arXiv subjects

Ye Zhu

Publications and source records attributed to Ye Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2026

LEMAS: Large A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models

We present the LEMAS-Dataset, which, to our knowledge, is currently the largest open-source multilingual speech corpus with word-level timestamps. Covering over 150,000 hours across 10 major languages, LEMAS-Dataset is constructed via a efficient data processing pipeline that ensures high-quality data and annotations. To validate the effectiveness of LEMAS-Dataset across diverse generative paradigms, we train two benchmark models with distinct architectures and task specializations on this dataset. LEMAS-TTS, built upon a non-autoregressive flow-matching framework, leverages the dataset's massive scale and linguistic diversity to achieve robust zero-shot multilingual synthesis. Our proposed accent-adversarial training and CTC loss mitigate cross-lingual accent issues, enhancing synthesis stability. Complementarily, LEMAS-Edit employs an autoregressive decoder-only architecture that formulates speech editing as a masked token infilling task. By exploiting precise word-level alignments to construct training masks and adopting adaptive decoding strategies, it achieves seamless, smooth-boundary speech editing with natural transitions. Experimental results demonstrate that models trained on LEMAS-Dataset deliver high-quality synthesis and editing performance, confirming the dataset's quality. We envision that this richly timestamp-annotated, fine-grained multilingual corpus will drive future advances in prompt-based speech generation systems.

cs.SD↗

arXiv2025

SCoNE: Spherical Consistent Neighborhoods Ensemble for Effective and Efficient Multi-View Anomaly Detection

The core problem in multi-view anomaly detection is to represent local neighborhoods of normal instances consistently across all views. Recent approaches consider a representation of local neighborhood in each view independently, and then capture the consistent neighbors across all views via a learning process. They suffer from two key issues. First, there is no guarantee that they can capture consistent neighbors well, especially when the same neighbors are in regions of varied densities in different views, resulting in inferior detection accuracy. Second, the learning process has a high computational cost of $\mathcal{O}(N^2)$, rendering them inapplicable for large datasets. To address these issues, we propose a novel method termed \textbf{S}pherical \textbf{C}onsistent \textbf{N}eighborhoods \textbf{E}nsemble (SCoNE). It has two unique features: (a) the consistent neighborhoods are represented with multi-view instances directly, requiring no intermediate representations as used in existing approaches; and (b) the neighborhoods have data-dependent properties, which lead to large neighborhoods in sparse regions and small neighborhoods in dense regions. The data-dependent properties enable local neighborhoods in different views to be represented well as consistent neighborhoods, without learning. This leads to $\mathcal{O}(N)$ time complexity. Empirical evaluations show that SCoNE has superior detection accuracy and runs orders-of-magnitude faster in large datasets than existing approaches.

cs.LG↗

arXiv2025

MelTok: 2D Tokenization for Single-Codebook Audio Compression

Large Audio Language Models (LALMs) have emerged with strong performance across diverse audio understanding tasks and can be further enhanced by neural audio codecs. Transitioning from multi-layer residual vector quantizers to a single-layer quantizer has been shown to facilitate more efficient downstream language models decoding. However, the ability of a single codebook to capture fine-grained acoustic details remains limited, as the frequency-variant nature of 1D tokenizers leads to redundancy. To address this issue, we propose MelTok, a two-dimensional (2D) tokenizer that effectively compresses acoustic details of 44.1 KHz audio into a single codebook. The tokenizer encodes audio into a more compact representation than one-dimensional tokenizers. Furthermore, to recover audio from mel-spectrogram tokens, we propose a token-based vocoder. Both objective and subjective evaluations demonstrate that MelTok achieves quality comparable to multi-codebook codecs and outperforms existing state-of-the-art neural codecs with a single codebook on high-fidelity audio reconstruction. By preserving acoustic details, MelTok offers a strong representation for downstream understanding tasks.

cs.SD↗

arXiv2025

A Sampling-Based Domain Generalization Study with Diffusion Generative Models

In this work, we investigate the domain generalization capabilities of diffusion models in the context of synthesizing images that are distinct from the training data. Instead of fine-tuning, we tackle this challenge from a sampling-based perspective using frozen, pre-trained diffusion models. Specifically, we demonstrate that arbitrary out-of-domain (OOD) images establish Gaussian priors in the latent spaces of a given model after inversion, and that these priors are separable from those of the original training domain. This OOD latent property allows us to synthesize new images of the target unseen domain by discovering qualified OOD latent encodings in the inverted noisy spaces, without altering the pre-trained models. Our cross-model and cross-domain experiments show that the proposed sampling-based method can expand the latent space and generate unseen images without impairing the generation quality of the original domain. We also showcase a practical application of our approach using astrophysical data, highlighting the potential of this generalization paradigm in data-sparse fields such as scientific exploration.

cs.LG↗

arXiv2025

DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion

Domain adaptive point cloud completion (DA PCC) aims to narrow the geometric and semantic discrepancies between the labeled source and unlabeled target domains. Existing methods either suffer from limited receptive fields or quadratic complexity due to using CNNs or vision Transformers. In this paper, we present the first work that studies the adaptability of State Space Models (SSMs) in DA PCC and find that directly applying SSMs to DA PCC will encounter several challenges: directly serializing 3D point clouds into 1D sequences often disrupts the spatial topology and local geometric features of the target domain. Besides, the overlook of designs in the learning domain-agnostic representations hinders the adaptation performance. To address these issues, we propose a novel framework, DAPointMamba for DA PCC, that exhibits strong adaptability across domains and has the advantages of global receptive fields and efficient linear complexity. It has three novel modules. In particular, Cross-Domain Patch-Level Scanning introduces patch-level geometric correspondences, enabling effective local alignment. Cross-Domain Spatial SSM Alignment further strengthens spatial consistency by modulating patch features based on cross-domain similarity, effectively mitigating fine-grained structural discrepancies. Cross-Domain Channel SSM Alignment actively addresses global semantic gaps by interleaving and aligning feature channels. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our DAPointMamba outperforms state-of-the-art methods with less computational complexity and inference latency.

cs.CV↗

arXiv2025

Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions

We study Diffusion Schrödinger Bridge (DSB) models in the context of dynamical astrophysical systems, specifically tackling observational inverse prediction tasks within Giant Molecular Clouds (GMCs) for star formation. We introduce the Astro-DSB model, a variant of DSB with the pairwise domain assumption tailored for astrophysical dynamics. By investigating its learning process and prediction performance in both physically simulated data and in real observations (the Taurus B213 data), we present two main takeaways. First, from the astrophysical perspective, our proposed paired DSB method improves interpretability, learning efficiency, and prediction performance over conventional astrostatistical and other machine learning methods. Second, from the generative modeling perspective, probabilistic generative modeling reveals improvements over discriminative pixel-to-pixel modeling in Out-Of-Distribution (OOD) testing cases of physical simulations with unseen initial conditions and different dominant physical processes. Our study expands research into diffusion models beyond the traditional visual synthesis application and provides evidence of the models' learning abilities beyond pure data statistics, paving a path for future physics-aware generative models which can align dynamics between machine learning and real (astro)physical systems.

astro-ph.IM↗

arXiv2025

D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation

Text-to-image (T2I) diffusion models have achieved strong performance in semantic alignment, yet they still struggle with generating the correct number of objects specified in prompts. Existing approaches typically incorporate auxiliary counting networks as external critics to enhance numeracy. However, since these critics must provide gradient guidance during generation, they are restricted to regression-based models that are inherently differentiable, thus excluding detector-based models with superior counting ability, whose count-via-enumeration nature is non-differentiable. To overcome this limitation, we propose Detector-to-Differentiable (D2D), a novel framework that transforms non-differentiable detection models into differentiable critics, thereby leveraging their superior counting ability to guide numeracy generation. Specifically, we design custom activation functions to convert detector logits into soft binary indicators, which are then used to optimize the noise prior at inference time with pre-trained T2I models. Our extensive experiments on SDXL-Turbo, SD-Turbo, and Pixart-DMD across four benchmarks of varying complexity (low-density, high-density, and multi-object scenarios) demonstrate consistent and substantial improvements in object counting accuracy (e.g., boosting up to 13.7% on D2D-Small, a 400-prompt, low-density benchmark), with minimal degradation in overall image quality and computational overhead.

cs.CV↗

arXiv2025

Noncollapsing for Curvature Flows with Inhomogeneous Speeds

We study closed, embedded hypersurfaces in Euclidean space evolving by fully nonlinear curvature flows, whose speed is given by a symmetric, monotone increasing, $1$-homogeneous, positive underlying speed function $F$ composed with a modulating function $Ψ$. Under the assumption that $F$ is convex or inverse-concave and that $Ψ$ satisfies the corresponding structural conditions, we establish exterior noncollapsing estimates for the flow. The main difficulty stems from the nonlinearity of the evolution equation satisfied in the viscosity sense by the exscribed curvature, whereas in previous works it is a solution to the linearized flow. Moreover, in the case where $F$ is inverse-concave, we refine Andrews and Langford's argument for the interior case.

math.DG↗

arXiv2025

The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation

In this work, we introduce NoiseQuery as a novel method for enhanced noise initialization in versatile goal-driven text-to-image (T2I) generation. Specifically, we propose to leverage an aligned Gaussian noise as implicit guidance to complement explicit user-defined inputs, such as text prompts, for better generation quality and controllability. Unlike existing noise optimization methods designed for specific models, our approach is grounded in a fundamental examination of the generic finite-step noise scheduler design in diffusion formulation, allowing better generalization across different diffusion-based architectures in a tuning-free manner. This model-agnostic nature allows us to construct a reusable noise library compatible with multiple T2I models and enhancement techniques, serving as a foundational layer for more effective generation. Extensive experiments demonstrate that NoiseQuery enables fine-grained control and yields significant performance boosts not only over high-level semantics but also over low-level visual attributes, which are typically difficult to specify through text alone, with seamless integration into current workflows with minimal computational overhead.

cs.CV↗

arXiv2025

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range (0.1s), and supports real-time animation and rendering.

cs.CV↗

arXiv2025

Qffusion: Controllable Portrait Video Editing via Quadrant-Grid Attention Learning

This paper presents Qffusion, a dual-frame-guided framework for portrait video editing. Specifically, we consider a design principle of ``animation for editing'', and train Qffusion as a general animation framework from two still reference images while we can use it for portrait video editing easily by applying modified start and end frames as references during inference. Leveraging the powerful generative power of Stable Diffusion, we propose a Quadrant-grid Arrangement (QGA) scheme for latent re-arrangement, which arranges the latent codes of two reference images and that of four facial conditions into a four-grid fashion, separately. Then, we fuse features of these two modalities and use self-attention for both appearance and temporal learning, where representations at different times are jointly modeled under QGA. Our Qffusion can achieve stable video editing without additional networks or complex training stages, where only the input format of Stable Diffusion is modified. Further, we propose a Quadrant-grid Propagation (QGP) inference strategy, which enjoys a unique advantage on stable arbitrary-length video generation by processing reference and condition frames recursively. Through extensive experiments, Qffusion consistently outperforms state-of-the-art techniques on portrait video editing. Project page: https://qffusion.github.io/page/.

cs.CV↗

arXiv2025

Self-Powered, Ultra-thin, Flexible, and Scalable Ultraviolet Detector Utilizing Diamond-MoS$_2$ Heterojunction

The escalating demand for ultraviolet (UV) sensing in space exploration, environmental monitoring, and agricultural productivity necessitates detectors that are both environmentally and mechanically resilient. Diamond, featuring its high bandgap and UV absorption, exceptional mechanical/chemical robustness, and excellent thermal stability, emerges as a highly promising material for next-generation UV detection in various scenarios. However, conventional diamond-based UV detectors are constrained by rigid bulk architectures and reliance on external power supplies, hindering their integration with curved and flexible platforms and complicating device scalability due to auxiliary power requirements. To tackle these challenges, herein, we firstly demonstrated a large-scale, self-powered, and flexible diamond UV detector by heterogeneously integrating a MoS$_2$ monolayer with an ultrathin, freestanding diamond membrane. The fabricated device operates at zero external bias, and simultaneously exhibits a high responsivity of 94 mA W$^{-1}$ at 220 nm, and detectivity of 5.88 x 109 Jones. Notably, mechanical bending enables strain-induced bandgap modulation of the diamond membrane, allowing dynamically tunable photoresponse-a capability absent in rigid diamond counterparts. To validate its practicality and scalability, a proof-of-concept UV imager with 3x3 pixels was demonstrated. This newly developed configuration will undoubtedly open up new routes toward scalable, integrable, flexible, and cost-effective UV sensing solutions for emerging technologies

physics.ins-det↗

arXiv2025

CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation

Video face swapping aims to address two primary challenges: effectively transferring the source identity to the target video and accurately preserving the dynamic attributes of the target face, such as head poses, facial expressions, lip-sync, \etc. Existing methods mainly focus on achieving high-quality identity transfer but often fall short in maintaining the dynamic attributes of the target face, leading to inconsistent results. We attribute this issue to the inherent coupling of facial appearance and motion in videos. To address this, we propose CanonSwap, a novel video face-swapping framework that decouples motion information from appearance information. Specifically, CanonSwap first eliminates motion-related information, enabling identity modification within a unified canonical space. Subsequently, the swapped feature is reintegrated into the original video space, ensuring the preservation of the target face's dynamic attributes. To further achieve precise identity transfer with minimal artifacts and enhanced realism, we design a Partial Identity Modulation module that adaptively integrates source identity features using a spatial mask to restrict modifications to facial regions. Additionally, we introduce several fine-grained synchronization metrics to comprehensively evaluate the performance of video face swapping methods. Extensive experiments demonstrate that our method significantly outperforms existing approaches in terms of visual quality, temporal consistency, and identity preservation. Our project page are publicly available at https://luoxyhappy.github.io/CanonSwap/.

cs.CV↗

arXiv2025

Multimodal Fake News Detection: MFND Dataset and Shallow-Deep Multitask Learning

Multimodal news contains a wealth of information and is easily affected by deepfake modeling attacks. To combat the latest image and text generation methods, we present a new Multimodal Fake News Detection dataset (MFND) containing 11 manipulated types, designed to detect and localize highly authentic fake news. Furthermore, we propose a Shallow-Deep Multitask Learning (SDML) model for fake news, which fully uses unimodal and mutual modal features to mine the intrinsic semantics of news. Under shallow inference, we propose the momentum distillation-based light punishment contrastive learning for fine-grained uniform spatial image and text semantic alignment, and an adaptive cross-modal fusion module to enhance mutual modal features. Under deep inference, we design a two-branch framework to augment the image and text unimodal features, respectively merging with mutual modalities features, for four predictions via dedicated detection and localization projections. Experiments on both mainstream and our proposed datasets demonstrate the superiority of the model. Codes and dataset are released at https://github.com/yunan-wang33/sdml.

cs.CV↗

arXiv2025

HRAvatar: High-Quality and Relightable Gaussian Head Avatar

Reconstructing animatable and high-quality 3D head avatars from monocular videos, especially with realistic relighting, is a valuable task. However, the limited information from single-view input, combined with the complex head poses and facial movements, makes this challenging. Previous methods achieve real-time performance by combining 3D Gaussian Splatting with a parametric head model, but the resulting head quality suffers from inaccurate face tracking and limited expressiveness of the deformation model. These methods also fail to produce realistic effects under novel lighting conditions. To address these issues, we propose HRAvatar, a 3DGS-based method that reconstructs high-fidelity, relightable 3D head avatars. HRAvatar reduces tracking errors through end-to-end optimization and better captures individual facial deformations using learnable blendshapes and learnable linear blend skinning. Additionally, it decomposes head appearance into several physical properties and incorporates physically-based shading to account for environmental lighting. Extensive experiments demonstrate that HRAvatar not only reconstructs superior-quality heads but also achieves realistic visual effects under varying lighting conditions.

cs.CV↗

arXiv2025

D$^3$: Scaling Up Deepfake Detection by Learning from Discrepancy

The boom of Generative AI brings opportunities entangled with risks and concerns. Existing literature emphasizes the generalization capability of deepfake detection on unseen generators, significantly promoting the detector's ability to identify more universal artifacts. This work seeks a step toward a universal deepfake detection system with better generalization and robustness. We do so by first scaling up the existing detection task setup from the one-generator to multiple-generators in training, during which we disclose two challenges presented in prior methodological designs and demonstrate the divergence of detectors' performance. Specifically, we reveal that the current methods tailored for training on one specific generator either struggle to learn comprehensive artifacts from multiple generators or sacrifice their fitting ability for seen generators (i.e., In-Domain (ID) performance) to exchange the generalization for unseen generators (i.e., Out-Of-Domain (OOD) performance). To tackle the above challenges, we propose our Discrepancy Deepfake Detector (D$^3$) framework, whose core idea is to deconstruct the universal artifacts from multiple generators by introducing a parallel network branch that takes a distorted image feature as an extra discrepancy signal and supplement its original counterpart. Extensive scaled-up experiments demonstrate the effectiveness of D$^3$, achieving 5.3% accuracy improvement in the OOD testing compared to the current SOTA methods while maintaining the ID performance. The source code will be updated in our GitHub repository: https://github.com/BigAandSmallq/D3

cs.CV↗

arXiv2025

A Reinforcement Learning-Driven Transformer GAN for Molecular Generation

Generating molecules with desired chemical properties presents a critical challenge in fields such as chemical synthesis and drug discovery. Recent advancements in artificial intelligence (AI) and deep learning have significantly contributed to data-driven molecular generation. However, challenges persist due to the inherent sensitivity of simplified molecular input line entry system (SMILES) representations and the difficulties in applying generative adversarial networks (GANs) to discrete data. This study introduces RL-MolGAN, a novel Transformer-based discrete GAN framework designed to address these challenges. Unlike traditional Transformer architectures, RL-MolGAN utilizes a first-decoder-then-encoder structure, facilitating the generation of drug-like molecules from both $de~novo$ and scaffold-based designs. In addition, RL-MolGAN integrates reinforcement learning (RL) and Monte Carlo tree search (MCTS) techniques to enhance the stability of GAN training and optimize the chemical properties of the generated molecules. To further improve the model's performance, RL-MolWGAN, an extension of RL-MolGAN, incorporates Wasserstein distance and mini-batch discrimination, which together enhance the stability of the GAN. Experimental results on two widely used molecular datasets, QM9 and ZINC, validate the effectiveness of our models in generating high-quality molecular structures with diverse and desirable chemical properties.

cs.LG↗

arXiv2025

TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction

3D facial reconstruction from a single in-the-wild image is a crucial task in human-centered computer vision tasks. While existing methods can recover accurate facial shapes, there remains significant space for improvement in fine-grained expression capture. Current approaches struggle with irregular mouth shapes, exaggerated expressions, and asymmetrical facial movements. We present TEASER (Token EnhAnced Spatial modeling for Expressions Reconstruction), which addresses these challenges and enhances 3D facial geometry performance. TEASER tackles two main limitations of existing methods: insufficient photometric loss for self-reconstruction and inaccurate localization of subtle expressions. We introduce a multi-scale tokenizer to extract facial appearance information. Combined with a neural renderer, these tokens provide precise geometric guidance for expression reconstruction. Furthermore, TEASER incorporates a pose-dependent landmark loss to further improve geometric performances. Our approach not only significantly enhances expression reconstruction quality but also offers interpretable tokens suitable for various downstream applications, such as photorealistic facial video driving, expression transfer, and identity swapping. Quantitative and qualitative experimental results across multiple datasets demonstrate that TEASER achieves state-of-the-art performance in precise expression reconstruction.

cs.CV↗