arXiv subjects

Wei Li

Publications and source records attributed to Wei Li.

At least 469 records · Page 26Linked to original sources

arXiv2025

CCMusic: An Open and Diverse Database for Chinese Music Information Retrieval Research

Data are crucial in various computer-related fields, including music information retrieval (MIR), an interdisciplinary area bridging computer science and music. This paper introduces CCMusic, an open and diverse database comprising multiple datasets specifically designed for tasks related to Chinese music, highlighting our focus on this culturally rich domain. The database integrates both published and unpublished datasets, with steps taken such as data cleaning, label refinement, and data structure unification to ensure data consistency and create ready-to-use versions. We conduct benchmark evaluations for all datasets using a unified evaluation framework developed specifically for this purpose. This publicly available framework supports both classification and detection tasks, ensuring standardized and reproducible results across all datasets. The database is hosted on HuggingFace and ModelScope, two open and multifunctional data and model hosting platforms, ensuring ease of accessibility and usability.

cs.IR↗

arXiv2025

Multi-Aggregator Time-Warping Heterogeneous Graph Neural Network for Personalized Micro-Video Recommendation

Micro-video recommendation is attracting global attention and becoming a popular daily service for people of all ages. Recently, Graph Neural Networks-based micro-video recommendation has displayed performance improvement for many kinds of recommendation tasks. However, the existing works fail to fully consider the characteristics of micro-videos, such as the high timeliness of news nature micro-video recommendation and sequential interactions of frequently changed interests. In this paper, a novel Multi-aggregator Time-warping Heterogeneous Graph Neural Network (MTHGNN) is proposed for personalized news nature micro-video recommendation based on sequential sessions, where characteristics of micro-videos are comprehensively studied, users' preference is mined via multi-aggregator, the temporal and dynamic changes of users' preference are captured, and timeliness is considered. Through the comparison with the state-of-the-arts, the experimental results validate the superiority of our MTHGNN model.

cs.IR↗

arXiv2025

Relativistic effects in the strong and electromagnetic decays of ${D^*}$ meson

In this paper, we solve the complete Salpeter equation and use the obtained relativistic wave function to calculate the strong and radiative electromagnetic decays of the ${D^*}$ meson. { We obtain the results $Γ(D^{*}(2007)^{0}\to D^{0}π^{0})=34.6~\rm{keV}$ and $Γ(D^{*}(2007)^{0}\rightarrow D^{0}γ)=19.4~\rm{keV}$, and the estimated full width is $Γ(D^{*}(2007)^{0})=54.0~\rm{keV}$.} The focus of this study is on the relativistic corrections. In our method, the wave function of the $D$ meson is not a pure $S$-wave, but includes both a non-relativistic $S$-wave and a relativistic $P$-wave, while the wave function of the $D^*$ meson includes a non-relativistic $S$-wave as well as both relativistic $P$-wave and $D$-wave. Therefore, in this case, the decay ${D^{*}\rightarrow{D}γ}$ is not a non-relativistic $M1$ transition, but rather an $M1+E2+M3+E4$ decay. We find that in a strong decay $D^{*}\rightarrow{D}π$, the non-relativistic contribution is dominant, while in an electromagnetic decay ${D^{*}\rightarrow{D}γ}$, the relativistic correction is dominant.

hep-ph↗

arXiv2025

Boosting Semi-Supervised Medical Image Segmentation via Masked Image Consistency and Discrepancy Learning

Semi-supervised learning is of great significance in medical image segmentation by exploiting unlabeled data. Among its strategies, the co-training framework is prominent. However, previous co-training studies predominantly concentrate on network initialization variances and pseudo-label generation, while overlooking the equilibrium between information interchange and model diversity preservation. In this paper, we propose the Masked Image Consistency and Discrepancy Learning (MICD) framework with three key modules. The Masked Cross Pseudo Consistency (MCPC) module enriches context perception and small sample learning via pseudo-labeling across masked-input branches. The Cross Feature Consistency (CFC) module fortifies information exchange and model robustness by ensuring decoder feature consistency. The Cross Model Discrepancy (CMD) module utilizes EMA teacher networks to oversee outputs and preserve branch diversity. Together, these modules address existing limitations by focusing on fine-grained local information and maintaining diversity in a heterogeneous framework. Experiments on two public medical image datasets, AMOS and Synapse, demonstrate that our approach outperforms state-of-the-art methods.

cs.CV↗

arXiv2025

A Fully Reconfigurable All-Optical Integrated Nonlinear Activator

Photonic neural networks have been considered as the promising candidates for next-generation neuromorphic computation, aiming to break both the power consumption wall and processing speed boundary of state-to-date digital computing architectures. Optics has shown its advantages in parallelism and linear manipulation. However, the lack of low-power and high-speed all-optical nonlinear activation neurons limits its revolution in large-scale photonic neural networks. Here we demonstrate an all-optical nonlinear activator (AONA) based on Fano-enhanced nonlinear optical effects in intra-cavity field, in which our device enables reconfigurability both in shape and type of the nonlinear functions (NFs) relying on the tuning biases on Fano interference and cavity buildup. Experimental results show that our AONA enables nonlinear optical computing with low-power continuous-wave light of 0.1 mW threshold, which can also support the overall processing speed of 13 GHz. The performances of the generated reconfigurable NFs are verified in the classification of handwritten digits and image recognition tasks, yielding the converged cost and enhanced accuracy compared to the linear-only networks. Our proposed device would pave the way for energy-efficient and accelerated all-optical intelligent processors with versatile functionalities and large-scale integration.

physics.optics↗

arXiv2025

V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning

Human processes video reasoning in a sequential spatio-temporal reasoning logic, we first identify the relevant frames ("when") and then analyse the spatial relationships ("where") between key objects, and finally leverage these relationships to draw inferences ("what"). However, can Video Large Language Models (Video-LLMs) also "reason through a sequential spatio-temporal logic" in videos? Existing Video-LLM benchmarks primarily focus on assessing object presence, neglecting relational reasoning. Consequently, it is difficult to measure whether a model truly comprehends object interactions (actions/events) in videos or merely relies on pre-trained "memory" of co-occurrences as biases in generating answers. In this work, we introduce a Video Spatio-Temporal Reasoning (V-STaR) benchmark to address these shortcomings. The key idea is to decompose video understanding into a Reverse Spatio-Temporal Reasoning (RSTR) task that simultaneously evaluates what objects are present, when events occur, and where they are located while capturing the underlying Chain-of-thought (CoT) logic. To support this evaluation, we construct a dataset to elicit the spatial-temporal reasoning process of Video-LLMs. It contains coarse-to-fine CoT questions generated by a semi-automated GPT-4-powered pipeline, embedding explicit reasoning chains to mimic human cognition. Experiments from 14 Video-LLMs on our V-STaR reveal significant gaps between current Video-LLMs and the needs for robust and consistent spatio-temporal reasoning.

cs.CV↗

arXiv2025

Compatible finite element interpolated neural networks

We extend the finite element interpolated neural network (FEINN) framework from partial differential equations (PDEs) with weak solutions in $H^1$ to PDEs with weak solutions in $H(\textbf{curl})$ or $H(\textbf{div})$. To this end, we consider interpolation trial spaces that satisfy the de Rham Hilbert subcomplex, providing stable and structure-preserving neural network discretisations for a wide variety of PDEs. This approach, coined compatible FEINNs, has been used to accurately approximate the $H(\textbf{curl})$ inner product. We numerically observe that the trained network outperforms finite element solutions by several orders of magnitude for smooth analytical solutions. Furthermore, to showcase the versatility of the method, we demonstrate that compatible FEINNs achieve high accuracy in solving surface PDEs such as the Darcy equation on a sphere. Additionally, the framework can integrate adaptive mesh refinements to effectively solve problems with localised features. We use an adaptive training strategy to train the network on a sequence of progressively adapted meshes. Finally, we compare compatible FEINNs with the adjoint neural network method for solving inverse problems. We consider a one-loop algorithm that trains the neural networks for unknowns and missing parameters using a loss function that includes PDE residual and data misfit terms. The algorithm is applied to identify space-varying physical parameters for the $H(\textbf{curl})$ model problem from partial or noisy observations. We find that compatible FEINNs achieve accuracy and robustness comparable to, if not exceeding, the adjoint method in these scenarios.

math.NA↗

arXiv2025

DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting

Recent advances in 3D Gaussian Splatting (3D-GS) have shown remarkable success in representing 3D scenes and generating high-quality, novel views in real-time. However, 3D-GS and its variants assume that input images are captured based on pinhole imaging and are fully in focus. This assumption limits their applicability, as real-world images often feature shallow depth-of-field (DoF). In this paper, we introduce DoF-Gaussian, a controllable depth-of-field method for 3D-GS. We develop a lens-based imaging model based on geometric optics principles to control DoF effects. To ensure accurate scene geometry, we incorporate depth priors adjusted per scene, and we apply defocus-to-focus adaptation to minimize the gap in the circle of confusion. We also introduce a synthetic dataset to assess refocusing capabilities and the model's ability to learn precise lens parameters. Our framework is customizable and supports various interactive applications. Extensive experiments confirm the effectiveness of our method. Our project is available at https://dof-gaussian.github.io.

cs.CV↗

arXiv2025

WildAvatar: Learning In-the-wild 3D Avatars from the Web

Existing research on avatar creation is typically limited to laboratory datasets, which require high costs against scalability and exhibit insufficient representation of the real world. On the other hand, the web abounds with off-the-shelf real-world human videos, but these videos vary in quality and require accurate annotations for avatar creation. To this end, we propose an automatic annotating pipeline with filtering protocols to curate these humans from the web. Our pipeline surpasses state-of-the-art methods on the EMDB benchmark, and the filtering protocols boost verification metrics on web videos. We then curate WildAvatar, a web-scale in-the-wild human avatar creation dataset extracted from YouTube, with $10000+$ different human subjects and scenes. WildAvatar is at least $10\times$ richer than previous datasets for 3D human avatar creation and closer to the real world. To explore its potential, we demonstrate the quality and generalizability of avatar creation methods on WildAvatar. We will publicly release our code, data source links and annotations to push forward 3D human avatar creation and other related fields for real-world applications.

cs.CV↗

arXiv2025

Autoregressive Image Generation with Vision Full-view Prompt

In autoregressive (AR) image generation, models based on the 'next-token prediction' paradigm of LLMs have shown comparable performance to diffusion models by reducing inductive biases. However, directly applying LLMs to complex image generation can struggle with reconstructing the image's structure and details, impacting the generation's accuracy and stability. Additionally, the 'next-token prediction' paradigm in the AR model does not align with the contextual scanning and logical reasoning processes involved in human visual perception, limiting effective image generation. Prompt engineering, as a key technique for guiding LLMs, leverages specifically designed prompts to improve model performance on complex natural language processing (NLP) tasks, enhancing accuracy and stability of generation while maintaining contextual coherence and logical consistency, similar to human reasoning. Inspired by prompt engineering from the field of NLP, we propose Vision Full-view prompt (VF prompt) to enhance autoregressive image generation. Specifically, we design specialized image-related VF prompts for AR image generation to simulate the process of human image creation. This enhances contextual logic ability by allowing the model to first perceive overall distribution information before generating the image, and improve generation stability by increasing the inference steps. Compared to the AR method without VF prompts, our method shows outstanding performance and achieves an approximate improvement of 20%.

cs.CV↗

arXiv2025

Neural network learning of multi-scale and discrete temporal features in directed percolation

Neural network methods are increasingly applied to solve phase transition problems, particularly in identifying critical points in non-equilibrium phase transitions, offering more convenience compared to traditional methods. In this paper, we analyze the (1+1)-dimensional and (2+1)-dimensional directed percolation models using an autoencoder network. We demonstrate that single-step configurations after reaching steady state can replace traditional full configurations for learning purposes. This approach significantly reduces data size and accelerates training time.Furthermore, we introduce a multi-input branch autoencoder network to extract shared features from systems of different sizes. The neural network is capable of learning results from finite-size scaling. By modifying the network input to include configurations at discrete time steps, the network can also capture temporal information, enabling dynamic analysis of non-equilibrium phase boundaries. Our proposed method allows for high-precision identification of critical points using both spatial and temporal features.

cond-mat.stat-mech↗

arXiv2025

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice

We present MagicInfinite, a novel diffusion Transformer (DiT) framework that overcomes traditional portrait animation limitations, delivering high-fidelity results across diverse character types-realistic humans, full-body figures, and stylized anime characters. It supports varied facial poses, including back-facing views, and animates single or multiple characters with input masks for precise speaker designation in multi-character scenes. Our approach tackles key challenges with three innovations: (1) 3D full-attention mechanisms with a sliding window denoising strategy, enabling infinite video generation with temporal coherence and visual quality across diverse character styles; (2) a two-stage curriculum learning scheme, integrating audio for lip sync, text for expressive dynamics, and reference images for identity preservation, enabling flexible multi-modal control over long sequences; and (3) region-specific masks with adaptive loss functions to balance global textual control and local audio guidance, supporting speaker-specific animations. Efficiency is enhanced via our innovative unified step and cfg distillation techniques, achieving a 20x inference speed boost over the basemodel: generating a 10 second 540x540p video in 10 seconds or 720x720p in 30 seconds on 8 H100 GPUs, without quality loss. Evaluations on our new benchmark demonstrate MagicInfinite's superiority in audio-lip synchronization, identity preservation, and motion naturalness across diverse scenarios. It is publicly available at https://www.hedra.com/, with examples at https://magicinfinite.github.io/.

cs.CV↗

arXiv2025

Spatial Distillation based Distribution Alignment (SDDA) for Cross-Headset EEG Classification

A non-invasive brain-computer interface (BCI) enables direct interaction between the user and external devices, typically via electroencephalogram (EEG) signals. However, decoding EEG signals across different headsets remains a significant challenge due to differences in the number and locations of the electrodes. To address this challenge, we propose a spatial distillation based distribution alignment (SDDA) approach for heterogeneous cross-headset transfer in non-invasive BCIs. SDDA uses first spatial distillation to make use of the full set of electrodes, and then input/feature/output space distribution alignments to cope with the significant differences between the source and target domains. To our knowledge, this is the first work to use knowledge distillation in cross-headset transfers. Extensive experiments on six EEG datasets from two BCI paradigms demonstrated that SDDA achieved superior performance in both offline unsupervised domain adaptation and online supervised domain adaptation scenarios, consistently outperforming 10 classical and state-of-the-art transfer learning algorithms.

cs.LG↗

arXiv2025

LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant

First-person video assistants are highly anticipated to enhance our daily lives through online video dialogue. However, existing online video assistants often sacrifice assistant efficacy for real-time efficiency by processing low-frame-rate videos with coarse-grained visual features.To overcome the trade-off between efficacy and efficiency, we propose "Fast & Slow Video-Language Thinker" as an onLIne videO assistaNt, LION-FS, achieving real-time, proactive, temporally accurate, and contextually precise responses. LION-FS adopts a two-stage optimization strategy: 1)Fast Path: Routing-Based Response Determination evaluates frame-by-frame whether an immediate response is necessary. To enhance response determination accuracy and handle higher frame-rate inputs efficiently, we employ Token Aggregation Routing to dynamically fuse spatiotemporal features without increasing token numbers, while utilizing Token Dropping Routing to eliminate redundant features. 2)Slow Path: Multi-granularity Keyframe Augmentation optimizes keyframes during response generation. To provide comprehensive and detailed responses beyond atomic actions constrained by training data, fine-grained spatial features and human-environment interaction features are extracted through multi-granular pooling. These features are further integrated into a meticulously designed multimodal Thinking Template to guide more precise response generation. Comprehensive evaluations on online video tasks demonstrate that LION-FS achieves state-of-the-art efficacy and efficiency.

cs.CV↗

arXiv2025

Feature Point Extraction for Extra-Affine Image

The issue concerning the significant decline in the stability of feature extraction for images subjected to large-angle affine transformations, where the angle exceeds 50 degrees, still awaits a satisfactory solution. Even ASIFT, which is built upon SIFT and entails a considerable number of image comparisons simulated by affine transformations, inevitably exhibits the drawbacks of being time-consuming and imposing high demands on memory usage. And the stability of feature extraction drops rapidly under large-view affine transformations. Consequently, we propose a method that represents an improvement over ASIFT. On the premise of improving the precision and maintaining the affine invariance, it currently ranks as the fastest feature extraction method for extra-affine images that we know of at present. Simultaneously, the stability of feature extraction regarding affine transformation images has been approximated to the maximum limits. Both the angle between the shooting direction and the normal direction of the photographed object (absolute tilt angle), and the shooting transformation angle between two images (transition tilt angle) are close to 90 degrees. The central idea of the method lies in obtaining the optimal parameter set by simulating affine transformation with the reference image. And the simulated affine transformation is reproduced by combining it with the Lanczos interpolation based on the optimal parameter set. Subsequently, it is combined with ORB, which exhibits excellent real-time performance for rapid orientation binary description. Moreover, a scale parameter simulation is introduced to further augment the operational efficiency.

cs.CV↗

arXiv2025

Identifying Ising and percolation phase transitions based on KAN method

Modern machine learning, grounded in the Universal Approximation Theorem, has achieved significant success in the study of phase transitions in both equilibrium and non-equilibrium systems. However, identifying the critical points of percolation models using raw configurations remains a challenging and intriguing problem. This paper proposes the use of the Kolmogorov-Arnold Network, which is based on the Kolmogorov-Arnold Representation Theorem, to input raw configurations into a learning model. The results demonstrate that the KAN can indeed predict the critical points of percolation models. Further observation reveals that, apart from models associated with the density of occupied points, KAN is also capable of effectively achieving phase classification for models where the sole alteration pertains to the orientation of spins, resulting in an order parameter that manifests as an external magnetic flux, such as the Ising model.

cond-mat.stat-mech↗

arXiv2025

Fine-Grained Controllable Apparel Showcase Image Generation via Garment-Centric Outpainting

In this paper, we propose a novel garment-centric outpainting (GCO) framework based on the latent diffusion model (LDM) for fine-grained controllable apparel showcase image generation. The proposed framework aims at customizing a fashion model wearing a given garment via text prompts and facial images. Different from existing methods, our framework takes a garment image segmented from a dressed mannequin or a person as the input, eliminating the need for learning cloth deformation and ensuring faithful preservation of garment details. The proposed framework consists of two stages. In the first stage, we introduce a garment-adaptive pose prediction model that generates diverse poses given the garment. Then, in the next stage, we generate apparel showcase images, conditioned on the garment and the predicted poses, along with specified text prompts and facial images. Notably, a multi-scale appearance customization module (MS-ACM) is designed to allow both overall and fine-grained text-based control over the generated model's appearance. Moreover, we leverage a lightweight feature fusion operation without introducing any extra encoders or modules to integrate multiple conditions, which is more efficient. Extensive experiments validate the superior performance of our framework compared to state-of-the-art methods.

cs.CV↗

arXiv2025

EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection

Rotary Position Embedding (RoPE) enables each attention head to capture multi-frequency information along the sequence dimension and is widely applied in foundation models. However, the nonlinearity introduced by RoPE complicates optimization of the key state in the Key-Value (KV) cache for RoPE-based attention. Existing KV cache compression methods typically store key state before rotation and apply the transformation during decoding, introducing additional computational overhead. This paper introduces EliteKV, a flexible modification framework for RoPE-based models supporting variable KV cache compression ratios. EliteKV first identifies the intrinsic frequency preference of each head using RoPElite, selectively restoring linearity to certain dimensions of key within attention computation. Building on this, joint low-rank compression of key and value enables partial cache sharing. Experimental results show that with minimal uptraining on only $0.6\%$ of the original training data, RoPE-based models achieve a $75\%$ reduction in KV cache size while preserving performance within a negligible margin. Furthermore, EliteKV consistently performs well across models of different scales within the same family.

cs.LG↗