Selected work

Representative Papers

Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data

Jul 07, 20252025 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)

This work addresses the limitation of pseudo-label quality in semi-supervised image classification by proposing a contrastive learning framework integrated with a distribution matching mechanism. For the first time in semi-supervised contrastive learning, the method explicitly aligns the feature distributions of labeled and unlabeled data by minimizing the divergence in their statistical characteristics within the embedding space, thereby enhancing the reliability of pseudo-labels and the model’s generalization capability. Extensive experiments on multiple standard image classification benchmarks demonstrate that the proposed approach significantly outperforms existing state-of-the-art methods, confirming the effectiveness and novelty of incorporating feature distribution alignment to improve semi-supervised learning performance.

1 citationsRead paper

Geographically Regularized AUC-Maximizing Personalized Federated Learning

Sep 08, 2026

为解决医疗数据隐私和分布差异问题，提出一种地理正则化的AUC最大化个性化联邦学习方法，以提高诊断模型的区分性能。

0 citationsRead paper

Verification-Guided Specification Synthesis with Large Language Models for Intrusion Detection Rules

Aug 24, 2026

本文提出了一种基于验证引导的规范合成框架，利用大型语言模型从HTTP请求轨迹生成Suricata入侵检测规则，通过CEGIS方法迭代优化，提高了检测率并保持了低误报率。

0 citationsRead paper

Spatio-Temporal Scheduling for Robust and Efficient Multi-Transmitter Wireless Power Transfer

Aug 10, 2026

This work addresses the challenge of achieving both efficiency and robustness in multi-user wireless power transfer under time-varying channels, where conventional single-transmitter time-division scheduling falls short. The authors propose a spatiotemporal joint scheduling approach that leverages coordinated multi-transmitter beamforming to simultaneously optimize temporal and spatial resource allocation. By incorporating a nonlinear rectenna model and strategically exploiting inter-cluster interference as a performance-enhancing factor, the method effectively adapts to dynamic channel conditions. Experimental results demonstrate that the proposed scheme significantly improves both the efficiency and stability of energy delivery, particularly in complex propagation environments characterized by shadow fading and other channel impairments.

0 citationsRead paper

Toward AI Systems That Understand Self and Others: A Multi-Phase Inference Framework for Human Cognitive Diversity and World-Model Alignment

May 28, 2026

This work addresses how cognitive differences among humans lead to heterogeneous reasoning objectives, state representations, and prediction errors from identical observations, thereby causing mutual misunderstanding. The paper proposes a Multi-stage Inference Model (MIM) that reframes the world model alignment problem as one of interoperability among heterogeneous representations rather than enforced convergence. By introducing a phased inference mechanism—integrating phase-generated representational spaces, agent-specific state encodings, and alignment mappings—the framework establishes a theoretical foundation grounded in cognitive typology and formalized philosophical divergence. This approach enables visualization, comparability, and transformability of cognitive differences, offering a novel pathway toward understanding human cognitive diversity, mitigating societal cognitive fragmentation, and advancing human-AI value alignment.

0 citationsRead paper

Recent publications

Latest Papers

Geographically Regularized AUC-Maximizing Personalized Federated Learning

Sep 08, 2026

为解决医疗数据隐私和分布差异问题，提出一种地理正则化的AUC最大化个性化联邦学习方法，以提高诊断模型的区分性能。

0 citationsRead paper

Verification-Guided Specification Synthesis with Large Language Models for Intrusion Detection Rules

Aug 24, 2026

本文提出了一种基于验证引导的规范合成框架，利用大型语言模型从HTTP请求轨迹生成Suricata入侵检测规则，通过CEGIS方法迭代优化，提高了检测率并保持了低误报率。

0 citationsRead paper

Spatio-Temporal Scheduling for Robust and Efficient Multi-Transmitter Wireless Power Transfer

Aug 10, 2026

This work addresses the challenge of achieving both efficiency and robustness in multi-user wireless power transfer under time-varying channels, where conventional single-transmitter time-division scheduling falls short. The authors propose a spatiotemporal joint scheduling approach that leverages coordinated multi-transmitter beamforming to simultaneously optimize temporal and spatial resource allocation. By incorporating a nonlinear rectenna model and strategically exploiting inter-cluster interference as a performance-enhancing factor, the method effectively adapts to dynamic channel conditions. Experimental results demonstrate that the proposed scheme significantly improves both the efficiency and stability of energy delivery, particularly in complex propagation environments characterized by shadow fading and other channel impairments.

0 citationsRead paper

Toward AI Systems That Understand Self and Others: A Multi-Phase Inference Framework for Human Cognitive Diversity and World-Model Alignment

May 28, 2026

This work addresses how cognitive differences among humans lead to heterogeneous reasoning objectives, state representations, and prediction errors from identical observations, thereby causing mutual misunderstanding. The paper proposes a Multi-stage Inference Model (MIM) that reframes the world model alignment problem as one of interoperability among heterogeneous representations rather than enforced convergence. By introducing a phased inference mechanism—integrating phase-generated representational spaces, agent-specific state encodings, and alignment mappings—the framework establishes a theoretical foundation grounded in cognitive typology and formalized philosophical divergence. This approach enables visualization, comparability, and transformability of cognitive differences, offering a novel pathway toward understanding human cognitive diversity, mitigating societal cognitive fragmentation, and advancing human-AI value alignment.

0 citationsRead paper

Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference

May 12, 2026

Why do individuals reach divergent conclusions despite identical observations? This work formalizes cognitive disagreement as a problem of structural non-identifiability in world model learning, distinguishing between two types: θ-level (reasoning profile) and W-level (world model) non-identifiability. It introduces a reasoning profile θ characterized by reference frames, exploration strategies, stability criteria, and temporal horizons to elucidate the mechanisms underlying such divergence. By integrating formal reasoning, hierarchical representation learning, and latent state estimation, the study demonstrates that disagreements arise from the projection of computational, observational, and coordination constraints onto abstract bases. This framework not only accounts for polarization in real-world debates—such as those surrounding AI regulation—but also provides a unified theoretical foundation for understanding cognitive differences between humans and artificial agents.

0 citationsRead paper