arXiv subjects

Zihao Chen

Publications and source records attributed to Zihao Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Your contrastive learning problem is secretly a distribution alignment problem

Despite the success of contrastive learning (CL) in vision and language, its theoretical foundations and mechanisms for building representations remain poorly understood. In this work, we build connections between noise contrastive estimation losses widely used in CL and distribution alignment with entropic optimal transport (OT). This connection allows us to develop a family of different losses and multistep iterative variants for existing CL methods. Intuitively, by using more information from the distribution of latents, our approach allows a more distribution-aware manipulation of the relationships within augmented sample sets. We provide theoretical insights and experimental evidence demonstrating the benefits of our approach for {\em generalized contrastive alignment}. Through this framework, it is possible to leverage tools in OT to build unbalanced losses to handle noisy views and customize the representation space by changing the constraints on alignment. By reframing contrastive learning as an alignment problem and leveraging existing optimization tools for OT, our work provides new insights and connections between different self-supervised learning models in addition to new tools that can be more easily adapted to incorporate domain knowledge into learning.

cs.LG↗

arXiv2025

ComposeOn Academy: Transforming Melodic Ideas into Complete Compositions Integrating Music Learning

Music composition has long been recognized as a significant art form. However, existing digital audio workstations and music production software often present high entry barriers for users lacking formal musical training. To address this, we introduce ComposeOn, a music theory-based tool designed for users with limited musical knowledge. ComposeOn enables users to easily extend their melodic ideas into complete compositions and offers simple editing features. By integrating music theory, it explains music creation at beginner, intermediate, and advanced levels. Our user study (N=10) compared ComposeOn with the baseline method, Suno AI, demonstrating that ComposeOn provides a more accessible and enjoyable composing and learning experience for individuals with limited musical skills. ComposeOn bridges the gap between theory and practice, offering an innovative solution as both a composition aid and music education platform. The study also explores the differences between theory-based music creation and generative music, highlighting the former's advantages in personal expression and learning.

cs.HC↗

arXiv2024

Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio

One fascinating aspect of pre-trained Audio-Language Models (ALMs) learning is their impressive zero-shot generalization capability and test-time adaptation (TTA) methods aiming to improve domain performance without annotations. However, previous test time adaptation (TTA) methods for ALMs in zero-shot classification tend to be stuck in incorrect model predictions. In order to further boost the performance, we propose multiple guidance on prompt learning without annotated labels. First, guidance of consistency on both context tokens and domain tokens of ALMs is set. Second, guidance of both consistency across multiple augmented views of each single test sample and contrastive learning across different test samples is set. Third, we propose a corresponding end-end learning framework for the proposed test-time adaptation method without annotated labels. We extensively evaluate our approach on 12 downstream tasks across domains, our proposed adaptation method leads to 4.41% (max 7.50%) average zero-shot performance improvement in comparison with the state-of-the-art models.

cs.SD↗

arXiv2024

YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls

Generating sound effects for product-level videos, where only a small amount of labeled data is available for diverse scenes, requires the production of high-quality sounds in few-shot settings. To tackle the challenge of limited labeled data in real-world scenes, we introduce YingSound, a foundation model designed for video-guided sound generation that supports high-quality audio generation in few-shot settings. Specifically, YingSound consists of two major modules. The first module uses a conditional flow matching transformer to achieve effective semantic alignment in sound generation across audio and visual modalities. This module aims to build a learnable audio-visual aggregator (AVA) that integrates high-resolution visual features with corresponding audio features at multiple stages. The second module is developed with a proposed multi-modal visual-audio chain-of-thought (CoT) approach to generate finer sound effects in few-shot settings. Finally, an industry-standard video-to-audio (V2A) dataset that encompasses various real-world scenarios is presented. We show that YingSound effectively generates high-quality synchronized sounds across diverse conditional inputs through automated evaluations and human studies. Project Page: \url{https://giantailab.github.io/yingsound/}

cs.SD↗

arXiv2024

Miniaturized spectrometer enabled by end-to-end deep learning on large-scale radiative cavity array

Miniaturized (mini-) spectrometers are highly desirable tools for chemical, biological, and medical diagnostics because of their potential for portable and in situ spectral detection. In this work, we propose and demonstrate a mini-spectrometer that combines a large-scale radiative cavity array with end-to-end deep learning networks. Specifically, we utilize high-Q bound states in continuum cavities with distinct radiation characteristics as the fundamental units to achieve parallel spectral detection. We realize a 36 $\times$ 30 cavity array that spans a wide spectral range from 1525 to 1605 nm with quality factors above 10^4. We further train a deep network with 8000 outputs to directly map arbitrary spectra to array responses excited by the out-of-plane incident. Experimental results demonstrate that the proposed mini-spectrometer can resolve unknown spectra with a resolution of 0.048 nm in a bandwidth of 80 nm and fidelity exceeding 95%, thus offering a promising method for compact, high resolution, and broadband spectroscopy.

physics.optics↗

arXiv2024

An Attack Traffic Identification Method Based on Temporal Spectrum

To address the issues of insufficient robustness, unstable features, and data noise interference in existing network attack detection and identification models, this paper proposes an attack traffic detection and identification method based on temporal spectrum. First, traffic data is segmented by a sliding window to construct a feature sequence and a corresponding label sequence for network traffic. Next, the proposed spectral label generation methods, SSPE and COAP, are applied to transform the label sequence into spectral labels and the feature sequence into temporal features. Spectral labels and temporal features are used to capture and represent behavioral patterns of attacks. Finally, the constructed temporal features and spectral labels are used to train models, which subsequently detects and identifies network attack behaviors. Experimental results demonstrate that compared to traditional methods, models trained with the SSPE or COAP method improve identification accuracy by 10%, and exhibit strong robustness, particularly in noisy environments.

cs.AI↗

arXiv2024

Intensity correlations in measurement-device-independent quantum key distribution

The intensity correlations due to imperfect modulation during the quantum-state preparation in a measurement-device-independent quantum key distribution (MDI QKD) system compromise its security performance. Therefore, it is crucial to assess the impact of intensity correlations on the practical security of MDI QKD systems. In this work, we propose a theoretical model that quantitatively analyzes the secure key rate of MDI QKD systems under intensity correlations. Furthermore, we apply the theoretical model to a practical MDI QKD system with measured intensity correlations, which shows that the system struggles to generate keys efficiently under this model. We also explore the boundary conditions of intensity correlations to generate secret keys. This study extends the security analysis of intensity correlations to MDI QKD protocols, providing a methodology to evaluate the practical security of MDI QKD systems.

quant-ph↗

arXiv2024

Isometric Immersion Learning with Riemannian Geometry

Manifold learning has been proven to be an effective method for capturing the implicitly intrinsic structure of non-Euclidean data, in which one of the primary challenges is how to maintain the distortion-free (isometry) of the data representations. Actually, there is still no manifold learning method that provides a theoretical guarantee of isometry. Inspired by Nash's isometric theorem, we introduce a new concept called isometric immersion learning based on Riemannian geometry principles. Following this concept, an unsupervised neural network-based model that simultaneously achieves metric and manifold learning is proposed by integrating Riemannian geometry priors. What's more, we theoretically derive and algorithmically implement a maximum likelihood estimation-based training method for the new model. In the simulation experiments, we compared the new model with the state-of-the-art baselines on various 3-D geometry datasets, demonstrating that the new model exhibited significantly superior performance in multiple evaluation metrics. Moreover, we applied the Riemannian metric learned from the new model to downstream prediction tasks in real-world scenarios, and the accuracy was improved by an average of 8.8%.

cs.LG↗

arXiv2024

Symbol-Level Precoding-Based Self-Interference Cancellation for ISAC Systems

Consider an integrated sensing and communication (ISAC) system where a base station (BS) employs a full-duplex radio to simultaneously serve multiple users and detect a target. The detection performance of the BS may be compromised by self-interference (SI) leakage. This paper investigates the feasibility of SI cancellation (SIC) through the application of symbol-level precoding (SLP). We first derive the target detection probability in the presence of the SI. We then formulate an SLP-based SIC problem, which optimizes the target detection probability while satisfying the quality of service requirements of all users. The formulated problem is a nonconvex fractional programming (FP) problem with a large number of equality and inequality constraints. We propose a penalty-based block coordinate descent (BCD) algorithm for solving the formulated problem, which allows for efficient closed-form updates of each block of variables at each iteration. Finally, numerical simulation results are presented to showcase the enhanced detection performance of the proposed SIC approach.

eess.SP↗

arXiv2024

Bailing-TTS: Chinese Dialectal Speech Synthesis Towards Human-like Spontaneous Representation

Large-scale text-to-speech (TTS) models have made significant progress recently.However, they still fall short in the generation of Chinese dialectal speech. Toaddress this, we propose Bailing-TTS, a family of large-scale TTS models capable of generating high-quality Chinese dialectal speech. Bailing-TTS serves as a foundation model for Chinese dialectal speech generation. First, continual semi-supervised learning is proposed to facilitate the alignment of text tokens and speech tokens. Second, the Chinese dialectal representation learning is developed using a specific transformer architecture and multi-stage training processes. With the proposed design of novel network architecture and corresponding strategy, Bailing-TTS is able to generate Chinese dialectal speech from text effectively and efficiently. Experiments demonstrate that Bailing-TTS generates Chinese dialectal speech towards human-like spontaneous representation. Readers are encouraged to listen to demos at \url{https://c9412600.github.io/bltts_tech_report/index.html}.

cs.CL↗

arXiv2024

Scalable and Versatile Linear Computation with Minimalistic Photonic Matrix Processor

The advancement of artificial intelligence demands flexible multimodal data processing with high throughput and energy efficiency. Photonic integrated circuits (PIC) has demonstrated promising potentials in terms of low latency and low power consumption per operation for linear operations such as matrix-vector multiplication. However, the existing schemes face challenges in their scalability due to the use of photonic circuits that expand with the scale of the operants, despite efforts of exploiting the multiple optical parameter dimensions such as time, wavelength and spatial parallelism. They also lacked flexibility and efficiency in switching between different types of operations or tasks and adapting to multimodal data. In this article, we introduce an optical matrix processor (MP) with a minimalistic recursive structure for both multiplications and accumulations. The MP consists of an eletro-optic ring-modulator implemented as a thin-film lithium niobate PIC that allows flexible configurability and time-division multiplexed scheduling. The MP supports not only versatile linear operations including vector/matrix-vector multiplication and single/multi-kernel convolution but also ultrafast task switching and adaptability to data of different sizes, by simply adjusting the data baud rate relative to the ring delay without structural modifications. We demonstrate its capabilities in a optic-electronic convolutional neural network with a computing throughput up to 73.4 billion operations per second. The MP further supports high scalability through appropriate allocation of wavelength and space resources,extending computing parallelism to handle higher data volumes with higher energy efficiency. This novel scheme paves the way for a new class of photonic processorscapable of managing escalating data workloads with unprecedented flexibility, efficiency and scalability.

physics.optics↗

arXiv2024

Feature screening for clustering analysis

In this paper, we consider feature screening for ultrahigh dimensional clustering analyses. Based on the observation that the marginal distribution of any given feature is a mixture of its conditional distributions in different clusters, we propose to screen clustering features by independently evaluating the homogeneity of each feature's mixture distribution. Important cluster-relevant features have heterogeneous components in their mixture distributions and unimportant features have homogeneous components. The well-known EM-test statistic is used to evaluate the homogeneity. Under general parametric settings, we establish the tail probability bounds of the EM-test statistic for the homogeneous and heterogeneous features, and further show that the proposed screening procedure can achieve the sure independent screening and even the consistency in selection properties. Limiting distribution of the EM-test statistic is also obtained for general parametric distributions. The proposed method is computationally efficient, can accurately screen for important cluster-relevant features and help to significantly improve clustering, as demonstrated in our extensive simulation and real data analyses.

stat.ME↗

arXiv2023

Single-Molecule Morphology of Topologically Digested Olympic Networks

The kinetoplast DNA (kDNA) is the archetype of a two-dimensional Olympic network, composed of thousands of DNA minicircles and found in the mitochondrion of certain parasites. The evolution, replication and self-assembly of this structure are fascinating open questions in biology that can also inform us how to realise synthetic Olympic networks in vitro. To obtain a deeper understanding of the structure and assembly of kDNA networks, we sequenced the Crithidia fasciculata kDNA genome and performed high-resolution Atomic Force Microscopy (AFM) and analysis of kDNA networks that had been partially digested by selected restriction enzymes. We discovered that these topological perturbations lead to networks with significantly different geometrical features and morphologies with respect to the unperturbed kDNA, and that these changes are strongly dependent on the class of DNA circles targeted by the restriction enzymes. Specifically, cleaving maxicircles leads to a dramatic reduction in network size once adsorbed onto the surface, whilst cleaving both maxicircles and a minor class of minicircles yields non-circular and deformed structures. We argue that our results are a consequence of a precise positioning of the maxicircles at the boundary of the network, and we discuss our findings in the context of kDNA biogenesis, design of artificial Olympic networks and detection of in vivo perturbations.

cond-mat.soft↗

arXiv2023

Statistical Barriers to Affine-equivariant Estimation

We investigate the quantitative performance of affine-equivariant estimators for robust mean estimation. As a natural stability requirement, the construction of such affine-equivariant estimators has been extensively studied in the statistics literature. We quantitatively evaluate these estimators under two outlier models which have been the subject of much recent work: the heavy-tailed and adversarial corruption settings. We establish lower bounds which show that affine-equivariance induces a strict degradation in recovery error with quantitative rates degrading by a factor of $\sqrt{d}$ in both settings. We find that classical estimators such as the Tukey median (Tukey '75) and Stahel-Donoho estimator (Stahel '81 and Donoho '82) are either quantitatively sub-optimal even within the class of affine-equivariant estimators or lack any quantitative guarantees. On the other hand, recent estimators with strong quantitative guarantees are not affine-equivariant or require additional distributional assumptions to achieve it. We remedy this by constructing a new affine-equivariant estimator which nearly matches our lower bound. Our estimator is based on a novel notion of a high-dimensional median which may be of independent interest. Notably, our results are applicable more broadly to any estimator whose performance is evaluated in the Mahalanobis norm which, for affine-equivariant estimators, corresponds to an evaluation in Euclidean norm on isotropic distributions.

math.ST↗

arXiv2023

Investigation into the nature behind the interesting half levitation behavior of claimed superconductor LK-99

A recent article published by Lee et.al. claimed to have successfully achieved superconductivity at room temperature (RT) has become a topical issue. Besides the research paper, Lee and his team provided a demonstration video of LK-99 half levitating (HL) on a magnet. Such interesting HL appearance has drawn tremendous sensation both in academia and the network. However, the true identity of LK-99 still remains unclear, i.e., whether the HL behavior can necessarily indicate the diamagnetism behavior of the sample. Here, we fabricated our own LK-99 samples following the procedures reported by Lee et al. We found quite a few sample pieces showing the typical HL that is similar to those reported. Meanwhile, oxidation during the sample preparation was found to deleterious to acquiring HL in the sample, while furnace cooling or water quenching in the last step revealed little effect. However, our careful observations indicated that those HL pieces are more likely simple ferromagnetic. Then we conducted a comprehensive study on the behavior patterns of typical diamagnetism and ferromagnetic substances interacting with a Nd2Fe14B magnet, and provided instructions to distinguish the characteristics between ferromagnetic and diamagnetic to prevent misunderstanding of LK-99 like levitation behavior.

cond-mat.mtrl-sci↗

arXiv2023

Enhancing Cardiac MRI Segmentation via Classifier-Guided Two-Stage Network and All-Slice Information Fusion Transformer

Cardiac Magnetic Resonance imaging (CMR) is the gold standard for assessing cardiac function. Segmenting the left ventricle (LV), right ventricle (RV), and LV myocardium (MYO) in CMR images is crucial but time-consuming. Deep learning-based segmentation methods have emerged as effective tools for automating this process. However, CMR images present additional challenges due to irregular and varying heart shapes, particularly in basal and apical slices. In this study, we propose a classifier-guided two-stage network with an all-slice fusion transformer to enhance CMR segmentation accuracy, particularly in basal and apical slices. Our method was evaluated on extensive clinical datasets and demonstrated better performance in terms of Dice score compared to previous CNN-based and transformer-based models. Moreover, our method produces visually appealing segmentation shapes resembling human annotations and avoids common issues like holes or fragments in other models' segmentations.

eess.IV↗

arXiv2023

Ultra-low-loss optical interconnect enabled by topological unidirectional guided resonance

Grating couplers that interconnect photonic chips to off-chip components are of essential importance for various optoelectronics applications. Despite numerous efforts in past decades, existing grating couplers still suffer from poor energy efficiency and thus hinder photonic integration toward a larger scale. Here, we theoretically propose and experimentally demonstrate a method to achieve ultra-low-loss grating coupler by employing topological unidirectional guided resonances (UGRs). Leveraging the unidirectional emitting nature of UGRs, the useless downward radiation is greatly suppressed with no mirror placed on the bottom. By engineering the dispersion and apodizing the geometry of grating, we realize a grating coupler on 340 nm silicon-on-insulator platform with a record-low-loss of 0.34 dB and bandwidth exceeding 30 nm at the telecom wavelength of 1550 nm. We further show a pair of grating couplers works as optic via that interconnects two stacked photonic chips with a loss of only 0.94 dB. Our work sheds light on the feasibility of energy-efficient optical interconnect for silicon photonics, and paving the way to large-scale photonic integration for applications from optical communication to photonic computing.

physics.optics↗

arXiv2023

Energy landscape reveals the underlying mechanism of cancer-adipose conversion with gene network models

Cancer is a systemic heterogeneous disease involving complex molecular networks. Tumor formation involves epithelial-mesenchymal transition (EMT), which promotes both metastasis and plasticity of cancer cells. Recent experiments proposed that cancer cells can be transformed into adipocytes with combination drugs. However, the underlying mechanisms for how these drugs work from molecular network perspective remain elusive. To reveal the mechanism of cancer-adipose conversion (CAC), we adopt a systems biology approach by combing mathematical modeling and molecular experiments based on the underlying molecular regulatory network. We identified four types of attractors which correspond to epithelial (E), mesenchymal (M), adipose (A) and partial/intermediate EMT (P) cell states on the CAC landscape. Landscape and transition path results illustrate that the intermediate states play critical roles in cancer to adipose transition. Through a landscape control strategy, we identified two new therapeutic strategies for drug combinations to promote CAC. We further verified these predictions by molecular experiments in different cell lines. Our combined computational and experimental approach provides a powerful tool to explore molecular mechanisms for cell fate transitions in cancer networks. Our results revealed the underlying mechanism for intermediate cell states governing the CAC, and identified new potential drug combinations to induce cancer adipogenesis.

q-bio.MN↗