arXiv subjects

Kun Yue

Publications and source records attributed to Kun Yue.

14 recordsLinked to original sources

arXiv2026

Link prediction on multi-relational graphs from an influence propagation perspective

Predicting the existence and type of links (edges) between nodes in a multi-relational graph is key for applications from social interaction prediction to knowledge relationship identification. Enhancing local features with relevant global information is crucial for accurate link prediction, yet it remains challenging. We address this by modeling the relationship between node pairs as node influence. That is, whether the node influence can be propagated and what type of influence is propagated indicates where and what type the edge is, which will be the most relevant local and global information to predict the edges. To this end, we extend the Susceptible-Infectious-Recovered (SIR) epidemic model to capture the influence propagation of nodes on a large scale through sub-graph structures. Subsequently, these sub-graphs are compressed using virtual edges, thereby substantially reducing the computation associated with utilizing the global graph structure. Finally, we propose the Influential Graph Neural Predictor, referred to as IGNP, a link prediction framework guided by influence propagation. Extensive experiments demonstrate the superiority of the proposed method, which outperforms strong baselines by a large margin on the widely used and real-world datasets.

cs.SI↗

arXiv2026

Dissecting Failure Dynamics in Large Language Model Reasoning

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors are not uniformly distributed but often originate from a small number of early transition points, after which reasoning remains locally coherent but globally incorrect. These transitions coincide with localized spikes in token-level entropy, and alternative continuations from the same intermediate state can still lead to correct solutions. Based on these observations, we introduce GUARD, a targeted inference-time framework that probes and redirects critical transitions using uncertainty signals. Empirical evaluations across multiple benchmarks confirm that interventions guided by these failure dynamics lead to more reliable reasoning outcomes. Our findings highlight the importance of understanding when and how reasoning first deviates, complementing existing approaches that focus on scaling inference-time computation.

cs.AI↗

arXiv2026

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice

While Large Language Models (LLMs) excel in various general domains, they exhibit notable gaps in the highly specialized, knowledge-intensive, and legally regulated Chinese tax domain. Consequently, while tax-related benchmarks are gaining attention, many focus on isolated NLP tasks, neglecting real-world practical capabilities. To address this issue, we introduce TaxPraBen, the first dedicated benchmark for Chinese taxation practice. It combines 10 traditional application tasks, along with 3 pioneering real-world scenarios: tax risk prevention, tax inspection analysis, and tax strategy planning, sourced from 14 datasets totaling 7.3K instances. TaxPraBen features a scalable structured evaluation paradigm designed through process of "structured parsing-field alignment extraction-numerical and textual matching", enabling end-to-end tax practice assessment while being extensible to other domains. We evaluate 19 LLMs based on Bloom's taxonomy. The results indicate significant performance disparities: all closed-source large-parameter LLMs excel, and Chinese LLMs like Qwen2.5 generally exceed multilingual LLMs, while the YaYi2 LLM, fine-tuned with some tax data, shows only limited improvement. TaxPraBen serves as a vital resource for advancing evaluations of LLMs in practical applications.

cs.CL↗

arXiv2026

SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly

Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose Synergistic Multi-agent Planning with Heterogeneous langauge model assembly (SYMPHONY), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.

cs.AI↗

arXiv2026

Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support

Large language models (LLMs) have shown strong capabilities across diverse decision-making tasks. However, existing approaches often overlook the specialization differences among available models, treating all LLMs as uniformly applicable regardless of task characteristics. This limits their ability to adapt to varying reasoning demands and task complexities. In this work, we propose Task-Aware LLM Council (TALC), a task-adaptive decision framework that integrates a council of LLMs with Monte Carlo Tree Search (MCTS) to enable dynamic expert selection and efficient multi-step planning. Each LLM is equipped with a structured success memory profile derived from prior task trajectories, enabling semantic matching between current reasoning context and past successes. At each decision point, TALC routes control to the most contextually appropriate model and estimates node value using a dual-signal mechanism that fuses model-based evaluations with historical utility scores. These signals are adaptively weighted based on intra-node variance and used to guide MCTS selection, allowing the system to balance exploration depth with planning confidence. Experiments on WebShop, HumanEval, and the Game of 24 demonstrate that TALC achieves superior task success rates and improved search efficiency compared to strong baselines, validating the benefits of specialization-aware routing and adaptive planning.

cs.AI↗

arXiv2025

Dual-Kernel Graph Community Contrastive Learning

Graph Contrastive Learning (GCL) has emerged as a powerful paradigm for training Graph Neural Networks (GNNs) in the absence of task-specific labels. However, its scalability on large-scale graphs is hindered by the intensive message passing mechanism of GNN and the quadratic computational complexity of contrastive loss over positive and negative node pairs. To address these issues, we propose an efficient GCL framework that transforms the input graph into a compact network of interconnected node sets while preserving structural information across communities. We firstly introduce a kernelized graph community contrastive loss with linear complexity, enabling effective information transfer among node sets to capture hierarchical structural information of the graph. We then incorporate a knowledge distillation technique into the decoupled GNN architecture to accelerate inference while maintaining strong generalization performance. Extensive experiments on sixteen real-world datasets of varying scales demonstrate that our method outperforms state-of-the-art GCL baselines in both effectiveness and scalability.

cs.LG↗

arXiv2024

Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching

Training-free conditional generation based on flow matching aims to leverage pre-trained unconditional flow matching models to perform conditional generation without retraining. Recently, a successful training-free conditional generation approach incorporates conditions via posterior sampling, which relies on the availability of a score function in the unconditional diffusion model. However, flow matching models do not possess an explicit score function, rendering such a strategy inapplicable. Approximate posterior sampling for flow matching has been explored, but it is limited to linear inverse problems. In this paper, we propose Flow Matching-based Posterior Sampling (FMPS) to expand its application scope. We introduce a correction term by steering the velocity field. This correction term can be reformulated to incorporate a surrogate score function, thereby bridging the gap between flow matching models and score-based posterior sampling. Hence, FMPS enables the posterior sampling to be adjusted within the flow matching framework. Further, we propose two practical implementations of the correction mechanism: one aimed at improving generation quality, and the other focused on computational efficiency. Experimental results on diverse conditional generation tasks demonstrate that our method achieves superior generation quality compared to existing state-of-the-art approaches, validating the effectiveness and generality of FMPS.

cs.CV↗

arXiv2024

SituFont: A Just-in-Time Adaptive Intervention System for Enhancing Mobile Readability in Situational Visual Impairments

Situational visual impairments (SVIs) hinder mobile readability, causing discomfort and limiting information access. Building on prior work in adaptive typography and accessibility, this paper presents SituFont, a context-aware and human-in-the-loop adaptive typography adjustment approach that enhances smartphone mobile readability by dynamically adjusting font parameters based on real-time contextual changes. Using smartphone sensors and a human-in-the-loop approach, SituFont personalizes text presentation to accommodate personal factors (e.g., fatigue, distraction) and environmental conditions (e.g., lighting, motion, location). To inform its design, we conducted formative interviews (N=15) to identify key SVI factors and controlled experiments (N=18) to quantify their impact on optimal text parameters. A comparative user study (N=12) across eight simulated SVI scenarios demonstrated SituFont's effectiveness in improving smartphone mobile readability in terms of improved efficiency and reduced workload compared with a non-trivial manual adjustment baseline.

cs.HC↗

arXiv2024

AngleSizer: Enhancing Spatial Scale Perception for the Visually Impaired with an Interactive Smartphone Assistant

Spatial perception, particularly at small and medium scales, is an essential human sense but poses a significant challenge for the blind and visually impaired (BVI). Traditional learning methods for BVI individuals are often constrained by the limited availability of suitable learning environments and high associated costs. To tackle these barriers, we conducted comprehensive studies to delve into the real-world challenges faced by the BVI community. We have identified several key factors hindering their spatial perception, including the high social cost of seeking assistance, inefficient methods of information intake, cognitive and behavioral disconnects, and a lack of opportunities for hands-on exploration. As a result, we developed AngleSizer, an innovative teaching assistant that leverages smartphone technology. AngleSizer is designed to enable BVI individuals to use natural interaction gestures to try, feel, understand, and learn about sizes and angles effectively. This tool incorporates dual vibration-audio feedback, carefully crafted teaching processes, and specialized learning modules to enhance the learning experience. Extensive user experiments validated its efficacy and applicability with diverse abilities and visual conditions. Ultimately, our research not only expands the understanding of BVI behavioral patterns but also greatly improves their spatial perception capabilities, in a way that is both cost-effective and allows for independent learning.

cs.HC↗

arXiv2024

Inference for Heterogeneous Graphical Models using Doubly High-Dimensional Linear-Mixed Models

Motivated by the problem of inferring the graph structure of functional connectivity networks from multi-level functional magnetic resonance imaging data, we develop a valid inference framework for high-dimensional graphical models that accounts for group-level heterogeneity. We introduce a neighborhood-based method to learn the graph structure and reframe the problem as that of inferring fixed effect parameters in a doubly high-dimensional linear mixed model. Specifically, we propose a LASSO-based estimator and a de-biased LASSO-based inference framework for the fixed effect parameters in the doubly high-dimensional linear mixed model, leveraging random matrix theory to deal with challenges induced by the identical fixed and random effect design matrices arising in our setting. Moreover, we introduce consistent estimators for the variance components to identify subject-specific edges in the inferred graph. To illustrate the generality of the proposed approach, we also adapt our method to account for serial correlation by learning heterogeneous graphs in the setting of a vector autoregressive model. We demonstrate the performance of the proposed framework using real data and benchmark simulation studies.

stat.ME↗

arXiv2023

Two Simple Principles for Diffusion-Based Test-Time Adaptation

Recently, diffusion-based test-time adaptations (TTA) have shown great advances, which leverage a diffusion model to map the images in the unknown test domain to the training domain. The unseen and diverse test domains make diffusion-based TTA an ill-posed problem. In this paper, we unravel two simple principles of the design tricks for diffusion-based methods. Intuitively, \textit{Principle 1} says semantic similarity preserving. We should preserve the semantic similarity between the original and generated test images. \textit{Principle 2} suggests minimal modifications. This principle enables the diffusion to map the test images to the training domain with minimal modifications of the test images. In particular, following the two principles, we propose our simple yet effective principle-guided diffusion-based test-time adaptation method (PDDA). Concretely, following Principle 1, we propose a semantic keeper, the method to preserve feature similarity, where the semantic keeper could filter the corruption introduced from the test domain, thus better preserving the semantics. Following Principle 2, we propose a modification keeper, where we introduce a regularization constraint into the generative process to minimize modifications to the test image. Meanwhile, there is a hidden conflict between the two principles. We further introduce the gradient-based view to unify the direction generated from two principles. Extensive experiments on CIFAR-10C, CIFAR-100C, ImageNet-W, and ImageNet-C with WideResNet-28-10, ResNet-50, Swin-T, and ConvNext-T demonstrate that PDDA significantly performs better than the complex state-of-the-art baselines. Specifically, PDDA achieves 2.4\% average accuracy improvements in ImageNet-C without any training process.

cs.LG↗

arXiv2023

A Game-Theoretic Framework for AI Governance

As a transformative general-purpose technology, AI has empowered various industries and will continue to shape our lives through ubiquitous applications. Despite the enormous benefits from wide-spread AI deployment, it is crucial to address associated downside risks and therefore ensure AI advances are safe, fair, responsible, and aligned with human values. To do so, we need to establish effective AI governance. In this work, we show that the strategic interaction between the regulatory agencies and AI firms has an intrinsic structure reminiscent of a Stackelberg game, which motivates us to propose a game-theoretic modeling framework for AI governance. In particular, we formulate such interaction as a Stackelberg game composed of a leader and a follower, which captures the underlying game structure compared to its simultaneous play counterparts. Furthermore, the choice of the leader naturally gives rise to two settings. And we demonstrate that our proposed model can serves as a unified AI governance framework from two aspects: firstly we can map one setting to the AI governance of civil domains and the other to the safety-critical and military domains, secondly, the two settings of governance could be chosen contingent on the capability of the intelligent systems. To the best of our knowledge, this work is the first to use game theory for analyzing and structuring AI governance. We also discuss promising directions and hope this can help stimulate research interest in this interdisciplinary area. On a high, we hope this work would contribute to develop a new paradigm for technology policy: the quantitative and AI-driven methods for the technology policy field, which holds significant promise for overcoming many shortcomings of existing qualitative approaches.

cs.GT↗

arXiv2023

Machine-Learning Recognition of Dzyaloshinskii-Moriya Interaction from Magnetometry

The Dzyaloshinskii-Moriya interaction (DMI), which is the antisymmetric part of the exchange interaction between neighboring local spins, winds the spin manifold and can stabilize non-trivial topological spin textures. Since topology is a robust information carrier, characterization techniques that can extract the DMI magnitude are important for the discovery and optimization of spintronic materials. Existing experimental techniques for quantitative determination of DMI, such as high-resolution magnetic imaging of spin textures and measurement of magnon or transport properties, are time consuming and require specialized instrumentation. Here we show that a convolutional neural network can extract the DMI magnitude from minor hysteresis loops, or magnetic "fingerprints" of a material. These hysteresis loops are readily available by conventional magnetometry measurements. This provides a convenient tool to investigate topological spin textures for next-generation information processing.

cond-mat.mtrl-sci↗

arXiv2022

Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder

Defining and separating cancer subtypes is essential for facilitating personalized therapy modality and prognosis of patients. The definition of subtypes has been constantly recalibrated as a result of our deepened understanding. During this recalibration, researchers often rely on clustering of cancer data to provide an intuitive visual reference that could reveal the intrinsic characteristics of subtypes. The data being clustered are often omics data such as transcriptomics that have strong correlations to the underlying biological mechanism. However, while existing studies have shown promising results, they suffer from issues associated with omics data: sample scarcity and high dimensionality. As such, existing methods often impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations. In this paper, we propose to leverage a recent strong generative model, Vector Quantized Variational AutoEncoder (VQ-VAE), to tackle the data issues and extract informative latent features that are crucial to the quality of subsequent clustering by retaining only information relevant to reconstructing the input. VQ-VAE does not impose strict assumptions and hence its latent features are better representations of the input, capable of yielding superior clustering performance with any mainstream clustering method. Extensive experiments and medical analysis on multiple datasets comprising 10 distinct cancers demonstrate the VQ-VAE clustering results can significantly and robustly improve prognosis over prevalent subtyping systems.

cs.LG↗