arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 559 records · Page 31Linked to original sources

arXiv2025

CoCoDiff: Diversifying Skeleton Action Features via Coarse-Fine Text-Co-Guided Latent Diffusion

In action recognition tasks, feature diversity is essential for enhancing model generalization and performance. Existing methods typically promote feature diversity by expanding the training data in the sample space, which often leads to inefficiencies and semantic inconsistencies. To overcome these problems, we propose a novel Coarse-fine text co-guidance Diffusion model (CoCoDiff). CoCoDiff generates diverse yet semantically consistent features in the latent space by leveraging diffusion and multi-granularity textual guidance. Specifically, our approach feeds spatio-temporal features extracted from skeleton sequences into a latent diffusion model to generate diverse action representations. Meanwhile, we introduce a coarse-fine text co-guided strategy that leverages textual information from large language models (LLMs) to ensure semantic consistency between the generated features and the original inputs. It is noted that CoCoDiff operates as a plug-and-play auxiliary module during training, incurring no additional inference cost. Extensive experiments demonstrate that CoCoDiff achieves SOTA performance on skeleton-based action recognition benchmarks, including NTU RGB+D, NTU RGB+D 120 and Kinetics-Skeleton.

cs.CV↗

arXiv2025

Adaptive Progressive Attention Graph Neural Network for EEG Emotion Recognition

In recent years, numerous neuroscientific studies demonstrate that specific areas of the brain are connected to human emotional responses, with these regions exhibiting variability across individuals and emotional states. To fully leverage these neural patterns, we propose an Adaptive Progressive Attention Graph Neural Network (APAGNN), which dynamically captures the spatial relationships among brain regions during emotional processing. The APAGNN employs three specialized experts that progressively analyze brain topology. The first expert captures global brain patterns, the second focuses on region-specific features, and the third examines emotion-related channels. This hierarchical approach enables increasingly refined analysis of neural activity. Additionally, a weight generator integrates the outputs of all three experts, balancing their contributions to produce the final predictive label. Extensive experiments conducted on SEED, SEED-IV and MPED datasets indicate that our method enhances EEG emotion recognition performance, achieving superior results compared to baseline methods.

eess.SP↗

arXiv2025

TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation

Soccer is a globally popular sporting event, typically characterized by long matches and distinctive highlight moments. Recent advances in Multimodal Large Language Models (MLLMs) offer promising capabilities in temporal grounding and video understanding, soccer commentary generation often requires precise temporal localization and semantically rich descriptions over long-form video. However, existing soccer MLLMs often rely on the temporal a priori for caption generation, so they cannot process the soccer video end-to-end. While some traditional approaches follow a two-step paradigm that is complex and fails to capture the global context to achieve suboptimal performance. To solve the above issues, we present TimeSoccer, the first end-to-end soccer MLLM for Single-anchor Dense Video Captioning (SDVC) in full-match soccer videos. TimeSoccer jointly predicts timestamps and generates captions in a single pass, enabling global context modeling across 45-minute matches. To support long video understanding of soccer matches, we introduce MoFA-Select, a training-free, motion-aware frame compression module that adaptively selects representative frames via a coarse-to-fine strategy, and incorporates complementary training paradigms to strengthen the model's ability to handle long temporal sequences. Extensive experiments demonstrate that our TimeSoccer achieves State-of-The-Art (SoTA) performance on the SDVC task in an end-to-end form, generating high-quality commentary with accurate temporal alignment and strong semantic relevance.

cs.CV↗

arXiv2025

LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation

Online fake news moderation now faces a new challenge brought by the malicious use of large language models (LLMs) in fake news production. Though existing works have shown LLM-generated fake news is hard to detect from an individual aspect, it remains underexplored how its large-scale release will impact the news ecosystem. In this study, we develop a simulation pipeline and a dataset with ~56k generated news of diverse types to investigate the effects of LLM-generated fake news within neural news recommendation systems. Our findings expose a truth decay phenomenon, where real news is gradually losing its advantageous position in news ranking against fake news as LLM-generated news is involved in news recommendation. We further provide an explanation about why truth decay occurs from a familiarity perspective and show the positive correlation between perplexity and news ranking. Finally, we discuss the threats of LLM-generated fake news and provide possible countermeasures. We urge stakeholders to address this emerging challenge to preserve the integrity of news ecosystems.

cs.CL↗

arXiv2025

Gravitational form factor $D$ of charmonium from shear stress

Based on our recent analysis of the hadronic matrix element of the stress-energy tensor in covariant light front dynamics, we extract the charmonium gravitational form factor $D(Q^2)$ from shear stress $T^{12}$. This is in contrast to our recent work using the (light-front) energy density $T^{+-}$. Indeed, by comparing these two currents, we identify terms that are responsible for the violation of the current conservation. Numerical results based on basis light-front quantization show that the violation effects are small and the $D$-term extracted from the two currents are close to each other, hence validating our previous work using $T^{+-}$.

hep-ph↗

arXiv2025

Incompressible and fast rotation limits for 3D compressible rotating Euler system with general initial data

This paper is concerned with the low Mach and Rossby number limits of $3$D compressible rotating Euler equations with ill-prepared initial data in the whole space. More precisely, the initial data is the sum of a $3$D part and a $2$D part. With the help of a suitable intermediate system, we perform this singular limit rigorously with the target system being a $2$D QG-type. This particularly gives an affirmative answer to the question raised by Ngo and Scrobogna [\emph{Discrete Contin. Dyn. Syst.}, 38 (2018), pp. 749-789]. As a by-product, our proof gives a rigorous justification from the $2$D inviscid rotating shallow water equations to the $2$D QG equations in whole space.

math.AP↗

arXiv2025

Bridging Optical Sensing and Wearable Health Monitoring: A Functionalized Plasmonic Nanopillar for Non-Invasive Sweat Glucose Detection

Continuous glucose monitoring (CGM) is vital for diabetes care, but current systems rely on invasive implants or electrochemical sensors that often cause discomfort and skin irritation. Non-invasive alternatives remain limited by low sensitivity and poor compatibility with complex sweat environments, highlighting the urgent need for a comfortable and reliable solution. Here, we report the development of a wearable optical sensor watch that integrates surface plasmon resonance (SPR) technology with a functionalized silver-coated silicon nanowire (Ag/SiNW) substrate for real-time, non-invasive glucose monitoring in sweat. The nanostructured sensor is functionalized with 4-mercaptophenylboronic acid (4-MPBA), enabling selective glucose capture and optical signal transduction through both Raman scattering and SPR shift. The dual-mode detection strategy was systematically optimized, and a miniaturized SPR system operating at 638 nm was successfully integrated into a wearable watch format with wireless data transmission to a mobile application. This wearable device demonstrated excellent sensitivity (LOD down to 0.12 mM) and high selectivity in detecting glucose within physiological sweat concentration ranges. Human subject trials confirmed its applicability in real-life scenarios. This study offers a promising non-invasive alternative to traditional CGM and highlights the potential of integrating nanophotonic sensors with wearable platforms for continuous health monitoring and personalized medicine.

physics.optics↗

arXiv2025

MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks

The emergence of multimodal large language models (MLLMs) has triggered extensive research in model evaluation. While existing evaluation studies primarily focus on unimodal (vision-only) comprehension and reasoning capabilities, they overlook critical assessments of complex multimodal reasoning tasks that require integrated understanding of both visual and textual contexts. Such multimodal tasks present unique challenges, demanding sophisticated reasoning across multiple modalities and deep comprehension of multimodal contexts. In this paper, we present MM-InstructEval, a comprehensive evaluation framework that incorporates diverse metrics to assess model performance across various multimodal reasoning tasks with vision-text contexts. We conduct extensive zero-shot evaluations on 45 models (including 36 MLLMs) across 16 multimodal datasets, encompassing 6 distinct tasks using 10 different instructions. Our framework introduces multiple innovative metrics, including the 'Best Performance' metric to benchmark peak model capabilities, the 'Mean Relative Gain' metric to assess overall efficacy across models and instructions, the 'Stability' metric to measure robustness, and the 'Adaptability' metric to quantify the compatibility between models and instructions. Through comprehensive evaluation and analysis, we uncover several significant insights about model architectures, instruction formats, and their interactions in multimodal reasoning tasks. Our findings establish new benchmarks for assessing the reasoning capabilities of MLLMs and provide strategic guidance for future developments. To facilitate continued research and evaluation in this field, we release our framework and resources at https://github.com/declare-lab/MM-InstructEval, with an interactive leaderboard available at MM-InstructEval Leaderboard (https://declare-lab.github.io/MM-InstructEval/).

cs.MM↗

arXiv2025

Iterative Collaboration Network Guided By Reconstruction Prior for Medical Image Super-Resolution

High-resolution medical images can provide more detailed information for better diagnosis. Conventional medical image super-resolution relies on a single task which first performs the extraction of the features and then upscaling based on the features. The features extracted may not be complete for super-resolution. Recent multi-task learning,including reconstruction and super-resolution, is a good solution to obtain additional relevant information. The interaction between the two tasks is often insufficient, which still leads to incomplete and less relevant deep features. To address above limitations, we propose an iterative collaboration network (ICONet) to improve communications between tasks by progressively incorporating reconstruction prior to the super-resolution learning procedure in an iterative collaboration way. It consists of a reconstruction branch, a super-resolution branch, and a SR-Rec fusion module. The reconstruction branch generates the artifact-free image as prior, which is followed by a super-resolution branch for prior knowledge-guided super-resolution. Unlike the widely-used convolutional neural networks for extracting local features and Transformers with quadratic computational complexity for modeling long-range dependencies, we develop a new residual spatial-channel feature learning (RSCFL) module of two branches to efficiently establish feature relationships in spatial and channel dimensions. Moreover, the designed SR-Rec fusion module fuses the reconstruction prior and super-resolution features with each other in an adaptive manner. Our ICONet is built with multi-stage models to iteratively upscale the low-resolution images using steps of 2x and simultaneously interact between two branches in multi-stage supervisions.

eess.IV↗

arXiv2025

SkyReels-V2: Infinite-length Film Generative Model

Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions. These intertwined limitations hinder realistic long-form synthesis and professional film-style generation. To address these limitations, we propose SkyReels-V2, an Infinite-length Film Generative Model, that synergizes Multi-modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework. Firstly, we design a comprehensive structural representation of video that combines the general descriptions by the Multi-modal LLM and the detailed shot language by sub-expert models. Aided with human annotation, we then train a unified Video Captioner, named SkyCaptioner-V1, to efficiently label the video data. Secondly, we establish progressive-resolution pretraining for the fundamental video generation, followed by a four-stage post-training enhancement: Initial concept-balanced Supervised Fine-Tuning (SFT) improves baseline quality; Motion-specific Reinforcement Learning (RL) training with human-annotated and synthetic distortion data addresses dynamic artifacts; Our diffusion forcing framework with non-decreasing noise schedules enables long-video synthesis in an efficient search space; Final high-quality SFT refines visual fidelity. All the code and models are available at https://github.com/SkyworkAI/SkyReels-V2.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results

This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image superresolution. The project is publicly available at https://github.com/lixinustc/KVQE- ChallengeCVPR-NTIRE2025.

eess.IV↗

arXiv2025

Unveiling Hidden Collaboration within Mixture-of-Experts in Large Language Models

Mixture-of-Experts based large language models (MoE LLMs) have shown significant promise in multitask adaptability by dynamically routing inputs to specialized experts. Despite their success, the collaborative mechanisms among experts are still not well understood, limiting both the interpretability and optimization of these models. In this paper, we focus on two critical issues: (1) identifying expert collaboration patterns, and (2) optimizing MoE LLMs through expert pruning. To address the first issue, we propose a hierarchical sparse dictionary learning (HSDL) method that uncovers the collaboration patterns among experts. For the second issue, we introduce the Contribution-Aware Expert Pruning (CAEP) algorithm, which effectively prunes low-contribution experts. Our extensive experiments demonstrate that expert collaboration patterns are closely linked to specific input types and exhibit semantic significance across various tasks. Moreover, pruning experiments show that our approach improves overall performance by 2.5\% on average, outperforming existing methods. These findings offer valuable insights into enhancing the efficiency and interpretability of MoE LLMs, offering a clearer understanding of expert interactions and improving model optimization.

cs.LG↗

arXiv2025

Understanding spin textures in PT-broken systems through universal symmetry-constrained rules

The current understanding of spin-polarization phenomena in crystals relies heavily on the development of specific k.p Hamiltonians. A more fundamental and symmetry-driven understanding, based solely on crystalline symmetries, remains largely incomplete. In this work, we develop a universal theory consisting of five symmetry-constrained rules to capture the key framework of diverse spin textures (STs) in PT-broken systems. These rules comprehensively classify spatial operations and their combinations with anti-unitary operation T in symmetry-preserved k-invariant subspaces. The theory allows us to address puzzling STs and facilitates the ab initio design of unconventional STs in spin-orbit coupled crystals. Key examples include the identification of vertex-like and windmill-like STs in materials with Dn and Cnv point groups, extending beyond the currently known Radial and Rashba STs. By integrating different types of antiferromagnetic configurations, we also achieve radial STs and the Dresselhaus effect in centrosymmetric systems, challenging the long-standing assumption that these effects exist solely in non-centrosymmetric systems. When combined with topological band theory, we further propose that symmetry-constrained three-dimensional persistent STs can widely exist in two types of non-symmorphic crystals, effectively resolving the ongoing debate regarding their existence.

cond-mat.mtrl-sci↗

arXiv2025

FLSSM: A Federated Learning Storage Security Model with Homomorphic Encryption

Federated learning based on homomorphic encryption has received widespread attention due to its high security and enhanced protection of user data privacy. However, the characteristics of encrypted computation lead to three challenging problems: ``computation-efficiency", ``attack-tracing" and ``contribution-assessment". The first refers to the efficiency of encrypted computation during model aggregation, the second refers to tracing malicious attacks in an encrypted state, and the third refers to the fairness of contribution assessment for local models after encryption. This paper proposes a federated learning storage security model with homomorphic encryption (FLSSM) to protect federated learning model privacy and address the three issues mentioned above. First, we utilize different nodes to aggregate local models in parallel, thereby improving encrypted models' aggregation efficiency. Second, we introduce trusted supervise nodes to examine local models when the global model is attacked, enabling the tracing of malicious attacks under homomorphic encryption. Finally, we fairly reward local training nodes with encrypted local models based on trusted training time. Experiments on multiple real-world datasets show that our model significantly outperforms baseline models in terms of both efficiency and security metrics.

cs.CR↗

arXiv2025

Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip

Objective: The clinical diagnosis of developmental dysplasia of the hip (DDH) typically involves manually measuring key radiological angles -- Center-Edge (CE), Tonnis, and Sharp angles -- from pelvic radiographs, a process that is time-consuming and susceptible to variability. This study aims to develop an automated system that integrates these measurements to enhance the accuracy and consistency of DDH diagnosis. Methods and procedures: We developed an end-to-end deep learning model for keypoint detection that accurately identifies eight anatomical keypoints from pelvic radiographs, enabling the automated calculation of CE, Tonnis, and Sharp angles. To support the diagnostic decision, we introduced a novel data-driven scoring system that combines the information from all three angles into a comprehensive and explainable diagnostic output. Results: The system demonstrated superior consistency in angle measurements compared to a cohort of eight moderately experienced orthopedists. The intraclass correlation coefficients for the CE, Tonnis, and Sharp angles were 0.957 (95% CI: 0.952--0.962), 0.942 (95% CI: 0.937--0.947), and 0.966 (95% CI: 0.964--0.968), respectively. The system achieved a diagnostic F1 score of 0.863 (95% CI: 0.851--0.876), significantly outperforming the orthopedist group (0.777, 95% CI: 0.737--0.817, p = 0.005), as well as using clinical diagnostic criteria for each angle individually (p<0.001). Conclusion: The proposed system provides reliable and consistent automated measurements of radiological angles and an explainable diagnostic output for DDH, outperforming moderately experienced clinicians. Clinical impact: This AI-powered solution reduces the variability and potential errors of manual measurements, offering clinicians a more consistent and interpretable tool for DDH diagnosis.

eess.IV↗

arXiv2025

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capability. Specifically, we adopt a set of interleaved Spatio-Temporal Aware Queries to capture temporal perception and dynamic spatial information. Moreover, we propose a Query-Guided Space Decoder to establish a corresponding connection between the queries and spatial coordinates. Additionally, due to the lack of spatio-temporal datasets, we construct the Unified Spatio-Temporal Grounding (Uni-STG) dataset, comprising 480K instances across three tasks. This dataset fully exploits the potential of MLLM to simultaneously facilitate localization in both temporal and spatial dimensions. Extensive experiments demonstrate that SpaceVLLM achieves the state-of-the-art performance across 11 benchmarks covering temporal, spatial, spatio-temporal and video understanding tasks, highlighting the effectiveness of our approach. Our code, datasets and model will be released at https://github.com/Jayce1kk/SpaceVLLM.

cs.CV↗

arXiv2025

Interconnections of Multimorbidity-Related Clinical Outcomes: Analysis of Health Administrative Claims Data with a Dynamic Network Approach

Given the rising complexity and burden of multimorbidity, it is crucial to provide evidence-based support for managing multimorbidity-related clinical outcomes. This study introduces a dynamic network approach to investigate conditional and time-varying interconnections in disease-specific clinical outcomes. Our method effectively tackles the issue of zero inflation, a frequent challenge in medical data that complicates traditional modeling techniques. The theoretical foundations of the proposed approach are rigorously developed and validated through extensive simulations. Using Taiwan's health administrative claims data from 2000 to 2013, we construct 14 yearly networks that are temporally correlated, featuring 125 nodes that represent different disease conditions. Key network properties, such as connectivity, module, and temporal variation are analyzed. To demonstrate how these networks can inform multimorbidity management, we focus on breast cancer and analyze the relevant network structures. The findings provide valuable clinical insights that enhance the current understanding of multimorbidity. The proposed methods offer promising applications in shaping treatment strategies, optimizing health resource allocation, and informing health policy development in the context of multimorbidity management.

stat.ME↗

arXiv2025

DataLab: A Unified Platform for LLM-Powered Business Intelligence

Business intelligence (BI) transforms large volumes of data within modern organizations into actionable insights for informed decision-making. Recently, large language model (LLM)-based agents have streamlined the BI workflow by automatically performing task planning, reasoning, and actions in executable environments based on natural language (NL) queries. However, existing approaches primarily focus on individual BI tasks such as NL2SQL and NL2VIS. The fragmentation of tasks across different data roles and tools lead to inefficiencies and potential errors due to the iterative and collaborative nature of BI. In this paper, we introduce DataLab, a unified BI platform that integrates a one-stop LLM-based agent framework with an augmented computational notebook interface. DataLab supports various BI tasks for different data roles in data preparation, analysis, and visualization by seamlessly combining LLM assistance with user customization within a single environment. To achieve this unification, we design a domain knowledge incorporation module tailored for enterprise-specific BI tasks, an inter-agent communication mechanism to facilitate information sharing across the BI workflow, and a cell-based context management strategy to enhance context utilization efficiency in BI notebooks. Extensive experiments demonstrate that DataLab achieves state-of-the-art performance on various BI tasks across popular research benchmarks. Moreover, DataLab maintains high effectiveness and efficiency on real-world datasets from Tencent, achieving up to a 58.58% increase in accuracy and a 61.65% reduction in token cost on enterprise-specific BI tasks.

cs.DB↗