张俊格 男 研究员 博导 中国科学院自动化研究所
电子邮件： jgzhang@nlpr.ia.ac.cn
通信地址： 北京市海淀区中关村东路95号
邮政编码：100190
中国科学院特聘核心岗位研究员
中国科学院青年促进会优秀会员
中国科学院稳定支持基础研究青年团队
北京市科技新星
研究领域
博弈智能, 强化学习，多智能体系统，决策大模型(LLM-as-agent and beyond)，通用人工智能
招生信息
希望学生具有优秀的编程（C/C++, Python）、数学、英语基础（如CET-6不低于550分）。
现在还有一名依托国科大前沿交叉科学学院培养的直博生保送招生指标，
欢迎有优秀编程基础的应用数学、统计物理、统计力学等相关专业学生报考。
课题组对博士研究生的培养定位为AI基础理论及应用基础研究，算力资源(近400张卡)非常充沛，因此希望学生对AGI有着极强的使命感和热情，做重要的问题，一流的问题，发表顶级论文。
研究组主要和国家能源、国家电投、国家电网、航天科技、航天科工、航空工业、中国船舶、中国兵器、中国电科、中国移动、华为等等知名央国企、民营企业以及相关部委下属研究机构有着长期合作。
教育背景
学历
学位
工作经历
工作简历
社会兼职
2018-07-30-2025-12-30,中国图象图形学会青年工作委员会委员, 委员
2017-08-31-2026-12-31,中国自动化学会混合智能专业委员会委员, 委员
2017-04-30-2024-12-31,中关村管委会专家委员会委员, 委员
2015-09-30-2027-12-31,中国计算机学会计算机视觉专业委员会委员, 委员
专利与奖励
奖励信息
出版信息
发表论文
（1） BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning, AAAI, 2024, 通讯作者
（2） Position: Foundation Agents as the Paradigm Shift for Decision Making, ICML, 2024, 通讯作者
（3） TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient, AAAI, 2024, 通讯作者
（4） Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models, AAMAS, 2024, 通讯作者
（5） ProAgent: Building Proactive Cooperative AI with Large Language Models, AAAI, 2024, 通讯作者
（6） Exemplar-based Continual Learning via Contrastive Learning, IEEE Transactions on Artificial Intelligence (TAI), 2024, 通讯作者
（7） PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning, AAMAS, 2024, 通讯作者
（8） TASK-WISE PROMPT QUERY FUNCTION FOR REHEARSAL-FREE CONTINUAL LEARNING, ICASSP, 2024, 通讯作者
（9） ADMN: Agent-Driven Modular Network for Dynamic Parameter Sharing in Cooperative Multi-Agent Reinforcement Learning, IJCAI, 2024, 通讯作者
（10） Population-Based Diverse Exploration for Sparse-Reward Multi-Agent Tasks, IJCAI, 2024, 通讯作者
（11） Learning Individual Difference Rewards in Multi-Agent Reinforcement Learning, AAMAS, 2023, 通讯作者
（12） Contrastive Correlation Preserving Replay for Online Continual Learning, IEEE CSVT, 2023, 通讯作者
（13） Dynamic Equilibrium-Based Continual Learning Model with Disentangled Meta-features, IEEE SMC, 2023, 通讯作者
（14） Leveraging Joint-action Embedding in Multi-agent Reinforcement Learning for Cooperative Games, TOG, 2023, 通讯作者
（15） Squeezing More Past Knowledge for Online Class-Incremental Continual Learning, Squeezing More Past Knowledge for Online Class-Incremental Continual Learning, IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2023, 通讯作者
（16） Subspace-Aware Exploration for Sparse-Reward Multi-Agent Tasks, AAAI, 2023, 通讯作者
（17） 兵棋推演的智能决策技术与挑战, 自动化学报, 2023
（18） Prioritized Tasks Mining for Multi-Task Cooperative Multi-Agent Reinforcement Learning, AAMAS, 2023, 通讯作者
（19） 基于模型的强化学习中可学习的样本加权机制, Learnable Weighting Mechanism in Model-based Reinforcement Learning, 软件学报, 2023
（20） PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination, AAMAS, 2023, 通讯作者
（21） Exploration via Joint Policy Diversity for Sparse-Reward Multi-Agent Tasks, IJCAI, 2023, 通讯作者
（22） DecisionHoldem: Safe Depth-Limited Solving With Diverse Opponents for Imperfect-Information Games, 2022
（23） RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning, IJCNN, 2022
（24） Deep Reinforcement Learning With Part-Aware Exploration Bonus in Video Games, IEEE TRANSACTIONS ON GAMES, 2022, 通讯作者
（25） Offline reinforcement learning with representations for actions, INFORMATION SCIENCES, 2022, 通讯作者
（26） Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning, 2022
（27） Learning Macromanagement in Starcraft by Deep Reinforcement Learning, SENSORS, 2021
（28） Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning, AAAI, 2021
（29） Universal adversarial perturbations against object detection, PATTERN RECOGNITION, 2021
（30） 基于深度学习的跨模态检索综述, Survey on deep learning based cross-modal retrieval, 中国图象图形学报, 2021
（31） Composing Good Shots by Exploiting Mutual Relations, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, 通讯作者
（32） Human-Machine Gaming Intelligence: A Review, Science China, 2020,
（33） Opponent Strategy Recognition In Real Time Strategy Game Using Deep Feature Fusion Neural Network, 2020 5TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS (ICCCS 2020), 2020
（34） 人机对抗智能技术, Intelligent technologies of human-computer gaming, 中国科学:信息科学, 2020,
（35） Learning to Learn Cropping Models for Different Aspect Ratio Requirements, IEEE Conference on Computer Vision and Pattern Recognition, 2020, 通讯作者
（36） Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping., IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY, 2019
（37） SparseMask: Differentiable Connectivity Learning for Dense Image Prediction, 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019
（38） Mixed supervised object detection with robust objectness transfer, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019
（39） GP-GAN: Towards Realistic High-Resolution Image Blending, PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019
（40） MVP-Net: Multi-view FPN with Position-Aware Attention for Deep Universal Lesion Detection, MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT VI, 2019
（41） Few-Shot Image Recognition with Knowledge Transfer, 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019
（42） Multi-view clustering via joint feature selection and partially constrained cluster label learning, PATTERN RECOGNITION, 2019, 通讯作者
（43） Transductive Zero-Shot Learning via Visual Center Adaptation, THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, 通讯作者
（44） Transductive Zero-Shot Learning with Visual Structure Constraint, ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019
（45） Bootstrap Estimated Uncertainty of the Environment Model for Model-Based Reinforcement Learning, THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019
（46） Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019
（47） Fast End-to-End Trainable Guided Filter, 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018
（48） ACM: Learning Dynamic Multi-agent Cooperation via Attentional Communication Model, ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT II, 2018
（49） Deep Semantic Structural Constraints for Zero-Shot Learning, 2018
（50） Df^2net: Discriminative feature learning and fusion network for RGB-D indoor scene classification, AAAI, 2018, 第 1 作者
（51） A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping, 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018
（52） DF2Net: A Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification., 2018
（53） DF(2)Net: A Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification, THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018
（54） Deep Semantic Structural Constraints for Zero-Shot Learning, THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018
（55） Discriminative learning of latent features for zero-shot recognition, 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018
（56） SEMANTICS-GUIDED MULTI-LEVEL RGB-D FEATURE FUSION FOR INDOOR SEMANTIC SEGMENTATION, 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017
（57） Semantics-guided Multi-level RGB-D Feature Fusion for Indoor Semantic Segmentation, 2017
（58） GRMA: Generalized Range Move Algorithms for the Efficient Optimization of MRFs, INTERNATIONAL JOURNAL OF COMPUTER VISION, 2017
（59） Local structured representation for generic object detection, FRONTIERS OF COMPUTER SCIENCE, 2017, 第 1 作者 通讯作者
（60） Encyclopedia Enhanced Semantic Embedding for Zero-Shot Learning, 2017
（61） ORGM: Occlusion Relational Graphical Model for Human Pose Estimation, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017
（62） FastLCD: Fast Label Coordinate Descent for the Efficient Optimization of 2D Label MRFs, INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016
（63） 利用双通道卷积神经网络的图像超分辨率算法, 中国图象图形学报, 2016
（64） ISEE Smart Home (ISH): Smart video analysis for home security, NEUROCOMPUTING, 2015, 第 1 作者 通讯作者
（65） Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for Human Pose Estimation, 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015
（66） Mirrored Non-Maximum Suppression for Accurate Object Part Localization, PROCEEDING OF 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION, 2015, 第 1 作者
（67） Large-Scale Weakly Supervised Object Localization via Latent Category Learning, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015
（68） Learning Convolutional NonLinear Features for K Nearest Neighbor Image Classification, PROC. INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION 2014, 2014, 第 1 作者
（69） Robust Object Recognition via Visual Pathway Feedback, ICPR, 2014, 第 1 作者
（70） Improved Optimization Based on Graph Cuts for Discrete Energy Minimization, INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, 2014
（71） Learning Convolutional NonLinear Features for K Nearest Neighbor Image Classification, 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014
（72） Deformable Object Matching via Deformation Decomposition based 2D Label MRF, IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, 2014, 第 1 作者
（73） Deformable Object Matching via Deformation Decomposition based 2D Label MRF, 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014
（74） Recent Progress on Object Classification and Detection, PROC. IBEROAMERICAN CONGRESS ON PATTERN RECOGNITION, 2013, 第 1 作者
（75） An adaptive combination of multiple features for robust tracking in real scene, IEEEINTERNATIONALCONFERENCEONCOMPUTERVISIONICCV, 2013
（76） Exploring the Power of Kernel in Feature Representation for Object Categorization, INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING, 2013, 第 1 作者
（77） An Adaptive Combination of Multiple Features for Robust Tracking in Real Scene, 2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2013
（78） Data Decomposition and Spatial Mixture Modeling for Part based Model, SPRINGER BERLIN HEIDELBERG,2012, 2012
（79） Semantic Windows Mining in Sliding Window Based Object Detection, INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2012
（80） Boosted Local Structured HOG-LBP for Object Localization, IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011
（81） Boosted Local Structured HOG-LBP for Object Localization, 2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, 第 1 作者 通讯作者
（82） An Empirical Study of Visual Features for Part Based Model, PATTERN RECOGNITION,2011, 2011