in the $K$ band ($A_K$) is constructed for three dark clouds: L1689, L1709, and L1712. The derived extinction map has a resolution of $1'$ and reaches a depth of $A_K\sim3$ mag. The FIR optical depths $τ_{250}$ at a reference wavelength of $250\,\rm μm$ are obtained by fitting the Herschel PACS and SPIRE continuum data at 100, 160, 250, 350 and 500 $\rm μm$ using a modified blackbody model. The average dust opacity per unit gas mass at $250\rm μm$, $rκ_{250}$ is determined through a pixel-by-pixel correlation of $τ_{250}$ with $A_K$, yielding a value of approximately $0.09\,\rm cm^2\,g^{-1}$, which is about 2-3 times higher than the typical value in the diffuse interstellar medium (ISM). Additionally, an independent analysis across 16 sub-regions within the Ophiuchus cloud indicates spatial variations in dust opacity, with values ranging from 0.07-0.12$\,\rm cm^2\,g^{-1}$. Although the observed trend of increasing dust opacity with higher extinction implies grain growth, our findings indicate that rapid grain growth clearly not yet occurred in the dark clouds studied in this work.

astro-ph.GA↗

arXiv2024

Generalizing Geometric Nonwindowed Scattering Transforms on Compact Riemannian Manifolds

Let $\mathcal{M}$ be a compact, smooth, $n$-dimensional Riemannian manifold without boundary. In this paper, we generalize nonwindowed geometric scattering transforms, which we formulate as $\mathbf{L}^q(\mathcal{M})$ norms of a cascade of geometric wavelet transforms and modulus operators. We then provide weighted measures for these operators, prove that these operators are well-defined under specific conditions on the manifold, invariant to the action of isometries, and stable to diffeomorphisms for $λ$-bandlimited functions.

math.FA↗

arXiv2024

MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/MobileVLM .

cs.CV↗

arXiv2024

Are Synthetic Time-series Data Really not as Good as Real Data?

Time-series data presents limitations stemming from data quality issues, bias and vulnerabilities, and generalization problem. Integrating universal data synthesis methods holds promise in improving generalization. However, current methods cannot guarantee that the generator's output covers all unseen real data. In this paper, we introduce InfoBoost -- a highly versatile cross-domain data synthesizing framework with time series representation learning capability. We have developed a method based on synthetic data that enables model training without the need for real data, surpassing the performance of models trained with real data. Additionally, we have trained a universal feature extractor based on our synthetic data that is applicable to all time-series data. Our approach overcomes interference from multiple sources rhythmic signal, noise interference, and long-period features that exceed sampling window capabilities. Through experiments, our non-deep-learning synthetic data enables models to achieve superior reconstruction performance and universal explicit representation extraction without the need for real data.

cs.LG↗

arXiv2024

MiniDisc: Minimal Distillation Schedule for Language Model Compression

Recent studies have uncovered that language model distillation is less effective when facing a large capacity gap between the teacher and the student, and introduced teacher assistant-based distillation to bridge the gap. As a connection, the scale and the performance of the teacher assistant is of vital importance to bring the knowledge from the teacher to the student. However, existing teacher assistant-based methods require maximally many trials before scheduling an optimal teacher assistant. To this end, we propose a minimal distillation schedule (MiniDisc) for scheduling the optimal teacher assistant in minimally one trial. In particular, motivated by the finding that the performance of the student is positively correlated to the scale-performance tradeoff of the teacher assistant, MiniDisc is designed with a $λ$-tradeoff to measure the optimality of the teacher assistant without trial distillation to the student. MiniDisc then can schedule the optimal teacher assistant with the best $λ$-tradeoff in a sandwich framework. MiniDisc is evaluated with an extensive set of experiments on GLUE. Experimental results demonstrate the improved efficiency our MiniDisc compared to several state-of-the-art baselines. We further apply MiniDisc to a language model with billions of parameters and show its scalability.

cs.CL↗

arXiv2024

Fast Updating Truncated SVD for Representation Learning with Sparse Matrices

Updating a truncated Singular Value Decomposition (SVD) is crucial in representation learning, especially when dealing with large-scale data matrices that continuously evolve in practical scenarios. Aligning SVD-based models with fast-paced updates becomes increasingly important. Existing methods for updating truncated SVDs employ Rayleigh-Ritz projection procedures, where projection matrices are augmented based on original singular vectors. However, these methods suffer from inefficiency due to the densification of the update matrix and the application of the projection to all singular vectors. To address these limitations, we introduce a novel method for dynamically approximating the truncated SVD of a sparse and temporally evolving matrix. Our approach leverages sparsity in the orthogonalization process of augmented matrices and utilizes an extended decomposition to independently store projections in the column space of singular vectors. Numerical experiments demonstrate a remarkable efficiency improvement of an order of magnitude compared to previous methods. Remarkably, this improvement is achieved while maintaining a comparable precision to existing approaches.

math.NA↗

arXiv2024

Binaural Angular Separation Network

We propose a neural network model that can separate target speech sources from interfering sources at different angular regions using two microphones. The model is trained with simulated room impulse responses (RIRs) using omni-directional microphones without needing to collect real RIRs. By relying on specific angular regions and multiple room simulations, the model utilizes consistent time difference of arrival (TDOA) cues, or what we call delay contrast, to separate target and interference sources while remaining robust in various reverberation environments. We demonstrate the model is not only generalizable to a commercially available device with a slightly different microphone geometry, but also outperforms our previous work which uses one additional microphone on the same device. The model runs in real-time on-device and is suitable for low-latency streaming applications such as telephony and video conferencing.

eess.AS↗

arXiv2024

Robust Semi-Supervised Learning for Self-learning Open-World Classes

Existing semi-supervised learning (SSL) methods assume that labeled and unlabeled data share the same class space. However, in real-world applications, unlabeled data always contain classes not present in the labeled set, which may cause classification performance degradation of known classes. Therefore, open-world SSL approaches are researched to handle the presence of multiple unknown classes in the unlabeled data, which aims to accurately classify known classes while fine-grained distinguishing different unknown classes. To address this challenge, in this paper, we propose an open-world SSL method for Self-learning Open-world Classes (SSOC), which can explicitly self-learn multiple unknown classes. Specifically, SSOC first defines class center tokens for both known and unknown classes and autonomously learns token representations according to all samples with the cross-attention mechanism. To effectively discover novel classes, SSOC further designs a pairwise similarity loss in addition to the entropy loss, which can wisely exploit the information available in unlabeled data from instances' predictions and relationships. Extensive experiments demonstrate that SSOC outperforms the state-of-the-art baselines on multiple popular classification benchmarks. Specifically, on the ImageNet-100 dataset with a novel ratio of 90%, SSOC achieves a remarkable 22% improvement.

cs.LG↗

arXiv2024

A Novel DDPM-based Ensemble Approach for Energy Theft Detection in Smart Grids

Energy theft, characterized by manipulating energy consumption readings to reduce payments, poses a dual threat-causing financial losses for grid operators and undermining the performance of smart grids. Effective Energy Theft Detection (ETD) methods become crucial in mitigating these risks by identifying such fraudulent activities in their early stages. However, the majority of current ETD methods rely on supervised learning, which is hindered by the difficulty of labelling data and the risk of overfitting known attacks. To address these challenges, several unsupervised ETD methods have been proposed, focusing on learning the normal patterns from honest users, specifically the reconstruction of input. However, our investigation reveals a limitation in current unsupervised ETD methods, as they can only detect anomalous behaviours in users exhibiting regular patterns. Users with high-variance behaviours pose a challenge to these methods. In response, this paper introduces a Denoising Diffusion Probabilistic Model (DDPM)-based ETD approach. This innovative approach demonstrates impressive ETD performance on high-variance smart grid data by incorporating additional attributes correlated with energy consumption. The proposed methods improve the average ETD performance on high-variance smart grid data from below 0.5 to over 0.9 w.r.t. AUC. On the other hand, our experimental findings indicate that while the state-of-the-art ETD methods based on reconstruction error can identify ETD attacks for the majority of users, they prove ineffective in detecting attacks for certain users. To address this, we propose a novel ensemble approach that considers both reconstruction error and forecasting error, enhancing the robustness of the ETD methodology. The proposed ensemble method improves the average ETD performance on the stealthiest attacks from nearly 0 to 0.5 w.r.t. 5%-TPR.

cs.LG↗

arXiv2024

Functional Geometry Guided Protein Sequence and Backbone Structure Co-Design

Proteins are macromolecules responsible for essential functions in almost all living organisms. Designing reasonable proteins with desired functions is crucial. A protein's sequence and structure are strongly correlated and they together determine its function. In this paper, we propose NAEPro, a model to jointly design Protein sequence and structure based on automatically detected functional sites. NAEPro is powered by an interleaving network of attention and equivariant layers, which can capture global correlation in a whole sequence and local influence from nearest amino acids in three dimensional (3D) space. Such an architecture facilitates effective yet economic message passing at two levels. We evaluate our model and several strong baselines on two protein datasets, $β$-lactamase and myoglobin. Experimental results show that our model consistently achieves the highest amino acid recovery rate, TM-score, and the lowest RMSD among all competitors. These findings prove the capability of our model to design protein sequences and structures that closely resemble their natural counterparts. Furthermore, in-depth analysis further confirms our model's ability to generate highly effective proteins capable of binding to their target metallocofactors. We provide code, data and models in Github.

cs.LG↗

arXiv2024

Distilling Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection

Striking a balance between precision and efficiency presents a prominent challenge in the bird's-eye-view (BEV) 3D object detection. Although previous camera-based BEV methods achieved remarkable performance by incorporating long-term temporal information, most of them still face the problem of low efficiency. One potential solution is knowledge distillation. Existing distillation methods only focus on reconstructing spatial features, while overlooking temporal knowledge. To this end, we propose TempDistiller, a Temporal knowledge Distiller, to acquire long-term memory from a teacher detector when provided with a limited number of frames. Specifically, a reconstruction target is formulated by integrating long-term temporal knowledge through self-attention operation applied to feature teachers. Subsequently, novel features are generated for masked student features via a generator. Ultimately, we utilize this reconstruction target to reconstruct the student features. In addition, we also explore temporal relational knowledge when inputting full frames for the student model. We verify the effectiveness of the proposed method on the nuScenes benchmark. The experimental results show our method obtain an enhancement of +1.6 mAP and +1.1 NDS compared to the baseline, a speed improvement of approximately 6 FPS after compressing temporal knowledge, and the most accurate velocity estimation.

cs.CV↗

arXiv2024

GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation

In this paper, we propose a novel cascaded diffusion-based generative framework for text-driven human motion synthesis, which exploits a strategy named GradUally Enriching SyntheSis (GUESS as its abbreviation). The strategy sets up generation objectives by grouping body joints of detailed skeletons in close semantic proximity together and then replacing each of such joint group with a single body-part node. Such an operation recursively abstracts a human pose to coarser and coarser skeletons at multiple granularity levels. With gradually increasing the abstraction level, human motion becomes more and more concise and stable, significantly benefiting the cross-modal motion synthesis task. The whole text-driven human motion synthesis problem is then divided into multiple abstraction levels and solved with a multi-stage generation framework with a cascaded latent diffusion model: an initial generator first generates the coarsest human motion guess from a given text description; then, a series of successive generators gradually enrich the motion details based on the textual description and the previous synthesized results. Notably, we further integrate GUESS with the proposed dynamic multi-condition fusion mechanism to dynamically balance the cooperative effects of the given textual condition and synthesized coarse motion prompt in different generation stages. Extensive experiments on large-scale datasets verify that GUESS outperforms existing state-of-the-art methods by large margins in terms of accuracy, realisticness, and diversity. Code is available at https://github.com/Xuehao-Gao/GUESS.

cs.CV↗

arXiv2024

Hierarchical speaker representation for target speaker extraction

Target speaker extraction aims to isolate a specific speaker's voice from a composite of multiple sound sources, guided by an enrollment utterance or called anchor. Current methods predominantly derive speaker embeddings from the anchor and integrate them into the separation network to separate the voice of the target speaker. However, the representation of the speaker embedding is too simplistic, often being merely a 1*1024 vector. This dense information makes it difficult for the separation network to harness effectively. To address this limitation, we introduce a pioneering methodology called Hierarchical Representation (HR) that seamlessly fuses anchor data across granular and overarching 5 layers of the separation network, enhancing the precision of target extraction. HR amplifies the efficacy of anchors to improve target speaker isolation. On the Libri-2talker dataset, HR substantially outperforms state-of-the-art time-frequency domain techniques. Further demonstrating HR's capabilities, we achieved first place in the prestigious ICASSP 2023 Deep Noise Suppression Challenge. The proposed HR methodology shows great promise for advancing target speaker extraction through enhanced anchor utilization.

cs.SD↗

arXiv2024

3S-TSE: Efficient Three-Stage Target Speaker Extraction for Real-Time and Low-Resource Applications

Target speaker extraction (TSE) aims to isolate a specific voice from multiple mixed speakers relying on a registerd sample. Since voiceprint features usually vary greatly, current end-to-end neural networks require large model parameters which are computational intensive and impractical for real-time applications, espetially on resource-constrained platforms. In this paper, we address the TSE task using microphone array and introduce a novel three-stage solution that systematically decouples the process: First, a neural network is trained to estimate the direction of the target speaker. Second, with the direction determined, the Generalized Sidelobe Canceller (GSC) is used to extract the target speech. Third, an Inplace Convolutional Recurrent Neural Network (ICRN) acts as a denoising post-processor, refining the GSC output to yield the final separated speech. Our approach delivers superior performance while drastically reducing computational load, setting a new standard for efficient real-time target speaker extraction.

cs.SD↗

arXiv2024

StreamVC: Real-Time Low-Latency Voice Conversion

We present StreamVC, a streaming voice conversion solution that preserves the content and prosody of any source speech while matching the voice timbre from any target speech. Unlike previous approaches, StreamVC produces the resulting waveform at low latency from the input signal even on a mobile platform, making it applicable to real-time communication scenarios like calls and video conferencing, and addressing use cases such as voice anonymization in these scenarios. Our design leverages the architecture and training strategy of the SoundStream neural audio codec for lightweight high-quality speech synthesis. We demonstrate the feasibility of learning soft speech units causally, as well as the effectiveness of supplying whitened fundamental frequency information to improve pitch stability without leaking the source timbre information.

eess.AS↗

arXiv2024

OFDM-Based Digital Semantic Communication with Importance Awareness

Semantic communication (SemCom) has received considerable attention for its ability to reduce data transmission size while maintaining task performance. However, existing works mainly focus on analog SemCom with simple channel models, which may limit its practical application. To reduce this gap, we propose an orthogonal frequency division multiplexing (OFDM)-based SemCom system that is compatible with existing digital communication infrastructures. In the considered system, the extracted semantics is quantized by scalar quantizers, transformed into OFDM signal, and then transmitted over the frequency-selective channel. Moreover, we propose a semantic importance measurement method to build the relationship between target task and semantic features. Based on semantic importance, we formulate a sub-carrier and bit allocation problem to maximize communication performance. However, the optimization objective function cannot be accurately characterized using a mathematical expression due to the neural network-based semantic codec. Given the complex nature of the problem, we first propose a low-complexity sub-carrier allocation method that assigns sub-carriers with better channel conditions to more critical semantics. Then, we propose a deep reinforcement learning-based bit allocation algorithm with dynamic action space. Simulation results demonstrate that the proposed system achieves 9.7% and 28.7% performance gains compared to analog SemCom and conventional bit-based communication systems, respectively.

eess.SP↗

arXiv2023

Shape-programmable Adaptive Multi-material Microrobots for Biomedical Applications

Flagellated microorganisms can swim at low Reynolds numbers and adapt to changes in their environment. Specifically, the flagella can switch their shapes or modes through gene expression. In the past decade, efforts have been made to fabricate and investigate rigid types of microrobots without any adaptation to the environments. More recently, obtaining adaptive microrobots mimicking real microorganisms is getting more attention. However, even though some adaptive microrobots achieved by hydrogels have emerged, the swimming behaviors of the microrobots before and after the environment-induced deformations are not predicted in a systematic standardized way. In this work, experiments, finite element analysis, and dynamic modeling are presented together to realize a complete understanding of these adaptive microrobots. The above three parts are cross-verified proving the success of using such methods, facilitating the bio-applications with shape-programmable and even swimming performance-programmable microrobots. Moreover, an application of targeted object delivery using the proposed microrobot has been successfully demonstrated. Finally, cytotoxicity tests are performed to prove the potential for using the proposed microrobot for biomedical applications.

cs.RO↗

arXiv2023

MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices. It is an amalgamation of a myriad of architectural designs and techniques that are mobile-oriented, which comprises a set of language models at the scale of 1.4B and 2.7B parameters, trained from scratch, a multimodal vision model that is pre-trained in the CLIP fashion, cross-modality interaction via an efficient projector. We evaluate MobileVLM on several typical VLM benchmarks. Our models demonstrate on par performance compared with a few much larger models. More importantly, we measure the inference speed on both a Qualcomm Snapdragon 888 CPU and an NVIDIA Jeston Orin GPU, and we obtain state-of-the-art performance of 21.5 tokens and 65.3 tokens per second, respectively. Our code will be made available at: https://github.com/Meituan-AutoML/MobileVLM.

cs.CV↗