arXiv subjects

Lu Xin

Publications and source records attributed to Lu Xin.

8 recordsLinked to original sources

arXiv2026

MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation

Multi-subject personalized image generation requires the precise rendering of all requested reference identities and their specified interactions based on a guiding prompt. However, state-of-the-art models still struggle with this process, frequently omitting subjects, failing to preserve reference appearances, or misattributing interactions. Furthermore, existing metrics designed primarily for single-subject fidelity cannot reliably capture these errors, suffering severe degradation in ranking separability and failing to align with human preference as the subject count increases. To address this gap, we introduce Multi-subject Interaction Benchmark and Evaluator (MIBE), a unified framework comprising a Multi-subject Interaction Benchmark (MIB) and a Multi-subject Interaction Evaluator (MIE). MIB systematically covers diverse relation types and scene complexities through a decoupled data regime. This consists of a 60K-pair VLM-labeled Silver Set for scalable metric training and a 4K-pair double-blind Human Evaluation Gold Set covering a diverse range of state-of-the-art generators, with the Silver Set reaching 95.1% cross-VLM preference agreement. To demonstrate the utility of this benchmark, we present MIE, a lightweight, reference-conditioned evaluator trained exclusively on the Silver Set with a dual-head ranking and diagnosis objective. MIE exhibits strong cross-generator generalization on the Gold Set, achieving 0.922 overall pairwise accuracy against human preference, including 0.982 on seen generators and 0.884 on unseen generators. By outperforming a broad spectrum of baseline metrics, including CLIP and DINO variants, MIE demonstrates that diagnostic supervision can preserve ranking separability and human alignment where traditional evaluators collapse.

cs.CV↗

arXiv2025

A Novel Multiple Interval Prediction Method for Electricity Prices based on Scenarios Generation: Definition and Method

This paper presents interval prediction methodology to address limitations in existing evaluation indicators and improve prediction accuracy and reliability. First, new evaluation indicators are proposed to comprehensively assess interval prediction methods, considering both all-sample and single-sample scenarios. Second, a novel Pattern-Diversity Conditional Time-Series Generative Adversarial Network (PDCTSGAN) is introduced to generate realistic scenarios, enabling a new interval prediction approach based on scenario generation. The PDCTSGAN model innovatively incorporates modifications to random noise inputs, allowing the generation of pattern-diverse realistic scenarios. These scenarios are further utilized to construct multiple interval patterns with high coverage probability and low average width. The effectiveness of the proposed methodology is demonstrated through comprehensive case studies. The paper concludes by highlighting future research directions to further enhance interval prediction methods.

eess.SY↗

arXiv2025

Scenarios Generation-based Multiple Interval Prediction Method for Electricity Prices

This paper introduces an innovative interval prediction methodology aimed at addressing the limitations of current evaluation indicators while enhancing prediction accuracy and reliability. To achieve this, new evaluation metrics are proposed, offering a comprehensive assessment of interval prediction methods across both all-sample and single-sample scenarios. Additionally, a novel Pattern-Diversity Conditional Time-Series Generative Adversarial Network (PDCTSGAN) is developed, designed to generate realistic scenarios and support a new interval prediction framework based on scenario generation. The PDCTSGAN model incorporates unique modifications to random noise inputs, enabling the creation of pattern-diverse and realistic scenarios. These scenarios are then utilized to produce multiple interval patterns characterized by high coverage probability and reduced average width. The proposed approach is validated through detailed case studies, and the paper concludes with a discussion of future research directions to further refine interval prediction techniques.

eess.SY↗

arXiv2024

Evidence for multiband gapless superconductivity in the topological superconductor candidate 4Hb-TaS2

We present the ultralow-temperature thermal conductivity measurements on single crystals of transition-metal dichalcogenide material 4Hb-TaS$_{2}$, which has recently been proposed as a topological superconductor candidate. In zero field, a small residual linear term $\kappa_{0}/T$ is observed, indicating the existence of a residual density of states in the superconducting state. The slow field dependence of $\kappa_{0}/T$ at low fields rules out the presence of nodes in the superconducting gap, and the S-shaped field dependence across the full field range suggests multiple superconducting gaps in 4Hb-TaS$_{2}$. Our results provide evidence for multiband gapless superconductivity in 4Hb-TaS$_{2}$, and the residual density of states come from certain gapless Fermi surfaces.

cond-mat.supr-con↗

arXiv2023

Three-way causal attribute partial order structure analysis

As an emerging concept cognitive learning model, partial order formal structure analysis (POFSA) has been widely used in the field of knowledge processing. In this paper, we propose the method named three-way causal attribute partial order structure (3WCAPOS) to evolve the POFSA from set coverage to causal coverage in order to increase the interpretability and classification performance of the model. First, the concept of causal factor (CF) is proposed to evaluate the causal correlation between attributes and decision attributes in the formal decision context. Then, combining CF with attribute partial order structure, the concept of causal attribute partial order structure is defined and makes set coverage evolve into causal coverage. Finally, combined with the idea of three-way decision, 3WCAPOS is formed, which makes the purity of nodes in the structure clearer and the changes between levels more obviously. In addition, the experiments are carried out from the classification ability and the interpretability of the structure through the six datasets. Through these experiments, it is concluded the accuracy of 3WCAPOS is improved by 1% - 9% compared with classification and regression tree, and more interpretable and the processing of knowledge is more reasonable compared with attribute partial order structure.

cs.AI↗

arXiv2016

A Continuous-time Stochastic Block Model for Basketball Networks

For professional basketball, finding valuable and suitable players is the key to building a winning team. To deal with such challenges, basketball managers, scouts and coaches are increasingly turning to analytics. Objective evaluation of players and teams has always been the top goal of basketball analytics. Typical statistical analytics mainly focuses on the box score and has developed various metrics. In spite of the more and more advanced methods, metrics built upon box score statistics provide limited information about how players interact with each other. Two players with similar box scores may deliver distinct team plays. Thus professional basketball scouts have to watch real games to evaluate players. Live scouting is effective, but suffers from inefficiency and subjectivity. In this paper, we go beyond the static box score and model basketball games as dynamic networks. The proposed Continuous-time Stochastic Block Model clusters the players according to their playing style and performance. The model provides cluster-specific estimates of the effectiveness of players at scoring, rebounding, stealing, etc, and also captures player interaction patterns within and between clusters. By clustering similar players together, the model can help basketball scouts to narrow down the search space. Moreover, the model is able to reveal the subtle differences in the offensive strategies of different teams. An application to NBA basketball games illustrates the performance of the model.

stat.AP↗

arXiv2012

On individual neutrality and collective decision making

We derive a simple mathematical "theory" to show that two decision-making entities can work better together only if at least one of them is occasionally willing to stay neutral. This provides a mathematical "justification" for an age-old cliche among marriage counselors.

stat.OT↗

arXiv2011

Stochastic Stepwise Ensembles for Variable Selection

In this article, we advocate the ensemble approach for variable selection. We point out that the stochastic mechanism used to generate the variable-selection ensemble (VSE) must be picked with care. We construct a VSE using a stochastic stepwise algorithm, and compare its performance with numerous state-of-the-art algorithms.

stat.ME↗