Zhezheng Hao

2026

1. TKDE

   LSPC-LA: Local Structure Preserving Clustering with Learnable Anchors

   Haonan Xin, Haoming Chen, Zhezheng Hao, Danyang Wu, Rong Wang, and Feiping Nie

   IEEE TKDE, 2026

   Abs HTML

   We propose LSPC-LA, an anchor-based clustering framework that jointly learns adaptive anchors and preserves the local manifold structure of the data, achieving scalable and accurate clustering on large-scale datasets.

2. TIP

   SimMTC: Simple Multi-view Tensor Clustering

   Haonan Xin, Zhezheng Hao, Zhe Cao, Zihua Zhao, Rong Wang, and Feiping Nie

   IEEE TIP, 2026

   Abs HTML

   We propose SimMTC, a simple yet effective multi-view tensor clustering method that captures higher-order cross-view correlations through a unified tensor representation, delivering strong performance with a clean and efficient formulation.

3. ACL

   Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective

   Zhezheng Hao^*, Hong Wang^*, Haoyang Liu, Jian Luo, Jiarui Yu, Hande Dong, Qiang Lin, Can Wang, and Jiawei Chen

   In ACL main (Oral, Top 5% of the Accepted), 2026

   Abs HTML

   We rethink entropy interventions in reinforcement learning from verbal reasoning, proposing an entropy change perspective for better training stability.

4. ACL

   ReCreate: Reasoning and Creating Domain Agents Driven by Experience

   Zhezheng Hao, Hong Wang, Jian Luo, Jianqing Zhang, Yuyan Zhou, Qiang Lin, Can Wang, Hande Dong, and Jiawei Chen

   In ACL main & ICLR Lifelong Agent Workshop, 2026

   Abs HTML

   We propose ReCreate, a framework for reasoning and creating domain agents driven by experience, enabling autonomous agent construction for complex real-world tasks.

5. ACL

   LEPO: Latent Reasoning Policy Optimization for Large Language Models

   Yuyan Zhou, Jiarui Yu, Hande Dong, Zhezheng Hao, Hong Wang, Jianqing Zhang, and Qiang Lin

   In ACL Findings, 2026

   Abs HTML

   We propose LEPO, a latent reasoning policy optimization method for large language models.

6. ACL

   GAPO: Robust Advantage Estimation for Real-World Code LLMs

   Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, and Jian Cao

   In ACL Findings, 2026

   Abs HTML

   We propose GAPO, a robust advantage estimation method for real-world code LLMs.

7. ACL

   Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay

   Jianqing Zhang, Zhezheng Hao, Wei Xia, Hong Wang, Hande Dong, Qiang Lin, Yang Liu, Jian Cao, and Qiang Yang

   In ACL Findings, 2026

   Abs HTML

   We propose a plug-and-play data module for code reinforcement learning with adaptive ambiguity replay.

8. ICLR

   Scheduling Your LLM Reinforcement Learning with Reasoning Trees

   Hong Wang^*, Zhezheng Hao^*, Jian Luo, Chenxing Wei, Yao Shu, Lei Liu, Qiang Lin, Hande Dong, and Jiawei Chen

   In ICLR, 2026

   Abs HTML

   We propose a reasoning tree-based scheduling method for LLM reinforcement learning.

2025

1. WWW

   Uncertainty-aware Graph Structure Learning

   Shen Han, Zhiyao Zhou, Jiawei Chen, Zhezheng Hao, Sheng Zhou, Gang Wang, Yan Feng, Chun Chen, and Can Wang

   In WWW, 2025

   Abs HTML

   We propose an uncertainty-aware approach to graph structure learning that improves robustness and generalization in graph neural networks.

2. AAAI

   Language Pre-training Guided Masking Representation Learning for Time Series Classification

   Liaoyuan Tang, Zheng Wang, Jie Wang, Guanxiong He, Zhezheng Hao, Rong Wang, and Feiping Nie

   In AAAI, 2025

   Abs HTML

   We propose a language pre-training guided masking approach for time series classification.

3. TKDE

   Acceleration Algorithms in GNNs: A Survey

   Lu Ma, Zeang Sheng, Xunkai Li, Xinyi Gao, Zhezheng Hao, Ling Yang, Wentao Zhang, and Bin Cui

   IEEE TKDE, 2025

   Abs HTML

   A comprehensive survey on acceleration algorithms for graph neural networks.

2024

1. AAAI

   Multi-class Support Vector Machine with Maximizing Minimum Margin

   Zhezheng Hao^*, Feiping Nie^*, and Rong Wang

   In AAAI (Oral, Top 10% of the Accepted), 2024

   Abs HTML

   We propose a novel multi-class SVM formulation that maximizes the minimum margin across all classes, achieving better generalization performance.

2. WWW

   Towards Expansive and Adaptive Hard Negative Mining: Graph Contrastive Learning via Subspace Preserving

   Zhezheng Hao, Haonan Xin, Long Wei, Liaoyuan Tang, Rong Wang, and Feiping Nie

   In WWW (Oral, Top 40% of the Accepted), 2024

   Abs HTML

   We propose a novel graph contrastive learning method via subspace preserving for expansive and adaptive hard negative mining.

3. Inf. Fusion

   Multi-view and Multi-order Graph Clustering via Constrained l1,2-norm

   Haonan Xin, Zhezheng Hao, Zhiwen Sun, Rong Wang, Zhengyu Miao, and Feiping Nie

   Information Fusion, 2024

   Abs HTML

   We propose a multi-view and multi-order graph clustering method via constrained L1,2-norm optimization.

2023

1. TKDE

   Ensemble Clustering with Attentional Representation

   Zhezheng Hao, Zhoumin Lu, Guoxu Li, Feiping Nie, Rong Wang, and Xuelong Li

   IEEE TKDE, 2023

   Abs HTML

   We propose an ensemble clustering method with attentional representation learning, achieving state-of-the-art performance on multiple benchmarks.

2. ICASSP

   Multi-view K-means with Laplacian Embedding

   Zhezheng Hao, Zhoumin Lu, Feiping Nie, Rong Wang, and Xuelong Li

   In ICASSP, 2023

   Abs HTML

   We propose a multi-view K-means algorithm incorporating Laplacian embedding for improved clustering.