arXiv subjects

Yiyang Zhang

Publications and source records attributed to Yiyang Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

MOSS-TTS Technical Report

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

cs.SD↗

arXiv2026

MOSS-TTSD: Text to Spoken Dialogue Generation

Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance text-to-speech (TTS). Key requirements include accurate turn-taking, cross-turn acoustic consistency, and long-form stability, which current models often fail to address due to a lack of dialogue context modeling. To bridge this gap, we present MOSS-TTSD, a spoken dialogue synthesis model designed for expressive, multi-party conversational speech across multiple languages. With enhanced long-context modeling, MOSS-TTSD generates long-form spoken conversations from dialogue scripts with explicit speaker tags, supporting up to 60 minutes of single-pass synthesis, multi-party dialogue with up to 5 speakers, and zero-shot voice cloning from a short reference audio clip. The model supports various mainstream languages, including English and Chinese, and is adapted to several long-form scenarios. Additionally, to address limitations of existing evaluation methods, we propose TTSD-eval, an objective evaluation framework based on forced alignment that measures speaker attribution accuracy and speaker similarity without relying on speaker diarization tools. Both objective and subjective evaluation results show that MOSS-TTSD surpasses strong open-source and proprietary baselines in dialogue synthesis.

cs.SD↗

arXiv2026

Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks

Although the temporal spike dynamics of spiking neural networks (SNNs) enable low-power temporal pattern capture capabilities, they also incur inherent inconsistencies that severely compromise representation. In this paper, we perform dual consistency optimization via Stable Spike to mitigate this problem, thereby improving the recognition performance of SNNs. With the hardware-friendly ``AND" bit operation, we efficiently decouple the stable spike skeleton from the multi-timestep spike maps, thereby capturing critical semantics while reducing inconsistencies from variable noise spikes. Enforcing the unstable spike maps to converge to the stable spike skeleton significantly improves the inherent consistency across timesteps. Furthermore, we inject amplitude-aware spike noise into the stable spike skeleton to diversify the representations while preserving consistent semantics. The SNN is encouraged to produce perturbation-consistent predictions, thereby contributing to generalization. Extensive experiments across multiple architectures and datasets validate the effectiveness and versatility of our method. In particular, our method significantly advances neuromorphic object recognition under ultra-low latency, improving accuracy by up to 8.33\%. This will help unlock the full power consumption and speed potential of SNNs.

cs.NE↗

arXiv2026

MOVA: Towards Scalable and Synchronized Video-Audio Generation

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and degrade overall quality. While systems such as Veo 3 and Sora 2 emphasize the value of simultaneous generation, joint multimodal modeling introduces unique challenges in architecture, data, and training. Moreover, the closed-source nature of existing systems limits progress in the field. In this work, we introduce MOVA (MOSS Video and Audio), an open-source model capable of generating high-quality, synchronized audio-visual content, including realistic lip-synced speech, environment-aware sound effects, and content-aligned music. MOVA employs a Mixture-of-Experts (MoE) architecture, with a total of 32B parameters, of which 18B are active during inference. It supports IT2VA (Image-Text to Video-Audio) generation task. By releasing the model weights and code, we aim to advance research and foster a vibrant community of creators. The released codebase features comprehensive support for efficient inference, LoRA fine-tuning, and prompt enhancement.

cs.CV↗

arXiv2026

On an approach to canonicalizing elliptic Feynman integrals

We present generic expressions for the integrands of canonical bases under maximal cut in elliptic Feynman integral families with multiple kinematic scales. Such integrals frequently arise in phenomenologically relevant scattering processes. The derivation of our results starts from the Legendre normal form of elliptic curves, where the geometric properties of the curves are simple and explicit, and further kinematic singularities are presented as marked points. The simplicity of the normal form allows a straightforward construction of canonical bases with an arbitrary number of marked points. They can then be mapped into any univariate elliptic integral families via an appropriate Möbius transformation, leading to universal expressions for the integrands. As a demonstration, we discuss the application of our method to several concrete examples, including two new integral families whose canonical bases were not available in the literature. In several examples, we derive canonical bases for the full integral families without any cuts, demonstrating the simplicity of the sub-sector dependence of our canonical bases.

hep-th↗

arXiv2025

From $\mathrm{d} \! \log$ to $\mathrm{d} \mathcal{E}$: Canonical Elliptic Integrands and Modular Symbol Letters with Pure eMPLs

We propose '$\mathrm{d} \mathcal{E}$-forms' as fundamental building blocks of canonical integrands for elliptic Feynman integrals, which lead to Kronecker-Eisenstein $ω$-form symbol letters. Built upon pure elliptic multiple polylogarithms, they provide a natural extension of the '$\mathrm{d} \! \log$-form' integrands and $\mathrm{d} \! \log$ letters for polylogarithmic cases. By introducing an extended basis treating all marked points equally, we manifest a hidden symmetry structure in the canonical connection matrix, and demonstrate its covariance under modular transformations. Our result provides a novel perspective on describing canonical bases and symbol letters in a unified language of pure functions.

hep-th↗

arXiv2025

Spin-flop driven interfacial tunneling magnetoresistance in an antiferromagnetic tunnel junction

The utilization of two-dimensional (2D) materials in magnetic tunnel junctions (MTJs) has shown excellent performance and rich physics. As for 2D antiferromagnets, the magnetic moments in different layers respond asynchronously and can be configured at various states under different magnetic fields, showing the possibility of efficient magnetic and electrical tunability. In this report, A-type antiferromagnetic (AFM) material (Fe0.5Co0.5)5GeTe2 (FCGT) works as electrodes to realize full van der Waals magnetic tunnel junctions. Owing to the interfacial effect, the even-layer FCGT, although with zero net magnetization, exhibits spin selectivity in MTJ architecture contributing to a tunneling magnetoresistance (TMR) reaching about 25% at a low operating current 1 nA at 100 K and persists near room temperature. Due to the surface spin-flop (SSF) effect in antiferromagnetic FCGT, the alternation flexibility between the volatile and nonvolatile memory behavior is achieved. The interfacial TMR can be tuned efficiently in amplitude and even sign under different bias currents and temperatures. These findings show precise magnetoelectric manipulation in MTJs based on 2D antiferromagnets and highlight the promise of 2D antiferromagnets for spintronic devices.

cond-mat.mes-hall↗

arXiv2025

Synergetic Enhancement on Bulk and Grain Boundary Ionic Conduction of Mg Doped High-Entropy NASICON-Type Solid Electrolyte for Solid-State Na+ Batteries by Spray Flame Synthesis

All-solid-state sodium batteries represent a promising next-generation energy storage technology, owing to cost-effectiveness and enhanced safety. Among solid electrolytes for solid-state sodium batteries, NASICON-structured Na3Zr2Si2PO12 has emerged as a predominant candidate. However, its widespread implementation remains limited by suboptimal ionic conductivity in both bulk and grain boundary regions. In this study, we demonstrate a novel approach utilizing swirling spray flame synthesis to produce Mg-doped NASICON solid electrolyte nanoparticles. This method facilitates efficient doping and homogeneous mixing for scalable production, resulting in core-shell non-NASICON structures with nano-scale high-entropy mixing. Notably, the atomic migration distances achieved by flame synthesis are significantly reduced compared to conventional solid-state reactions, thereby enabling reactive sintering to preserve high sinterability of nanoparticles during post-treatment processes. High-temperature sintering yields dense NASICON-structured solid electrolytes. Among those, Mg0.25NZSP exhibits an optimal ionic conductivity of 1.91 mS/cm at room temperature and an activation energy of 0.200 eV. The enhancement mechanism can be attributed to incorporation into the NASICON phase and formation of a secondary phase. The low-melting-point secondary phase significantly improves grain boundary contact to enhance grain boundary conductivity. The process achieves simultaneous enhancement of both bulk and grain boundary conduction through a single-step procedure. Comparative analysis of sintering temperatures and ionic conductivities among NASICON solid electrolytes synthesized via different methods demonstrates flame-synthesized nanoparticles offer superior performance and reduced post-treatment costs, owing to their exceptional nano-scale sinterability and uniform elemental distribution.

cond-mat.mtrl-sci↗

arXiv2025

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and better preserve these cues, yet still rely on text intermediates, creating a fundamental bottleneck. We present MOSS-Speech, a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance. Our approach combines a modality-based layer-splitting architecture with a frozen pre-training strategy, preserving the reasoning and knowledge of pretrained text LLMs while adding native speech capabilities. Experiments show that our model achieves state-of-the-art results in spoken question answering and delivers comparable speech-to-speech performance relative to existing text-guided systems, while still maintaining competitive text performance. By narrowing the gap between text-guided and direct speech generation, our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.

cs.CL↗

arXiv2025

Data-driven Piecewise Affine Decision Rules for Stochastic Programming with Covariate Information

Focusing on stochastic programming (SP) with covariate information, this paper proposes an empirical risk minimization (ERM) method embedded within a nonconvex piecewise affine decision rule (PADR), which aims to learn the direct mapping from features to optimal decisions. We establish the nonasymptotic consistency result of our PADR-based ERM model for unconstrained problems and asymptotic consistency result for constrained ones. To solve the nonconvex and nondifferentiable ERM problem, we develop an enhanced stochastic majorization-minimization algorithm and establish the asymptotic convergence to (composite strong) directional stationarity along with complexity analysis. We show that the proposed PADR-based ERM method applies to a broad class of nonconvex SP problems with theoretical consistency guarantees and computational tractability. Our numerical study demonstrates the superior performance of PADR-based ERM methods compared to state-of-the-art approaches under various settings, with significantly lower costs, less computation time, and robustness to feature dimensions and nonlinearity of the underlying dependency.

math.OC↗

arXiv2025

SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data

Poor sitting posture is a critical yet often overlooked factor contributing to long-term musculoskeletal disorders and physiological dysfunctions. Existing sitting posture monitoring systems, although leveraging visual, IMU, or pressure-based modalities, often suffer from coarse-grained recognition and lack the semantic expressiveness necessary for personalized feedback. In this paper, we propose \textbf{SitLLM}, a lightweight multimodal framework that integrates flexible pressure sensing with large language models (LLMs) to enable fine-grained posture understanding and personalized health-oriented response generation. SitLLM comprises three key components: (1) a \textit{Gaussian-Robust Sensor Embedding Module} that partitions pressure maps into spatial patches and injects local noise perturbations for robust feature extraction; (2) a \textit{Prompt-Driven Cross-Modal Alignment Module} that reprograms sensor embeddings into the LLM's semantic space via multi-head cross-attention using the pre-trained vocabulary embeddings; and (3) a \textit{Multi-Context Prompt Module} that fuses feature-level, structure-level, statistical-level, and semantic-level contextual information to guide instruction comprehension.

cs.CL↗

arXiv2025

Neural Proteomics Fields for Super-resolved Spatial Proteomics Prediction

Spatial proteomics maps protein distributions in tissues, providing transformative insights for life sciences. However, current sequencing-based technologies suffer from low spatial resolution, and substantial inter-tissue variability in protein expression further compromises the performance of existing molecular data prediction methods. In this work, we introduce the novel task of spatial super-resolution for sequencing-based spatial proteomics (seq-SP) and, to the best of our knowledge, propose the first deep learning model for this task--Neural Proteomics Fields (NPF). NPF formulates seq-SP as a protein reconstruction problem in continuous space by training a dedicated network for each tissue. The model comprises a Spatial Modeling Module, which learns tissue-specific protein spatial distributions, and a Morphology Modeling Module, which extracts tissue-specific morphological features. Furthermore, to facilitate rigorous evaluation, we establish an open-source benchmark dataset, Pseudo-Visium SP, for this task. Experimental results demonstrate that NPF achieves state-of-the-art performance with fewer learnable parameters, underscoring its potential for advancing spatial proteomics research. Our code and dataset are publicly available at https://github.com/Bokai-Zhao/NPF.

q-bio.QM↗

arXiv2025

Spray flame synthesis of Y2O3-MgO nanoparticles for mid-infrared transparent nanocomposite ceramics

Spray flame synthesis offers a promising method for scalable production of homogeneously mixed Y2O3-MgO nanopowders as next-generation infrared-transparent window material, which has attracted significant attention owing to its excellent optical properties at high temperatures. However, systematic understanding of how flame synthesis parameters influence particle morphology, crystal phase, solid solubility, and subsequent ceramic performance remains insufficiently understood. In this study, we investigated the influence of precursor chemistry on particle crystal phase and examined the solid solubility of MgO in Y2O3 under different flame temperatures, demonstrating that the high-temperature conditions with O2 as dispersion gas allow up to 50 mol% MgO to fully dissolve into Y2O3, far exceeding the equilibrium solubility limit of 7 mol% at the eutectic temperature (2100°C) and near-zero at room temperature. Furthermore, we systematically evaluated how powder characteristics and sintering parameters-including powder deagglomeration methods, vacuum sintering temperature, hot isostatic pressing (HIP) temperature, and initial powder characteristics-affect ceramic microstructures and infrared transmittance. Despite cracking induced by phase transformation and finer particle sizes, ceramics fabricated from oxygen-synthesized monoclinic-dominated powders exhibited superior near-infrared transmittance (56.2% at 1550 nm), attributed to enhanced atomic mixing and effective grain boundary pinning. After optimization, pure cubic phase powders produced intact and crack-free ceramics with outstanding mid-infrared transparency, achieving a maximum transmittance of 84.6% and an average transmittance of 82.3% in 3-5 um range.

cond-mat.mtrl-sci↗

arXiv2025

Cardiac-CLIP: A Vision-Language Foundation Model for 3D Cardiac CT Images

Foundation models have demonstrated remarkable potential in medical domain. However, their application to complex cardiovascular diagnostics remains underexplored. In this paper, we present Cardiac-CLIP, a multi-modal foundation model designed for 3D cardiac CT images. Cardiac-CLIP is developed through a two-stage pre-training strategy. The first stage employs a 3D masked autoencoder (MAE) to perform self-supervised representation learning from large-scale unlabeled volumetric data, enabling the visual encoder to capture rich anatomical and contextual features. In the second stage, contrastive learning is introduced to align visual and textual representations, facilitating cross-modal understanding. To support the pre-training, we collect 16641 real clinical CT scans, supplemented by 114k publicly available data. Meanwhile, we standardize free-text radiology reports into unified templates and construct the pathology vectors according to diagnostic attributes, based on which the soft-label matrix is generated to supervise the contrastive learning process. On the other hand, to comprehensively evaluate the effectiveness of Cardiac-CLIP, we collect 6,722 real-clinical data from 12 independent institutions, along with the open-source data to construct the evaluation dataset. Specifically, Cardiac-CLIP is comprehensively evaluated across multiple tasks, including cardiovascular abnormality classification, information retrieval and clinical analysis. Experimental results demonstrate that Cardiac-CLIP achieves state-of-the-art performance across various downstream tasks in both internal and external data. Particularly, Cardiac-CLIP exhibits great effectiveness in supporting complex clinical tasks such as the prospective prediction of acute coronary syndrome, which is notoriously difficult in real-world scenarios.

eess.IV↗

arXiv2025

MAMBO-NET: Multi-Causal Aware Modeling Backdoor-Intervention Optimization for Medical Image Segmentation Network

Medical image segmentation methods generally assume that the process from medical image to segmentation is unbiased, and use neural networks to establish conditional probability models to complete the segmentation task. This assumption does not consider confusion factors, which can affect medical images, such as complex anatomical variations and imaging modality limitations. Confusion factors obfuscate the relevance and causality of medical image segmentation, leading to unsatisfactory segmentation results. To address this issue, we propose a multi-causal aware modeling backdoor-intervention optimization (MAMBO-NET) network for medical image segmentation. Drawing insights from causal inference, MAMBO-NET utilizes self-modeling with multi-Gaussian distributions to fit the confusion factors and introduce causal intervention into the segmentation process. Moreover, we design appropriate posterior probability constraints to effectively train the distributions of confusion factors. For the distributions to effectively guide the segmentation and mitigate and eliminate the Impact of confusion factors on the segmentation, we introduce classical backdoor intervention techniques and analyze their feasibility in the segmentation task. To evaluate the effectiveness of our approach, we conducted extensive experiments on five medical image datasets. The results demonstrate that our method significantly reduces the influence of confusion factors, leading to enhanced segmentation accuracy.

eess.IV↗

arXiv2024

GCLS$^2$: Towards Efficient Community Detection Using Graph Contrastive Learning with Structure Semantics

Due to the power of learning representations from unlabeled graphs, graph contrastive learning (GCL) has shown excellent performance in community detection tasks. Existing GCL-based methods on the community detection usually focused on learning attribute representations of individual nodes, which, however, ignores structural semantics of communities (e.g., nodes in the same community should be structurally cohesive). Therefore, in this paper, we will consider the community detection under the community structure semantics and propose an effective framework for graph contrastive learning under structure semantics (GCLS$^2$) to detect communities. To seamlessly integrate interior dense and exterior sparse characteristics of communities with our contrastive learning strategy, we employ classic community structures to extract high-level structural views and design a structure semantic expression module to augment the original structural feature representation. Moreover, we formulate the structure contrastive loss to optimize the feature representation of nodes, which can better capture the topology of communities. To adapt to large-scale networks, we design a high-level graph partitioning (HGP) algorithm that minimizes the community detection loss for GCLS$^2$ online training. It is worth noting that we prove a lower bound on the training of GCLS$^2$ from the perspective of the information theory, explaining why GCLS$^2$ can learn a more accurate representation of the structure. Extensive experiments have been conducted on various real-world graph datasets and confirmed that GCLS$^2$ outperforms nine state-of-the-art methods, in terms of the accuracy, modularity, and efficiency of detecting communities.

cs.SI↗

arXiv2024

CP-UNet: Contour-based Probabilistic Model for Medical Ultrasound Images Segmentation

Deep learning-based segmentation methods are widely utilized for detecting lesions in ultrasound images. Throughout the imaging procedure, the attenuation and scattering of ultrasound waves cause contour blurring and the formation of artifacts, limiting the clarity of the acquired ultrasound images. To overcome this challenge, we propose a contour-based probabilistic segmentation model CP-UNet, which guides the segmentation network to enhance its focus on contour during decoding. We design a novel down-sampling module to enable the contour probability distribution modeling and encoding stages to acquire global-local features. Furthermore, the Gaussian Mixture Model utilizes optimized features to model the contour distribution, capturing the uncertainty of lesion boundaries. Extensive experiments with several state-of-the-art deep learning segmentation methods on three ultrasound image datasets show that our method performs better on breast and thyroid lesions segmentation.

eess.IV↗

arXiv2024

MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer

LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and hollowness of point clouds create some difficulties for voxel-based methods. The sparsity of point clouds makes it challenging to describe the geometric features of objects. The hollowness of point clouds poses difficulties for the aggregation of 3D features. We propose a two-stage 3D object detection framework, called MS23D. (1) We propose a method using voxel feature points from multi-branch to construct the 3D feature layer. Using voxel feature points from different branches, we construct a relatively compact 3D feature layer with rich semantic features. Additionally, we propose a distance-weighted sampling method, reducing the loss of foreground points caused by downsampling and allowing the 3D feature layer to retain more foreground points. (2) In response to the hollowness of point clouds, we predict the offsets between deep-level feature points and the object's centroid, making them as close as possible to the object's centroid. This enables the aggregation of these feature points with abundant semantic features. For feature points from shallow-level, we retain them on the object's surface to describe the geometric features of the object. To validate our approach, we evaluated its effectiveness on both the KITTI and ONCE datasets.

cs.CV↗