陈永强｜清华大学｜学者主页

2026

APeB: Benchmarking Personalization Ability of Large Language Model Agents

Gary Yang, Zi-Zhe Chen, Xinru Chen, Yongqiang Chen, Jian-Xiang Wang, Deyu Zou, Lin-Yi Ding, Jia-Liang Wu, Yunzhong He, Yu-Ning Gong, James Cheng, Huai-Xiao Tou

arXiv.org

DOI

2026

Rich Feature Learning via Diversification

Xin-Yi Leng, Yongqiang Chen, Xiao-Ying Tang, Ya-Tao Bian

2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)

DOI

2026

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents

Deyu Zou, Yongqiang Chen, Fan Feng, Mufei Li, Pan Li, Yunchi Gong, James Cheng

arXiv.org

DOI

2026

Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

Fan Feng, Yujian Zheng, Minghao Fu, Yongqiang Chen, Guang-Yi Chen, Kevin P. Murphy, Bi-Wei Huang, Kun Zhang

arXiv.org

DOI

2026

CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad

Yongqiang Chen, Chenxi Liu, Zhen-Hao Chen, Tongliang Liu, Bo Han, Kun Zhang

arXiv.org

DOI

2026

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

J. Li, Yongqiang Chen, Ning-Ning Ding

Annual Meeting of the Association for Computational Linguistics

DOI

2026

Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis

Yongqiang Chen, Guang-Yi Chen, Yue-Wen Sun, Kun Zhang

arXiv.org

DOI

2026

CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

Zhen-Hao Chen, Yongqiang Chen, Chenxi Liu, Jun-Chi Yu, Xiang-Chen Song, Zi-Jian Li, Jia-Lin Li, P. Torr, Bo Han, Kun Zhang

arXiv.org

DOI

2026

ParamMem: Augmenting Language Agents with Parametric Reflective Memory

Tian-Jun Yao, Yongqiang Chen, Yujian Zheng, Pan Li, Zhiqiang Shen, Kun Zhang

arXiv.org

DOI

2025

数据跨境流动规制综述

葛平原，陈永强，郭伟豪，荣景峰，刘美琦，张玉清

《信息安全研究》

2025

BrainOOD: Out-of-distribution Generalizable Brain Network Analysis

Jiaxing Xu, Yongqiang Chen, Xia Dong, Meng-Cheng Lan, Tian-Cheng Huang, Qingtian Bian, James Cheng, Yi-Ping Ke

International Conference on Learning Representations

DOI

2025

Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

Deyu Zou, Yongqiang Chen, Mufei Li, Siqi Miao, Chenxi Liu, Bo Han, James Cheng, Pan Li

arXiv.org

DOI

2025

On the Thinking-Language Modeling Gap in Large Language Models

Chenxi Liu, Yongqiang Chen, Tong-Liang Liu, James Cheng, Bo Han, Kun Zhang

arXiv.org

DOI

2025

T3: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning

Deyu Zou, Yongqiang Chen, Jian-Xiang Wang, Haochen Yang, Mufei Li, James Cheng, Pan Li, Yu-Ning Gong

arXiv.org

DOI

2025

Retrieval-Augmented Generation with Hierarchical Knowledge

Haoyu Huang, Yong-Feng Huang, Jun-Jie Yang, Zhenyu Pan, Yongqiang Chen, Kaili Ma, Hong-Zhi Chen, James Cheng

Conference on Empirical Methods in Natural Language Processing

DOI

2025

DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization

Jiaqi Wang, Yu-Hang Zhou, Zhixiong Zhang, Qi-Guang Chen, Yongqiang Chen, James Cheng

Trans. Mach. Learn. Res.

DOI

2025

Can Large Language Models Help Experimental Design for Causal Discovery?

J. Li, Yongqiang Chen, Chenxi Liu, Qian-Yi Cai, Tongliang Liu, Bo Han, Kun Zhang, Hui Xiong

arXiv.org

DOI

2025

Learning Graph Invariance by Harnessing Spuriosity

Tian-Jun Yao, Yongqiang Chen, Kai Hu, Tongliang Liu, Kun Zhang, Zhiqiang Shen

International Conference on Learning Representations

2025

Pruning Spurious Subgraphs for Graph Out-of-Distribtuion Generalization

Tian-Jun Yao, Haoxuan Li, Yongqiang Chen, Tongliang Liu, Le Song, E. Xing, Zhiqiang Shen

Neural Information Processing Systems

DOI

2024

基于样本类不确定性抽样的端到端语音关键词检测训练方法

贺前华，陈永强，郑若伟，黄金鑫

《电子学报》

2024

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation

Juzheng Zhang, Ya-Tao Bian, Yongqiang Chen, Quan-Ming Yao

International Joint Conference on Artificial Intelligence

DOI

2024

Enhancing Evolving Domain Generalization through Dynamic Latent Representations

Bing-Hui Xie, Yongqiang Chen, Jiaqi Wang, Kaiwen Zhou, Bo Han, Wei Meng, James Cheng

AAAI Conference on Artificial Intelligence

DOI

2024

Discovery of the Hidden World with Large Language Models

Chenxi Liu, Yongqiang Chen, Tong-Liang Liu, Mingming Gong, James Cheng, Bo Han, Kun Zhang

Neural Information Processing Systems

DOI

2024

How Interpretable Are Interpretable Graph Neural Networks?

Yongqiang Chen, Ya-Tao Bian, Bo Han, James Cheng

International Conference on Machine Learning

DOI

2024

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks

Yajing Wang, Zongwei Luo, Jingzhe Wang, Zhan-Ke Zhou, Yongqiang Chen, Bo Han

AAAI Conference on Artificial Intelligence

DOI

2024

Hierarchical Graph Tokenization for Molecule-Language Alignment

Yongqiang Chen, Quan-Ming Yao, Juzheng Zhang, James Cheng, Ya-Tao Bian

International Conference on Machine Learning

2024

Solving the non-submodular network collapse problems via Decision Transformer

Kaili Ma, Han Yang, Shanchao Yang, Kangfei Zhao, Lan-Qing Li, Yongqiang Chen, Jun-Zhou Huang, James Cheng, Yu Rong

Neural Networks

DOI

2024

A Sober Look at the Robustness of CLIPs to Spurious Features

Qi-Zhou Wang, Yong Lin, Yongqiang Chen, Ludwig Schmidt, Bo Han, Tong Zhang

Neural Information Processing Systems

DOI

2024

HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection

Bing-Hui Xie, Yixuan Wang, Yongqiang Chen, Kaiwen Zhou, Yu Li, Wei Meng, James Cheng

Neural Information Processing Systems

DOI

2024

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations

Bing-Hui Xie, Ya-Tao Bian, Kaiwen Zhou, Yongqiang Chen, Peilin Zhao, Bo Han, Wei Meng, James Cheng

International Conference on Learning Representations

DOI

2024

Empowering Graph Invariance Learning with Deep Spurious Infomax

Tian-Jun Yao, Yongqiang Chen, Zhen-Hao Chen, Kai Hu, Zhiqiang Shen, Kun Zhang

International Conference on Machine Learning

DOI

2023

云数据安全去重技术研究综述

伍高飞，袁紫依，孙思贤，陈永强，孙润东，付安民，朱笑岩，张玉清

《密码学报(中英文)》

2023

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

Yongqiang Chen, Ya-Tao Bian, Kaiwen Zhou, Bing-Hui Xie, Bo Han, James Cheng

Neural Information Processing Systems

DOI

2023

Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes

Yongqiang Chen, Bing-Hui Xie, Kaiwen Zhou, Bo Han, Ya-Tao Bian, James Cheng

arXiv.org

DOI

2023

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

Yongqiang Chen, Wei Huang, Kaiwen Zhou, Yatao Bian, Bo Han, James Cheng

Neural Information Processing Systems

DOI

2023

Towards out-of-distribution generalizable predictions of chemical kinetics properties

Zihao Wang, Yongqiang Chen, Yang Duan, Weijiang Li, Bo Han, James Cheng, Hang-Hang Tong

arXiv.org

DOI

2022

面向社会计算的集成建模方法与应用系统

王奇，王刚桥，陈永强，刘奕

《计算机科学》

2022

Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

Yongqiang Chen, Han Yang, Yonggang Zhang, Kaili Ma, Tong-Liang Liu, Bo Han, James Cheng

International Conference on Learning Representations

2022

Exact Shape Correspondence via 2D graph convolution

Barakeel Fanseu Kamhoua, Lin Zhang, Yongqiang Chen, Han Yang, Kaili Ma, Bo Han, Boyang Li, James Cheng

Neural Information Processing Systems

DOI

2022

Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization

Yongqiang Chen, Kaiwen Zhou, Yatao Bian, Bing-Hui Xie, Bing Wu, Yonggang Zhang, Kaili Ma, Han Yang, Pei-Lin Zhao, Bo Han, James Cheng

International Conference on Learning Representations

2022

Invariance Principle Meets Out-of-Distribution Generalization on Graphs

Yongqiang Chen, Yonggang Zhang, Han Yang, Kaili Ma, Bing-Hui Xie, Tong-Liang Liu, Bo Han, James Cheng

arXiv.org

2022

Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs

Yongqiang Chen, Yonggang Zhang, Yatao Bian, Han Yang, Kaili Ma, Bing-Hui Xie, Tong-Liang Liu, Bo Han, James Cheng

Neural Information Processing Systems

DOI

2021

Calibrating and Improving Graph Contrastive Learning

Kaili Ma, Gary Yang, Han Yang, Yongqiang Chen, James Cheng

Trans. Mach. Learn. Res.

2021

Improving Graph Representation Learning by Contrastive Regularization

Kaili Ma, Haochen Yang, Han Yang, Tatiana Jin, Peng Chen, Yongqiang Chen, Barakeel Fanseu Kamhoua, James Cheng

arXiv.org

2020

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

Han Yang, Xiao Yan, XINYAN DAI, Yongqiang Chen, James Cheng

IEEE International Joint Conference on Neural Network

DOI

2019

面向社区风险防范的大数据平台理论架构设计

贾楠，郭旦怀，陈永强，刘奕

《清华大学学报(自然科学版)》

DOI

R ETHINKING I NVARIANT G RAPH R EPRESENTATION L EARNING WITHOUT E NVIRONMENT P ARTITIONS

Yongqiang Chen, Ya-Tao Bian, Kaiwen Zhou, Bing-Hui Xie, Bo Han, James Cheng

精选作品

期刊论文

APeB: Benchmarking Personalization Ability of Large Language Model Agents

Rich Feature Learning via Diversification

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents

Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis

CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

ParamMem: Augmenting Language Agents with Parametric Reflective Memory

数据跨境流动规制综述

BrainOOD: Out-of-distribution Generalizable Brain Network Analysis

Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

On the Thinking-Language Modeling Gap in Large Language Models

T3: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning

Retrieval-Augmented Generation with Hierarchical Knowledge

DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization

Can Large Language Models Help Experimental Design for Causal Discovery?

Learning Graph Invariance by Harnessing Spuriosity

Pruning Spurious Subgraphs for Graph Out-of-Distribtuion Generalization

基于样本类不确定性抽样的端到端语音关键词检测训练方法

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation

Enhancing Evolving Domain Generalization through Dynamic Latent Representations

Discovery of the Hidden World with Large Language Models

How Interpretable Are Interpretable Graph Neural Networks?

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks

Hierarchical Graph Tokenization for Molecule-Language Alignment

Solving the non-submodular network collapse problems via Decision Transformer

A Sober Look at the Robustness of CLIPs to Spurious Features

HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations

Empowering Graph Invariance Learning with Deep Spurious Infomax

云数据安全去重技术研究综述

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

Towards out-of-distribution generalizable predictions of chemical kinetics properties

面向社会计算的集成建模方法与应用系统

Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

Exact Shape Correspondence via 2D graph convolution

Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization

Invariance Principle Meets Out-of-Distribution Generalization on Graphs

Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs

Calibrating and Improving Graph Contrastive Learning

Improving Graph Representation Learning by Contrastive Regularization

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

面向社区风险防范的大数据平台理论架构设计

R ETHINKING I NVARIANT G RAPH R EPRESENTATION L EARNING WITHOUT E NVIRONMENT P ARTITIONS

预印本

When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

Concept Concentration for Faithful Representation Intervention