Faculty Profiles - PAN Ling | The Hong Kong University of Science and Technology

Assistant Professor
Department of Electronic and Computer Engineering
Department of Computer Science and Engineering

Research Interest

Reinforcement learning

Machine learning

Artificial intelligence

AI for science

Publications

2025 8

Evolution guided generative flow networks

Transactions on Machine Learning Research, v. 2025-June
Ikram, Zarif; Pan, Ling; Liu, Dianbo
Article

Flow Factorization for Efficient Generative Flow Networks

Proceedings of the AAAI Conference on Artificial Intelligence, v. 39, (25), p. 26833-26840
Liu, Jiashun; Li, Chunhui; Liu, Cheng Hao; Liu, Dianbo; Cai, Qingpeng; Pan, Ling
Article

Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p. 23625-23635, article number 11092704
Yun, Taeyoung; Zhang, Dinghuai; Park, Jinkyoo; Pan, Ling
Article

AgentIR: 2nd Workshop on Agent-based Information Retrieval

SIGIR 2025 - Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, 2025, p. 4180-4183
Jia, Pengyue; Cai, Qingpeng; Zhao, Xiangyu; Pan, Ling; Xin, Xin; Huang, Jin; Zhang, Weinan; Zhao, Li; Yin, Dawei; Yang, Grace Hui
Conference paper

Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets

Paper presented at The Thirteenth International Conference on Learning Representations
HE, Haoran; CHANG, Can; XU, Huazhe; PAN, Ling
Conference paper

NEUROPLASTIC EXPANSION IN DEEP REINFORCEMENT LEARNING

13th International Conference on Learning Representations, ICLR 2025, International Conference on Learning Representations, ICLR, 2025, p. 3114-3136
Liu, Jiashun; Obando-Ceron, Johan; Courville, Aaron; Pan, Ling
Conference paper

Tackling Sparsity in Designated Driver Dispatch with Multi-Agent Reinforcement Learning

Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 / edited by Vorobeychik Yevgeniy; Das Sanmay; Nowe Ann. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025, p. 1060-1069
Jiang, Jiaxuan; Pan, Ling; Zhou, Lin; Huang, Longbo; Fang, Zhixuan
Conference paper

Towards Robust, Efficient, and Practical Decision-Making: From Reward-Maximizing Deep Reinforcement Learning to Reward-Matching GFlowNets

Special Track on AI Alignment / edited by Walsh Toby; Shah Julie; Kolter Zico. Association for the Advancement of Artificial Intelligence, 2025, p. 28724
Pan, Ling
Conference paper

2024 10

Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective

Proceedings of Machine Learning Research, v. 270, p. 473-495
He, Haoran; Wu, Peilin; Bai, Chenjia; Lai, Hang; Wang, Lingxiao; Pan, Ling; Hu, Xiaolin; Zhang, Weinan
Article

Distributional GFlowNets with Quantile Flows

Transactions on Machine Learning Research, v. 2024
Zhang, Dinghuai; Pan, Ling; Chen, Ricky T.Q.; Courville, Aaron; Bengio, Yoshua
Article

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

Advances in Neural Information Processing Systems, v. 37
Li, Xinran; Pan, Ling; Zhang, Jun
Article

Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training

Advances in Neural Information Processing Systems, v. 37
He, Haoran; Bai, Chenjia; Pan, Ling; Zhang, Weinan; Zhao, Bin; Li, Xuelong
Article

Learning to Scale Logits for Temperature-Conditional GFlowNets

Proceedings of Machine Learning Research, v. 235, p. 24248-24270
Kim, Minsu; Ko, Joohwan; Yun, Taeyoung; Zhang, Dinghuai; Pan, Ling; Kim, Woo Chang; Park, Jinkyoo; Bengio, Emmanuel; Bengio, Yoshua
Article

Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning

IEEE/ACM Transactions on Networking, v. 32, (3), p. 2344-2359
Hu, Pihe; Chen, Yu; Pan, Ling; Fang, Zhixuan; Xiao, Fu; Huang, Longbo
Article

QGFN: Controllable Greediness with Action Values

Advances in Neural Information Processing Systems, v. 37
Lau, Elaine; Lu, Stephen Zhewen; Pan, Ling; Precup, Doina; Bengio, Emmanuel
Article

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training

Advances in Neural Information Processing Systems, v. 37
Hu, Pihe; Li, Shaolong; Li, Zhuoran; Pan, Ling; Huang, Longbo
Article

AgentIR: 1st Workshop on Agent-based Information Retrieval

SIGIR 2024 - Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, 2024, p. 3025-3028
Cai, Qingpeng; Zhao, Xiangyu; Pan, Ling; Xin, Xin; Huang, Jin; Zhang, Weinan; Zhao, Li; Yin, Dawei; Yang, Grace Hui
Conference paper

PRE-TRAINING AND FINE-TUNING GENERATIVE FLOW NETWORKS

Paper presented at 12th International Conference on Learning Representations, ICLR 2024, Hybrid, Vienna, Austria
Pan, Ling; Jain, Moksh; Madan, Kanika; Bengio, Yoshua
Conference paper

2023 7

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Proceedings of Machine Learning Research, v. 202, p. 26878-26890
Pan, Ling; Malkin, Nikolay; Zhang, Dinghuai; Bengio, Yoshua
Article

Network Topology Optimization via Deep Reinforcement Learning

IEEE Transactions on Communications, v. 71, (5), p. 2847-2859
Li, Zhuoran; Wang, Xing; Pan, Ling; Zhu, Lin; Wang, Zhendong; Feng, Junlan; Deng, Chao; Huang, Longbo
Article

Stochastic Generative Flow Networks

Proceedings of Machine Learning Research, v. 216, p. 1628-1638
Pan, Ling; Zhang, Dinghuai; Jain, Moksh; Huang, Longbo; Bengio, Yoshua
Article

Generative Augmented Flow Networks

Proceedings of the 11th International Conference on Learning Representations, 2023
Pan, Ling; Zhang, Dinghuai; Courville, Aaron; Huang, Longbo; Bengio, Yoshua
Conference paper

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023 / edited by Oh A.; Neumann T.; Globerson A.; Saenko K.; Hardt M.; Levine S.. Neural information processing systems foundation, 2023,
Zhang, Dinghuai; Dai, Hanjun; Malkin, Nikolay; Courville, Aaron; Bengio, Yoshua; Pan, Ling
Conference paper

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

Paper presented at 37th Conference on Neural Information Processing Systems
Bengio, Yoshua; Courville, Aaron; Dai, Hanjun; Malkin, Nikolay; Pan, Ling; Zhang, Dinghuai
Conference paper

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

Paper presented at Proceedings of the 11th International Conference on Learning Representations
Hu, Pihe; Huang, Jiatai; Huang, Longbo; Pan, Ling; Tan, Yiqin
Conference paper

2022 3

Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification

Proceedings of Machine Learning Research, v. 162, p. 17221-17237
Pan, Ling; Huang, Longbo; Ma, Tengyu; Xu, Huazhe
Article

Effective multi-user delay-constrained scheduling with deep recurrent reinforcement learning

MobiHoc 2022 - Proceedings of the 2022 23rd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, Association for Computing Machinery, 2022, p. 1-10
Hu, Pihe; Pan, Ling; Chen, Yu; Fang, Zhixuan; Huang, Longbo
Conference paper

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022 / edited by Koyejo S.; Mohamed S.; Agarwal A.; Belgrave D.; Cho K.; Oh A.. Neural information processing systems foundation, 2022,
Chang, Can; Mu, Ni; Wu, Jiajun; Pan, Ling; Xu, Huazhe
Conference paper

2021 2

Exploration in policy optimization through multiple paths

Autonomous Agents and Multi-Agent Systems, v. 35, (2), article number 33
Pan, Ling; Cai, Qingpeng; Huang, Longbo
Article

Regularized Softmax Deep Multi-Agent Q-Learning

Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 / edited by Ranzato Marc'Aurelio; Beygelzimer Alina; Dauphin Yann; Liang Percy S.; Wortman Vaughan Jenn. Neural information processing systems foundation, 2021, p. 1365-1377
Pan, Ling; Rashid, Tabish; Peng, Bei; Huang, Longbo; Whiteson, Shimon
Conference paper

2020 4

Softmax deep double deterministic policy gradients

Advances in Neural Information Processing Systems, v. 2020-December
Pan, Ling; Cai, Qingpeng; Huang, Longbo
Article

Deterministic value-policy gradients

AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, AAAI Press, 2020, p. 3316-3323
Cai, Qingpeng; Pan, Ling; Tang, Pingzhong
Conference paper

Multi-path policy optimization

Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 / edited by An Bo; El Fallah Seghrouchni Amal; Sukthankar Gita. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2020, p. 1001-1009
Pan, Ling; Cai, Qingpeng; Huang, Longbo
Conference paper

Reinforcement learning with dynamic boltzmann softmax updates

Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020 / edited by Bessiere Christian. International Joint Conferences on Artificial Intelligence, 2020, p. 1992-1998
Pan, Ling; Cai, Qingpeng; Meng, Qi; Chen, Wei; Huang, Longbo
Conference paper

2019 1

A deep reinforcement learning framework for rebalancing dockless bike sharing systems

33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, AAAI Press, 2019, p. 1393-1400
Pan, Ling; Cai, Qingpeng; Fang, Zhixuan; Tang, Pingzhong; Huang, Longbo
Conference paper

Article 3

Evolution guided generative flow networks

Transactions on Machine Learning Research, v. 2025-June
Ikram, Zarif; Pan, Ling; Liu, Dianbo

Flow Factorization for Efficient Generative Flow Networks

Proceedings of the AAAI Conference on Artificial Intelligence, v. 39, (25), p. 26833-26840
Liu, Jiashun; Li, Chunhui; Liu, Cheng Hao; Liu, Dianbo; Cai, Qingpeng; Pan, Ling

Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p. 23625-23635, article number 11092704
Yun, Taeyoung; Zhang, Dinghuai; Park, Jinkyoo; Pan, Ling

Conference paper 5

AgentIR: 2nd Workshop on Agent-based Information Retrieval

SIGIR 2025 - Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, 2025, p. 4180-4183
Jia, Pengyue; Cai, Qingpeng; Zhao, Xiangyu; Pan, Ling; Xin, Xin; Huang, Jin; Zhang, Weinan; Zhao, Li; Yin, Dawei; Yang, Grace Hui

Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets

Paper presented at The Thirteenth International Conference on Learning Representations
HE, Haoran; CHANG, Can; XU, Huazhe; PAN, Ling

NEUROPLASTIC EXPANSION IN DEEP REINFORCEMENT LEARNING

13th International Conference on Learning Representations, ICLR 2025, International Conference on Learning Representations, ICLR, 2025, p. 3114-3136
Liu, Jiashun; Obando-Ceron, Johan; Courville, Aaron; Pan, Ling

Tackling Sparsity in Designated Driver Dispatch with Multi-Agent Reinforcement Learning

Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 / edited by Vorobeychik Yevgeniy; Das Sanmay; Nowe Ann. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025, p. 1060-1069
Jiang, Jiaxuan; Pan, Ling; Zhou, Lin; Huang, Longbo; Fang, Zhixuan

Towards Robust, Efficient, and Practical Decision-Making: From Reward-Maximizing Deep Reinforcement Learning to Reward-Matching GFlowNets

Special Track on AI Alignment / edited by Walsh Toby; Shah Julie; Kolter Zico. Association for the Advancement of Artificial Intelligence, 2025, p. 28724
Pan, Ling

Article 8

Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective

Proceedings of Machine Learning Research, v. 270, p. 473-495
He, Haoran; Wu, Peilin; Bai, Chenjia; Lai, Hang; Wang, Lingxiao; Pan, Ling; Hu, Xiaolin; Zhang, Weinan

Distributional GFlowNets with Quantile Flows

Transactions on Machine Learning Research, v. 2024
Zhang, Dinghuai; Pan, Ling; Chen, Ricky T.Q.; Courville, Aaron; Bengio, Yoshua

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

Advances in Neural Information Processing Systems, v. 37
Li, Xinran; Pan, Ling; Zhang, Jun

Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training

Advances in Neural Information Processing Systems, v. 37
He, Haoran; Bai, Chenjia; Pan, Ling; Zhang, Weinan; Zhao, Bin; Li, Xuelong

Learning to Scale Logits for Temperature-Conditional GFlowNets

Proceedings of Machine Learning Research, v. 235, p. 24248-24270
Kim, Minsu; Ko, Joohwan; Yun, Taeyoung; Zhang, Dinghuai; Pan, Ling; Kim, Woo Chang; Park, Jinkyoo; Bengio, Emmanuel; Bengio, Yoshua

Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning

IEEE/ACM Transactions on Networking, v. 32, (3), p. 2344-2359
Hu, Pihe; Chen, Yu; Pan, Ling; Fang, Zhixuan; Xiao, Fu; Huang, Longbo

QGFN: Controllable Greediness with Action Values

Advances in Neural Information Processing Systems, v. 37
Lau, Elaine; Lu, Stephen Zhewen; Pan, Ling; Precup, Doina; Bengio, Emmanuel

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training

Advances in Neural Information Processing Systems, v. 37
Hu, Pihe; Li, Shaolong; Li, Zhuoran; Pan, Ling; Huang, Longbo

Conference paper 2

AgentIR: 1st Workshop on Agent-based Information Retrieval

SIGIR 2024 - Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, 2024, p. 3025-3028
Cai, Qingpeng; Zhao, Xiangyu; Pan, Ling; Xin, Xin; Huang, Jin; Zhang, Weinan; Zhao, Li; Yin, Dawei; Yang, Grace Hui

PRE-TRAINING AND FINE-TUNING GENERATIVE FLOW NETWORKS

Paper presented at 12th International Conference on Learning Representations, ICLR 2024, Hybrid, Vienna, Austria
Pan, Ling; Jain, Moksh; Madan, Kanika; Bengio, Yoshua

Article 3

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Proceedings of Machine Learning Research, v. 202, p. 26878-26890
Pan, Ling; Malkin, Nikolay; Zhang, Dinghuai; Bengio, Yoshua

Network Topology Optimization via Deep Reinforcement Learning

IEEE Transactions on Communications, v. 71, (5), p. 2847-2859
Li, Zhuoran; Wang, Xing; Pan, Ling; Zhu, Lin; Wang, Zhendong; Feng, Junlan; Deng, Chao; Huang, Longbo

Stochastic Generative Flow Networks

Proceedings of Machine Learning Research, v. 216, p. 1628-1638
Pan, Ling; Zhang, Dinghuai; Jain, Moksh; Huang, Longbo; Bengio, Yoshua

Conference paper 4

Generative Augmented Flow Networks

Proceedings of the 11th International Conference on Learning Representations, 2023
Pan, Ling; Zhang, Dinghuai; Courville, Aaron; Huang, Longbo; Bengio, Yoshua

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023 / edited by Oh A.; Neumann T.; Globerson A.; Saenko K.; Hardt M.; Levine S.. Neural information processing systems foundation, 2023,
Zhang, Dinghuai; Dai, Hanjun; Malkin, Nikolay; Courville, Aaron; Bengio, Yoshua; Pan, Ling

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

Paper presented at 37th Conference on Neural Information Processing Systems
Bengio, Yoshua; Courville, Aaron; Dai, Hanjun; Malkin, Nikolay; Pan, Ling; Zhang, Dinghuai

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

Paper presented at Proceedings of the 11th International Conference on Learning Representations
Hu, Pihe; Huang, Jiatai; Huang, Longbo; Pan, Ling; Tan, Yiqin

Article 1

Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification

Proceedings of Machine Learning Research, v. 162, p. 17221-17237
Pan, Ling; Huang, Longbo; Ma, Tengyu; Xu, Huazhe

Conference paper 2

Effective multi-user delay-constrained scheduling with deep recurrent reinforcement learning

MobiHoc 2022 - Proceedings of the 2022 23rd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, Association for Computing Machinery, 2022, p. 1-10
Hu, Pihe; Pan, Ling; Chen, Yu; Fang, Zhixuan; Huang, Longbo

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022 / edited by Koyejo S.; Mohamed S.; Agarwal A.; Belgrave D.; Cho K.; Oh A.. Neural information processing systems foundation, 2022,
Chang, Can; Mu, Ni; Wu, Jiajun; Pan, Ling; Xu, Huazhe

Article 1

Exploration in policy optimization through multiple paths

Autonomous Agents and Multi-Agent Systems, v. 35, (2), article number 33
Pan, Ling; Cai, Qingpeng; Huang, Longbo

Conference paper 1

Regularized Softmax Deep Multi-Agent Q-Learning

Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 / edited by Ranzato Marc'Aurelio; Beygelzimer Alina; Dauphin Yann; Liang Percy S.; Wortman Vaughan Jenn. Neural information processing systems foundation, 2021, p. 1365-1377
Pan, Ling; Rashid, Tabish; Peng, Bei; Huang, Longbo; Whiteson, Shimon

Article 1

Softmax deep double deterministic policy gradients

Advances in Neural Information Processing Systems, v. 2020-December
Pan, Ling; Cai, Qingpeng; Huang, Longbo

Conference paper 3

Deterministic value-policy gradients

AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, AAAI Press, 2020, p. 3316-3323
Cai, Qingpeng; Pan, Ling; Tang, Pingzhong

Multi-path policy optimization

Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 / edited by An Bo; El Fallah Seghrouchni Amal; Sukthankar Gita. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2020, p. 1001-1009
Pan, Ling; Cai, Qingpeng; Huang, Longbo

Reinforcement learning with dynamic boltzmann softmax updates

Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020 / edited by Bessiere Christian. International Joint Conferences on Artificial Intelligence, 2020, p. 1992-1998
Pan, Ling; Cai, Qingpeng; Meng, Qi; Chen, Wei; Huang, Longbo

Conference paper 1

A deep reinforcement learning framework for rebalancing dockless bike sharing systems

33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, AAAI Press, 2019, p. 1393-1400
Pan, Ling; Cai, Qingpeng; Fang, Zhixuan; Tang, Pingzhong; Huang, Longbo

2019 1

A deep reinforcement learning framework for rebalancing dockless bike sharing systems

33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, AAAI Press, 2019, p. 1393-1400
Pan, Ling; Cai, Qingpeng; Fang, Zhixuan; Tang, Pingzhong; Huang, Longbo
Conference paper

Teaching Assignment

ELEC1910	Academic and Professional Development I
ELEC2600	Probability and Random Processes in Engineering
ELEC2910	Academic and Professional Development II
ELEC3910	Academic and Professional Development III

ELEC2910	Academic and Professional Development I
ELEC3910	Academic and Professional Development II
ELEC4900	Final Year Design Project
ELEC6910J	Deep Reinforcement Learning

ELEC2600	Probability and Random Processes in Engineering
ELEC2910	Academic and Professional Development I
ELEC3910	Academic and Professional Development II

No Teaching Assignments

Research Interest

Publications

2025 8

2024 10

2023 7

2022 3

2021 2

2020 4

2019 1

Article 3

Conference paper 5

Article 8

Conference paper 2

Article 3

Conference paper 4

Article 1

Conference paper 2

Article 1

Conference paper 1

Article 1

Conference paper 3

Conference paper 1

2019 1

Teaching Assignment

Research Postgraduate (RPG) Supervision

From January 2022 to December 2025 (As of 23 December 2025)

Current RPGs

Projects

From January 2023 to December 2025

Your browser is out of date!