彭浩｜北京航空航天大学｜学者主页

2026

计算式安全的治理范式、生成图景与长效路径

阙天舒，彭浩

《学习与实践》，No. 4

下载原文 DOI

2026

智能社会的注意力分配：从“标签”机制到“标识”治理体系的进阶

阙天舒，彭浩

《上海行政学院学报》，Vol. 40, No. 2

下载原文

2026

人工智能技术驱动的数质空间及其正义对齐

阙天舒，彭浩

《广州大学学报(社会科学版)》，Vol. 25, No. 1

下载原文

2026

基于流量交互图分析的Web服务威胁检测方法

余北缘，曾广杰，彭浩，刘建伟，李洪亮，谭学士

《网络与信息安全学报》

2026

大模型红队评测中的语义重构与激活引导

王杰聪，彭浩，毛存礼，房玉龙，王书海，陈杰，刘建伟

《人工智能》

2026

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Xiao-Zhen Qiao, Zi-Yue Hua, Zi-Rui Ou, Zi-Hao Yue, Zi-Han Jiang, Zhuo Huang, Zhi-Yang Chen, Zhi-Xian Zheng, Zhi-Peng Xu, Zhengrui Ma, Yuyang Hu, Yu-Hang Dong, Yuechen Zhang, Yudong Wang, Yuan-Xin Liu, Yi-Xin Yang, Yi-Shuo Cai, Yi-Kai Zhao, Yi-Han Yan, Yi-Fan Zhang, Yifan Song, Xi-Yu Wei, Xing Zhang, Xin Zhang, Xiao-Qian Liu, Xiao-Dong Ji, Xiang-Wei Deng, Xue Guo, Wenhan Ma, Wei-Min Xiong, Wei-Kun Wang, Wei-Ji Zhuang, Shuo Liu, Shuhuai Ren, Shu-Hao Gu, Shi-Mao Chen, Shi-Jie Cao, Shi-Liang Yu, Shi-Cheng Li, Sheng-Jie Zhou, Shao-Lei Zhang, Rang Li, Qi-Ying Wang, Qingkai Fang, Qian Chen, Minzheng Wang, Li-Wen Wang, Lin-Li Yao, Ling-Hao Zhang, Li Cheng, Liang Zhao, Lei Li, Jin-Hao Dong, Jin-Yu Xiang, Jian-Yu Wei, Jiang-Shan Duo, Hua-Qiu Liu, Hua Fan, Hong-Yi Guan, Hong-Shen Xu, Hao Tian, Han-Yu Li, Hai-Lin Zhang, Gang Wang, Fu-Li Luo, Feng Wei, Dong Zhang, Dawei Zhu, Chiheng Lou, Chen-Hong He, Cheng-Hao He, Cheng-Hua Liu, Bo-Wen Ye, Bo-Wen Shen, Bo-Shen Xu, Bo Yang, Bing Xia, Bang-Jun Xiao, Bai-Xuan Xu, Zhou-Xiang Mao, Zhi-Yang Zhang, Zhi-Xiang Xu, Zhen-Ru Lin, Zheng-Ju Tang, Zhao-Jun Huang, Yu-Zhe Weng, Yu-Xing Xiang, Yu-Xiao Li, Yu-Heng Yang, Yu-Hang Wang, Yuchen Liu, Yu Tian, Yuan-Liang Dong, Yu Cheng, Yong He, Yong-Shun Liang, Yong Wang, Yi-Yan Wang, Yi-Tian Gong, Yi-Jie Zhang, Yan Xin, Xun Zhang, Xing-Jian Zhao, Wen-Yu Yang, Wen-Shan Huang, Wen-Hao Li, Ting Huang, Tian-Yu Yu, Tian-Yang Lu, Tao Yang, Si-Nan Du, Shu-Tong Tian, Shu-Lin Du, Sheng-Fan Wang, Shan Fang, Qi-Hao Zhang, Qi-Bin Yang, Qian Yu, Qian Tu, Peng Xie, Pei-Pei Wang, Pei-Dian Li, Min Guo, Ming-Chen Shao, Lu Gao, Li-Jie Wang, Liang Shi, Kai-Qi Chen, Kai Liu, Kai-Fei Wang, Kai Yang, Jin-Long Xue, Jie-Chen Zhang, Jia-Xuan Liu, Hong-Xu An, Hao Peng, Han Lu, Guo-Nan Wang, Fei Yang, Fan Cao, Fang-Yu Liu, Fan Cui, Cong Wang, Chun Chen, Chen-Xu Bai, Chen Zhu, Cheng-Hua Wang, Bo-Yi Zeng

2026

Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs

Sagnik Mukherjee, Li-Fan Yuan, Pavan Jayasinha, Dilek Hakkani-Tur, Hao Peng

arXiv.org

精选作品

期刊论文

计算式安全的治理范式、生成图景与长效路径

智能社会的注意力分配：从“标签”机制到“标识”治理体系的进阶

人工智能技术驱动的数质空间及其正义对齐

基于流量交互图分析的Web服务威胁检测方法

大模型红队评测中的语义重构与激活引导

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs

CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs

Dual Curriculum Learning Training Guided Graph Autoencoder for Anomaly Detection

SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis

Mitigating Privacy Risks in Graph Condensation from a Hyperbolic Geometry Perspective

Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger

MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues

Revisiting Graph-Level Anomaly Detection: From Partially to Fully Unsupervised Learning

Effective and Unsupervised Social Event Detection and Evolution via RAG and Structural Entropy

DHMNN: A Hypergraph Motif-Based Framework for Directed Hyperlink Prediction

网络舆情事件检测技术

RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Free Process Rewards without Process Labels

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones

Process Reinforcement through Implicit Rewards

Adaptive and Robust DBSCAN With Multi-Agent Reinforcement Learning

Proactive Bot Detection Based on Structural Information Principles

Hyperbolic Prompt Learning for Incremental Event Detection with LLMs

Dialogues Aspect-based Sentiment Quadruple Extraction via Structural Entropy Minimization Partitioning

T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction

Unsupervised Graph Clustering with Deep Structural Entropy

Global Interpretable Graph-level Anomaly Detection via Prototype

PromptSED: An evolving topic-enhanced prompting framework for incremental social event detection

Hierarchical Text Classification Optimization via Structural Entropy and Singular Smoothing

Community Detection in Large-Scale Complex Networks via Structural Entropy Game

RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry

Structural Entropy Guided Probabilistic Coding

Introduction to the Special Issue on Knowledge Transferring for Recommender Systems

A Scalable Algorithm for Fair Influence Maximization with Unbiased Estimator

Emergence of Cooperation in Multi-Agent Reinforcement Learning via Coalition Labeling and Structural Entropy

Toward Enhancing Cross-Lingual Domain Knowledge Sharing and Transferring for Multilingual Domain Adaptation in NMT

Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation

STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation

基于非回溯矩阵中心性的超图可靠性研究

A Survey of Structural Entropy: Theory, Methods, and Applications

Multivariate Time-Series Anomaly Detection based on Enhancing Graph Attention Networks with Topological Analysis

A Mixed-Curvature Graph Diffusion Model

A Structural Information Guided Hierarchical Reconstruction for Graph Anomaly Detection

Adaptive Differentially Private Structural Entropy Minimization for Unsupervised Social Event Detection

DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism

Table-Filling via Mean Teacher for Cross-domain Aspect Sentiment Triplet Extraction

ReiPool: Reinforced Pooling Graph Neural Networks for Graph-Level Representation Learning

Relational Prompt-Based Pre-Trained Language Models for Social Event Detection

State of the Art and Potentialities of Graph-level Learning

Improving Generalization and Personalization in Model-Heterogeneous Federated Learning

R-ODE: Ricci Curvature Tells When You Will be Informed

Augmenting Low-Resource Cross-Lingual Summarization with Progression-Grounded Training and Prompting

RicciNet: Deep Clustering via A Riemannian Generative Model

Reinforced GNNs for Multiple Instance Learning

Introduction to the Special Issue on Advanced Graph Mining on the Web: Theory, Algorithms, and Applications: Part 2

CoSENT: Consistent Sentence Embedding via Similarity Ranking

Semi-Supervised Clustering via Structural Entropy with Different Constraints

Zero-Shot Text Normalization via Cross-Lingual Knowledge Distillation

WDEA: The Structure and Semantic Fusion With Wasserstein Distance for Low-Resource Language Entity Alignment

基于对抗多关系图神经网络的机器账号检测

图神经网络嵌入维度估计的结构熵极小化方法

JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction

Guest Editorial Introduction to the Special Issue on Anomaly Detection in Emerging Data-Driven Applications: Theory, Algorithms, and Applications

Targeted mining of contiguous sequential patterns

A Comprehensive Survey on Automatic Knowledge Graph Construction

LUAD: A lightweight unsupervised anomaly detection scheme for multivariate time series data

A Perspective Survey on Industrial Knowledge Graphs: Recent Advances, Open Challenges, and Future Directions

Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces

Introduction to the Special Issue on Advanced Graph Mining on the Web: Theory, Algorithms, and Applications: Part 1

Ranking-based Group Identification via Factorized Attention on Social Tripartite Graph

Reinforcement Learning Guided Multi-Objective Exam Paper Generation

信息生态视域下突发公共事件网络舆情运行方式研究

Sequential Recommendation with Auxiliary Item Relationships via Multi-Relational Transformer

Domain-Invariant Feature Progressive Distillation with Adversarial Adaptive Augmentation for Low-Resource Cross-Domain NER