Searcharxiv⌕ Search

arXiv subjects

Yu Tian

Publications and source records attributed to Yu Tian.

At least 127 records · Page 7Linked to original sources
arXiv2025

Global Synchronization in Matrix-Weighted Networks

Synchronization phenomena in complex systems are fundamental to understanding collective behavior across disciplines. While classical approaches model such systems by using scalar-weighted networks and simple diffusive couplings, many real-world interactions are inherently multidimensional and transformative. To address this limitation, Matrix-Weighted Networks (MWNs) have been introduced as a versatile framework where edges are associated with matrix weights that encode both interaction strength and directional transformation. In this work, we investigate the emergence and stability of global synchronization (GS) in MWNs by studying coupled Stuart-Landau (SL) oscillators, an archetypal model of nonlinear dynamics near a Hopf bifurcation. Besides the SL, we considered a generalization of regular oscillators to higher dimensions and also the Lorenz model as a prototype of chaotic oscillators. We derive a generalized Master Stability Function (MSF) tailored to MWNs and establish necessary and sufficient conditions for GS to occur. Central to our analysis is the concept of coherence, a structural property of MWNs ensuring path-independent transformations. Our results show that coherence is necessary to have global synchronization and provides a theoretical foundation for analyzing multidimensional dynamical processes in complex networked systems.

cond-mat.stat-mech↗
arXiv2025

Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion

Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain limited by oversmoothing and poor performance on heterophilic graphs. To address these challenges, we introduce a novel framework that equips graphs with a complex-weighted structure, assigning each edge a complex number to drive a diffusion process that extends random walks into the complex domain. We prove that this diffusion is highly expressive: with appropriately chosen complex weights, any node-classification task can be solved in the steady state of a complex random walk. Building on this insight, we propose the Complex-Weighted Convolutional Network (CWCN), which learns suitable complex-weighted structures directly from data while enriching diffusion with learnable matrices and nonlinear activations. CWCN is simple to implement, requires no additional hyperparameters beyond those of standard GNNs, and achieves competitive performance on benchmark datasets. Our results demonstrate that complex-weighted diffusion provides a principled and general mechanism for enhancing GNN expressiveness, opening new avenues for models that are both theoretically grounded and practically effective.

cs.LG↗
arXiv2025

Noise-Resilient Quantum Metrology with Quantum Computing

Quantum computing has made remarkable strides in recent years, as demonstrated by quantum supremacy experiments and the realization of high-fidelity, fault-tolerant gates. However, a major obstacle persists: practical real-world applications remain scarce, largely due to the inefficiency of loading classical data into quantum processors. Here, we propose an alternative strategy that shifts the focus from classical data encoding to directly processing quantum data. We target quantum metrology, a practical quantum technology whose precision is often constrained by realistic noise. We develop an experimentally feasible scheme in which a quantum computer optimizes information acquired from quantum metrology, thereby enhancing performance in noisy quantum metrology tasks and overcoming the classical-data-loading bottleneck. We demonstrate this approach through experimental implementation with nitrogen-vacancy centers in diamond and numerical simulations using models of distributed superconducting quantum processors. Our results show that this method improves the accuracy of sensing estimates and significantly boosts sensitivity, as quantified by the quantum Fisher information, thus offering a new pathway to harness near-term quantum computers for realistic quantum metrology.

quant-ph↗
arXiv2025

CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation

Brain lesion segmentation remains challenging due to small, low-contrast lesions, anisotropic sampling, and cross-slice discontinuities. We propose CenterMamba-SAM, an end-to-end framework that freezes a pretrained backbone and trains only lightweight adapters for efficient fine-tuning. At its core is the CenterMamba encoder, which employs a novel 3x3 corner-axis-center short-sequence scanning strategy to enable center-prioritized, axis-reinforced, and diagonally compensated information aggregation. This design enhances sensitivity to weak boundaries and tiny foci while maintaining sparse yet effective feature representation. A memory-driven structural prompt generator maintains a prototype bank across neighboring slices, enabling automatic synthesis of reliable prompts without user interaction, thereby improving inter-slice coherence. The memory-augmented multi-scale decoder integrates memory attention modules at multiple levels, combining deep supervision with progressive refinement to restore fine details while preserving global consistency. Extensive experiments on public benchmarks demonstrate that CenterMamba-SAM achieves state-of-the-art performance in brain lesion segmentation.

cs.CV↗
arXiv2025

Reconstruction of Black Hole Ringdown Signals with Data Gaps using a Deep-Learning Framework

We introduce DenoiseGapFiller (DGF), a deep-learning framework specifically designed to reconstruct gravitational-wave ringdown signals corrupted by data gaps and instrumental noise. DGF employs a dual-branch encoder-decoder architecture, which is fused via mixing layers and Transformer-style blocks. Trained end-to-end on synthetic ringdown waveforms with gaps up to 20% of the segment length, DGF can achieve a mean waveform mismatch of 0.002. The residual amplitudes of the Time-domain shrink by roughly an order of magnitude and the power spectral density in the 0.01-1 Hz band is suppressed by 1-2 orders of magnitude, restoring the peak of quasi-normal mode(QNM) in the time-frequency representation around 0.01-0.1 Hz. The ability of the model to faithfully reconstruct the original signals, which implies milder penalties in the detection evidence and tighter credible regions for parameter estimation, lay a foundation for the following scientific work.

gr-qc↗
arXiv2025

Numerical computation of electromagnetically sourced nonlinear tails

Amazingly, recent studies indicate that nonlinear effects are of great significance for modelling black hole ringdown. Transient electromagnetic events in the astrophysical environment are typically high energetic, potentially responsible for some nonlinearities in ringdown. Motivated by the desire to understand these nonlinearities, we solve the inhomogeneous Bardeen-Press-Teukolsky equation numerically, and find second-order gravitational tails induced by an electromagnetic source. Our results suggest that the second-order tails of curvature perturbations with multipole numbers $l\geq4$ decay as $t^{-2l-2}$ at fixed spatial position and $u^{-l-3}$ in retarded-time $u$ at null infinity, slower than their linear counterparts, which can play a role in multi-messenger observations.

gr-qc↗
arXiv2025

Dynamical Phase Transition of Dark Solitons in Spherical Holographic Superfluids

In this paper, we employ, for the first time, the holographic gravity approach to investigate the dynamical stability of solitons in spherical superfluids. Transverse perturbations are applied to the background of spherical soliton configurations, and the collective excitation modes of the solitons are examined within the framework of linear analysis. Our study reveals the existence of two distinct unstable modes in the soliton configurations. Through fully nonlinear evolution schemes, the dynamical evolution and final states of the solitons are elucidated. The results demonstrate that the solitons exhibit both self-acceleration instability and snake instability at different temperatures, respectively. And we explore the corresponding temperature-dependent dynamical phase transitions. It is noteworthy that the dynamical behavior of spherical solitons is distinct from the planar case due to the presence of spherical curvature.

hep-th↗
arXiv2025

Fourier Transform Multiple Instance Learning for Whole Slide Image Classification

Whole Slide Image (WSI) classification relies on Multiple Instance Learning (MIL) with spatial patch features, yet existing methods struggle to capture global dependencies due to the immense size of WSIs and the local nature of patch embeddings. This limitation hinders the modeling of coarse structures essential for robust diagnostic prediction. We propose Fourier Transform Multiple Instance Learning (FFT-MIL), a framework that augments MIL with a frequency-domain branch to provide compact global context. Low-frequency crops are extracted from WSIs via the Fast Fourier Transform and processed through a modular FFT-Block composed of convolutional layers and Min-Max normalization to mitigate the high variance of frequency data. The learned global frequency feature is fused with spatial patch features through lightweight integration strategies, enabling compatibility with diverse MIL architectures. FFT-MIL was evaluated across six state-of-the-art MIL methods on three public datasets (BRACS, LUAD, and IMP). Integration of the FFT-Block improved macro F1 scores by an average of 3.51% and AUC by 1.51%, demonstrating consistent gains across architectures and datasets. These results establish frequency-domain learning as an effective and efficient mechanism for capturing global dependencies in WSI classification, complementing spatial features and advancing the scalability and accuracy of MIL-based computational pathology.

cs.CV↗
arXiv2025

Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum

The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both model-specific knowledge distributions and the intrinsic complexity of the tasks, resulting in suboptimal and unstable model performance. To address this, we propose a novel framework inspired by the pedagogical principle of "tailored teaching with balanced difficulty". We reframe prompt selection as a prompt curriculum design problem: constructing a well ordered set of training examples that align with the model's current capabilities. Our approach integrates two complementary signals: (1) model-perceived difficulty, quantified through prediction disagreement in an active learning setup, capturing what the model itself finds challenging; and (2) intrinsic sample complexity, which measures the inherent difficulty of each question-image pair independently of any model. By jointly analyzing these signals, we develop a difficulty-balanced sampling strategy that ensures the selected prompt examples are diverse across both dimensions. Extensive experiments conducted on five challenging benchmarks and multiple popular Multimodal Large Language Models (MLLMs) demonstrate that our method yields substantial and consistent improvements and greatly reduces performance discrepancies caused by random sampling, providing a principled and robust approach for enhancing multimodal reasoning.

cs.CL↗
arXiv2025

Accelerating Diffusion LLM Inference via Local Determinism Propagation

Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede their practical deployment. Conservative sampling strategies typically decode only the most confident token per step to ensure quality (i.e., greedy decoding), at the cost of inference efficiency due to repeated redundant refinement iterations--a phenomenon we term delayed decoding. Through systematic analysis of dLLM decoding dynamics, we characterize this delayed decoding behavior and propose a training-free adaptive parallel decoding strategy, named LocalLeap, to address these inefficiencies. LocalLeap is built on two fundamental empirical principles: local determinism propagation centered on high-confidence anchors and progressive spatial consistency decay. By applying these principles, LocalLeap identifies anchors and performs localized relaxed parallel decoding within bounded neighborhoods, achieving substantial inference step reduction through early commitment of already-determined tokens without compromising output quality. Comprehensive evaluation on various benchmarks demonstrates that LocalLeap achieves 6.94$\times$ throughput improvements and reduces decoding steps to just 14.2\% of the original requirement, achieving these gains with negligible performance impact. The source codes are available at: https://github.com/friedrichor/LocalLeap.

cs.CL↗
arXiv2025

AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment

Image quality assessment (IQA) is inherently complex, as it reflects both the quantification and interpretation of perceptual quality rooted in the human visual system. Conventional approaches typically rely on fixed models to output scalar scores, limiting their adaptability to diverse distortions, user-specific queries, and interpretability needs. Furthermore, scoring and interpretation are often treated as independent processes, despite their interdependence: interpretation identifies perceptual degradations, while scoring abstracts them into a compact metric. To address these limitations, we propose AgenticIQA, a modular agentic framework that integrates vision-language models (VLMs) with traditional IQA tools in a dynamic, query-aware manner. AgenticIQA decomposes IQA into four subtasks -- distortion detection, distortion analysis, tool selection, and tool execution -- coordinated by a planner, executor, and summarizer. The planner formulates task-specific strategies, the executor collects perceptual evidence via tool invocation, and the summarizer integrates this evidence to produce accurate scores with human-aligned explanations. To support training and evaluation, we introduce AgenticIQA-200K, a large-scale instruction dataset tailored for IQA agents, and AgenticIQA-Eval, the first benchmark for assessing the planning, execution, and summarization capabilities of VLM-based IQA agents. Extensive experiments across diverse IQA datasets demonstrate that AgenticIQA consistently surpasses strong baselines in both scoring accuracy and explanatory alignment.

cs.CV↗
arXiv2025

Adapting SAM with Dynamic Similarity Graphs for Few-Shot Parameter-Efficient Small Dense Object Detection: A Case Study of Chickpea Pods in Field Conditions

Parameter-Efficient Fine-Tuning (PEFT) of foundation models for agricultural computer vision tasks remains challenging due to limited training data and complex field conditions. This study introduces a Dynamic Similarity-based Graph Adaptation (DSGA) module to adapt the Segment Anything Model (SAM) under extreme data constraints for precise foreground and instance segmentation of small dense objects in complex agricultural environments. Through dynamic similarity graph construction with a learnable polynomial decay-initialized weight ranking mechanism and adaptive local feature aggregation, DSGA establishes robust spatial and dynamic similarity representation with only 4.00M trainable parameters, which is 4.26% of the original SAM. Integrating this graph-based feature adaptation with Low-Rank Adaptation (LoRA) creates a complementary optimization framework that effectively captures both local and global dependencies in image embeddings while preserving model stability and parameter efficiency. Experimental results on a challenging chickpea pod dataset demonstrated that DSGA with LoRA achieved superior performance across multiple metrics evaluated under 2, 4, 8 and 10 shots, with progressive performance gains as shot count increased. Quantitative metrics showed a 17.31% improvement in Structure-measure and a 62.36% gain in adaptive F-measure compared to the baseline SAM fine-tuning. Comprehensive ablation studies and visualization analyses through Grad-CAM and t-SNE validated the framework's effectiveness in feature discrimination. The proposed adaptation demonstrated practical utility for automated agricultural monitoring applications, achieving accurate pod-counting with an adjusted R-squared of 0.8987 for images with 10 to 120 pods under challenging field conditions.

cs.CV↗
arXiv2025

MEF: A Systematic Evaluation Framework for Text-to-Image Models

Rapid advances in text-to-image (T2I) generation have raised higher requirements for evaluation methodologies. Existing benchmarks center on objective capabilities and dimensions, but lack an application-scenario perspective, limiting external validity. Moreover, current evaluations typically rely on either ELO for overall ranking or MOS for dimension-specific scoring, yet both methods have inherent shortcomings and limited interpretability. Therefore, we introduce the Magic Evaluation Framework (MEF), a systematic and practical approach for evaluating T2I models. First, we propose a structured taxonomy encompassing user scenarios, elements, element compositions, and text expression forms to construct the Magic-Bench-377, which supports label-level assessment and ensures a balanced coverage of both user scenarios and capabilities. On this basis, we combine ELO and dimension-specific MOS to generate model rankings and fine-grained assessments respectively. This joint evaluation method further enables us to quantitatively analyze the contribution of each dimension to user satisfaction using multivariate logistic regression. By applying MEF to current T2I models, we obtain a leaderboard and key characteristics of the leading models. We release our evaluation framework and make Magic-Bench-377 fully open-source to advance research in the evaluation of visual generative models.

cs.AI↗
arXiv2025

MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation

Smartphones have become indispensable in people's daily lives, permeating nearly every aspect of modern society. With the continuous advancement of large language models (LLMs), numerous LLM-based mobile agents have emerged. These agents are capable of accurately parsing diverse user queries and automatically assisting users in completing complex or repetitive operations. However, current agents 1) heavily rely on the comprehension ability of LLMs, which can lead to errors caused by misoperations or omitted steps during tasks, 2) lack interaction with the external environment, often terminating tasks when an app cannot fulfill user queries, and 3) lack memory capabilities, requiring each instruction to reconstruct the interface and being unable to learn from and correct previous mistakes. To alleviate the above issues, we propose MobileRAG, a mobile agents framework enhanced by Retrieval-Augmented Generation (RAG), which includes InterRAG, LocalRAG, and MemRAG. It leverages RAG to more quickly and accurately identify user queries and accomplish complex and long-sequence mobile tasks. Additionally, to more comprehensively assess the performance of MobileRAG, we introduce MobileRAG-Eval, a more challenging benchmark characterized by numerous complex, real-world mobile tasks that require external knowledge assistance. Extensive experimental results on MobileRAG-Eval demonstrate that MobileRAG can easily handle real-world mobile tasks, achieving 10.3\% improvement over state-of-the-art methods with fewer operational steps. Our code is publicly available at: https://github.com/liuxiaojieOutOfWorld/MobileRAG_arxiv

cs.CL↗
arXiv2025

Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum Robots

Deformable continuum robots (DCRs) present unique planning challenges due to nonlinear deformation mechanics and partial state observability, violating the Markov assumptions of conventional reinforcement learning (RL) methods. While Jacobian-based approaches offer theoretical foundations for rigid manipulators, their direct application to DCRs remains limited by time-varying kinematics and underactuated deformation dynamics. This paper proposes Jacobian Exploratory Dual-Phase RL (JEDP-RL), a framework that decomposes planning into phased Jacobian estimation and policy execution. During each training step, we first perform small-scale local exploratory actions to estimate the deformation Jacobian matrix, then augment the state representation with Jacobian features to restore approximate Markovianity. Extensive SOFA surgical dynamic simulations demonstrate JEDP-RL's three key advantages over proximal policy optimization (PPO) baselines: 1) Convergence speed: 3.2x faster policy convergence, 2) Navigation efficiency: requires 25% fewer steps to reach the target, and 3) Generalization ability: achieve 92% success rate under material property variations and achieve 83% (33% higher than PPO) success rate in the unseen tissue environment.

cs.RO↗
arXiv2025

Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data

In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this challenge, we propose a novel approach called Meta-learned Modality-weighted Knowledge Distillation (MetaKD), which enables multi-modal models to maintain high accuracy even when key modalities are missing. MetaKD adaptively estimates the importance weight of each modality through a meta-learning process. These learned importance weights guide a pairwise modality-weighted knowledge distillation process, allowing high-importance modalities to transfer knowledge to lower-importance ones, resulting in robust performance despite missing inputs. Unlike previous methods in the field, which are often task-specific and require significant modifications, our approach is designed to work in multiple tasks (e.g., segmentation and classification) with minimal adaptation. Experimental results on five prevalent datasets, including three Brain Tumor Segmentation datasets (BraTS2018, BraTS2019 and BraTS2020), the Alzheimer's Disease Neuroimaging Initiative (ADNI) classification dataset and the Audiovision-MNIST classification dataset, demonstrate the proposed model is able to outperform the compared models by a large margin. The code is available at https://github.com/billhhh/MetaKD.

cs.CV↗
arXiv2025

From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models

Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to effectively extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (feature decoupling). Motivated by our findings on the preliminary investigation, we propose a novel tuning strategy, PATCH, to mitigate hallucinations in LVLMs. This plug-and-play method can be integrated into various LVLMs, utilizing adaptive virtual tokens to extract object features from bounding boxes, thereby addressing hallucinations caused by insufficient decoupling of visual features. PATCH achieves state-of-the-art performance on multiple multi-modal hallucination datasets. We hope this approach provides researchers with deeper insights into the underlying causes of hallucinations in LVLMs, fostering further advancements and innovation in this field.

cs.CL↗