Research outputs
2026
Empirical Study of Social Bias in Medical Question Answering via Large Language Models
Xiao, X., Zhao, J., Payne, T. R., & Fang, M. (2026). Empirical Study of Social Bias in Medical Question Answering via Large Language Models. In Lecture Notes in Computer Science (pp. 3-16). Springer Nature Switzerland. doi:10.1007/978-3-032-00652-3_1
2025
MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data.
Fang, M., Wan, X., Lu, F., Xing, F., & Zou, K. (2025). MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data.. Scientific data, 12(1), 1392. doi:10.1038/s41597-025-05283-3
A unified multi-subgraph pre-training framework for spatio-temporal graph
Zhong, M., Long, Z., Wang, X., Cheng, T., Fang, M., & Chen, L. (2025). A unified multi-subgraph pre-training framework for spatio-temporal graph. Knowledge-Based Systems, 330, 114428. doi:10.1016/j.knosys.2025.114428
FS-GNN: Improving Fairness in Graph Neural Networks via Joint Sparsification
Zhao, J., Huang, T., Liu, S., Yin, J., Pei, Y., Fang, M., & Pechenizkiy, M. (2025). FS-GNN: Improving Fairness in Graph Neural Networks via Joint Sparsification. Neurocomputing, 648, 130641. doi:10.1016/j.neucom.2025.130641
Self Data Augmentation for Open Domain Question Answering
Zhang, Q., Zheng, M., Chen, S., Liu, H., & Fang, M. (2025). Self Data Augmentation for Open Domain Question Answering. ACM Transactions on Information Systems, 43(2), 1-35. doi:10.1145/3707449
HASARD: A BENCHMARK FOR VISION-BASED SAFE REINFORCEMENT LEARNING IN EMBODIED AGENTS
Tomilin, T., Fang, M., & Pechenizkiy, M. (2025). HASARD: A BENCHMARK FOR VISION-BASED SAFE REINFORCEMENT LEARNING IN EMBODIED AGENTS. In 13th International Conference on Learning Representations Iclr 2025 (pp. 9304-9336).
Integrating Large Language Models with Reinforcement Learning for Generalization in Strategic Card Games: Extended Abstract
Xia, W., Fang, M., Guo, Z., Du, Y., & Xu, B. (2025). Integrating Large Language Models with Reinforcement Learning for Generalization in Strategic Card Games: Extended Abstract. In Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Aamas (pp. 2795-2797).
MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment
Wang, Z., Du, Y., Zhang, Y., Fang, M., & Huang, B. (2025). MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment. Transactions on Machine Learning Research, 2025-June.
MONTE CARLO PLANNING WITH LARGE LANGUAGE MODEL FOR TEXT-BASED GAME AGENTS
Shi, Z., Fang, M., & Chen, L. (2025). MONTE CARLO PLANNING WITH LARGE LANGUAGE MODEL FOR TEXT-BASED GAME AGENTS. In 13th International Conference on Learning Representations Iclr 2025 (pp. 72995-73015).
Model-Based Offline Reinforcement Learning With Adversarial Data Augmentation.
Cao, H., Feng, F., Huo, J., Yang, S., Fang, M., Yang, T., & Gao, Y. (2025). Model-Based Offline Reinforcement Learning With Adversarial Data Augmentation.. IEEE transactions on neural networks and learning systems, PP. doi:10.1109/tnnls.2025.3636176
PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
Schipper, O., Zhang, Y., Du, Y., Pechenizkiy, M., & Fang, M. (2025). PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments. In 2025 IEEE Conference on Games (CoG) (pp. 1-15). IEEE. doi:10.1109/cog64752.2025.11114387
RuAG: LEARNED-RULE-AUGMENTED GENERATION FOR LARGE LANGUAGE MODELS
Zhang, Y., Xiao, P., Wang, L., Zhang, C., Fang, M., Du, Y., . . . Zhang, Q. (2025). RuAG: LEARNED-RULE-AUGMENTED GENERATION FOR LARGE LANGUAGE MODELS. In 13th International Conference on Learning Representations Iclr 2025 (pp. 23316-23339).
TACKLING DATA CORRUPTION IN OFFLINE REINFORCEMENT LEARNING VIA SEQUENCE MODELING
Xu, J., Yang, R., Qiu, S., Luo, F., Fang, M., Wang, B., & Han, L. (2025). TACKLING DATA CORRUPTION IN OFFLINE REINFORCEMENT LEARNING VIA SEQUENCE MODELING. In 13th International Conference on Learning Representations Iclr 2025 (pp. 67875-67903).
TOWARDS EMPOWERMENT GAIN THROUGH CAUSAL STRUCTURE LEARNING IN MODEL-BASED REINFORCEMENT LEARNING
Cao, H., Feng, F., Fang, M., Dong, S., Yang, T., Huo, J., & Gao, Y. (2025). TOWARDS EMPOWERMENT GAIN THROUGH CAUSAL STRUCTURE LEARNING IN MODEL-BASED REINFORCEMENT LEARNING. In 13th International Conference on Learning Representations Iclr 2025 (pp. 88829-88863).
Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models
Zhao, J., Fang, M., Zhang, K., & Pechenizkiy, M. (2025). Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models. In Proceedings of the Annual Meeting of the Association for Computational Linguistics Vol. 1 (pp. 16314-16338).
What If London Bridge Is Closed? Feature-Aware Subgraph Augmentation for Modeling Road Network Structure Changes
Cheng, T., Can Ozkan, M., Fang, M., & Zhang, X. (2025). What If London Bridge Is Closed? Feature-Aware Subgraph Augmentation for Modeling Road Network Structure Changes. IEEE Transactions on Intelligent Transportation Systems, 26(11), 21135-21148. doi:10.1109/tits.2025.3601234
2024
Augmenting biomedical named entity recognition with general-domain resources.
Yin, Y., Kim, H., Xiao, X., Wei, C. H., Kang, J., Lu, Z., . . . Chen, Q. (2024). Augmenting biomedical named entity recognition with general-domain resources.. Journal of biomedical informatics, 159, 104731. doi:10.1016/j.jbi.2024.104731
Human-Guided Moral Decision Making in Text-Based Games
Shi, Z., Fang, M., Chen, L., Du, Y., & Wang, J. (2024). Human-Guided Moral Decision Making in Text-Based Games. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 38 (pp. 21574-21582). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v38i19.30155
Large Language Models Are Neurosymbolic Reasoners
Fang, M., Deng, S., Zhang, Y., Shi, Z., Chen, L., Pechenizkiy, M., & Wang, J. (2024). Large Language Models Are Neurosymbolic Reasoners. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 38 (pp. 17985-17993). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v38i16.29754
Representation-Based Robustness in Goal-Conditioned Reinforcement Learning
Yin, X., Wu, S., Liu, J., Fang, M., Zhao, X., Huang, X., & Ruan, W. (2024). Representation-Based Robustness in Goal-Conditioned Reinforcement Learning. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 38 (pp. 21761-21769). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v38i19.30176
Dynamic Truck–UAV Collaboration and Integrated Route Planning for Resilient Urban Emergency Response
Long, Y., Xu, G., Zhao, J., Xie, B., & Fang, M. (2023). Dynamic Truck–UAV Collaboration and Integrated Route Planning for Resilient Urban Emergency Response. IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT. doi:10.1109/TEM.2023.3299693
GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models
Wang, M., Yang, R., Chen, X., Sun, H., Fang, M., & Montana, G. (2024). GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models. Transactions on Machine Learning Research, 2024.
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
Du, J., Wang, Y., Zhao, W., Deng, Z., Liu, S., Lou, R., . . . Yin, W. (2024). LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (pp. 5081-5099). Association for Computational Linguistics. doi:10.18653/v1/2024.emnlp-main.292
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
Jin, X., Wang, Z., Du, Y., Fang, M., Zhang, H., & Wang, J. (2024). Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf. In Advances in Neural Information Processing Systems Vol. 37.
MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning
Grooten, B., Taylor, M. E., Tomilin, T., Mahmood, A. R., Vasan, G., Fang, M., . . . Mocanu, D. C. (2024). MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning. In Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Aamas Vol. 2024-May (pp. 733-742).
MedINST: Meta Dataset of Biomedical Instructions
Han, W., Fang, M., Zhang, Z., Yin, Y., Song, Z., Chen, L., . . . Chen, Q. (2024). MedINST: Meta Dataset of Biomedical Instructions. In Findings of the Association for Computational Linguistics: EMNLP 2024 (pp. 8221-8240). Association for Computational Linguistics. doi:10.18653/v1/2024.findings-emnlp.482
Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting
Chen, X. H., Wang, Z., Du, Y., Jiang, S., Fang, M., Yu, Y., & Wang, J. (2024). Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting. In Advances in Neural Information Processing Systems Vol. 37.
RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering
Zhang, Z., Fang, M., & Chen, L. (2024). RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering. In Findings of the Association for Computational Linguistics ACL 2024 (pp. 6963-6975). Association for Computational Linguistics. doi:10.18653/v1/2024.findings-acl.415
Revisiting Catastrophic Forgetting in Large Language Model Tuning
Li, H., Ding, L., Fang, M., & Tao, D. (2024). Revisiting Catastrophic Forgetting in Large Language Model Tuning. In Findings of the Association for Computational Linguistics: EMNLP 2024 (pp. 4297-4308). Association for Computational Linguistics. doi:10.18653/v1/2024.findings-emnlp.249
TASK ADAPTATION FROM SKILLS: INFORMATION GEOMETRY, DISENTANGLEMENT, AND NEW OBJECTIVES FOR UNSUPERVISED REINFORCEMENT LEARNING
Yang, Y., Zhou, T., He, Q., Han, L., Pechenizkiy, M., & Fang, M. (2024). TASK ADAPTATION FROM SKILLS: INFORMATION GEOMETRY, DISENTANGLEMENT, AND NEW OBJECTIVES FOR UNSUPERVISED REINFORCEMENT LEARNING. In 12th International Conference on Learning Representations Iclr 2024.
Unsupervised Multiple Choices Question Answering Via Universal Corpus
Zhang, Q., Ge, H., Chen, X., & Fang, M. (2024). Unsupervised Multiple Choices Question Answering Via Universal Corpus. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 11771-11775). IEEE. doi:10.1109/icassp48485.2024.10446538
2023
Discourse-Aware Graph Networks for Textual Logical Reasoning
Huang, Y., Liu, L., Xu, K., Fang, M., Lin, L., & Liang, X. (2023). Discourse-Aware Graph Networks for Textual Logical Reasoning. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 45(10), 11668-11688. doi:10.1109/TPAMI.2023.3280178
Prescribed Safety Performance Imitation Learning From a Single Expert Dataset
Cheng, Z., Shen, L., Zhu, M., Guo, J., Fang, M., Liu, L., . . . Tao, D. (2023). Prescribed Safety Performance Imitation Learning From a Single Expert Dataset. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 45(10), 12236-12249. doi:10.1109/TPAMI.2023.3287908
Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost
Yin, L., Liu, S., Fang, M., Huang, T., Menkovski, V., & Pechenizkiy, M. (2023). Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 37 (pp. 10945-10953). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v37i9.26297
Dual-Modality Co-Learning for Unveiling Deepfake in Spatio-Temporal Space
Guan, J., Zhou, H., Guo, Z., Hu, T., Deng, L., Quan, C., . . . Zhao, Y. (2023). Dual-Modality Co-Learning for Unveiling Deepfake in Spatio-Temporal Space. In PROCEEDINGS OF THE 2023 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2023 (pp. 85-94). doi:10.1145/3591106.3592284
Dynamic Contrastive Distillation for Image-Text Retrieval
Rao, J., Ding, L., Qi, S., Fang, M., Liu, Y., Shen, L., & Tao, D. (2023). Dynamic Contrastive Distillation for Image-Text Retrieval. IEEE Transactions on Multimedia, 1-13. doi:10.1109/tmm.2023.3236837
Shared dynamics learning for large-scale traveling salesman problem
Xu, Y., Fang, M., Chen, L., Du, Y., Xu, G., & Zhang, C. (2023). Shared dynamics learning for large-scale traveling salesman problem. ADVANCED ENGINEERING INFORMATICS, 56. doi:10.1016/j.aei.2023.102005
Joint reasoning with knowledge subgraphs for Multiple Choice Question Answering
Zhang, Q., Chen, S., Fang, M., & Chen, X. (2023). Joint reasoning with knowledge subgraphs for Multiple Choice Question Answering. INFORMATION PROCESSING & MANAGEMENT, 60(3). doi:10.1016/j.ipm.2023.103297
Deep Reinforcement Learning for Real-Time Assembly Planning in Robot-Based Prefabricated Construction
Zhu, A., Dai, T., Xu, G., Pauwels, P., de Vries, B., & Fang, M. (2023). Deep Reinforcement Learning for Real-Time Assembly Planning in Robot-Based Prefabricated Construction. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING. doi:10.1109/TASE.2023.3236805
A Survey for Efficient Open Domain Question Answering
Zhang, Q., Chen, S., Xu, D., Cao, Q., Chen, X., Cohn, T., & Fang, M. (2023). A Survey for Efficient Open Domain Question Answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 14447-14465). Association for Computational Linguistics. doi:10.18653/v1/2023.acl-long.808
Are Large Kernels Better Teachers than Transformers for ConvNets?
Huang, T., Yin, L., Zhang, Z., Shen, L., Fang, M., Pechenizkiy, M., . . . Liu, S. (2023). Are Large Kernels Better Teachers than Transformers for ConvNets?. In Proceedings of Machine Learning Research Vol. 202 (pp. 14023-14038).
CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models
Zhao, J., Fang, M., Shi, Z., Li, Y., Chen, L., & Pechenizkiy, M. (2023). CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 13538-13556). Association for Computational Linguistics. doi:10.18653/v1/2023.acl-long.757
Dynamic Sparsity Is Channel-Level Sparsity Learner
Yin, L., Li, G., Fang, M., Shen, L., Huang, T., Wang, Z., . . . Liu, S. (2023). Dynamic Sparsity Is Channel-Level Sparsity Learner. In Advances in Neural Information Processing Systems Vol. 36.
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances
Zhang, Z., Fang, M., Chen, L., Namazi-Rad, M. -R., & Wang, J. (2023). How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 8289-8311). Association for Computational Linguistics. doi:10.18653/v1/2023.emnlp-main.516
Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
Zhang, Y., Du, Y., Huang, B., Wang, Z., Wang, J., Fang, M., & Pechenizkiy, M. (2023). Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach. In Advances in Neural Information Processing Systems Vol. 36.
NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist
Nimah, I., Fang, M., Menkovski, V., & Pechenizkiy, M. (2023). NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1240-1266). Association for Computational Linguistics. doi:10.18653/v1/2023.acl-long.69
REST: Enhancing Group Robustness in DNNs Through Reweighted Sparse Training
Zhao, J., Yin, L., Liu, S., Fang, M., & Pechenizkiy, M. (2023). REST: Enhancing Group Robustness in DNNs Through Reweighted Sparse Training. In Unknown Conference (pp. 313-329). Springer Nature Switzerland. doi:10.1007/978-3-031-43415-0_19
STAY MORAL AND EXPLORE: LEARN TO BEHAVE MORALLY IN TEXT-BASED GAMES
Shi, Z., Fang, M., Xu, Y., Chen, L., & Du, Y. (2023). STAY MORAL AND EXPLORE: LEARN TO BEHAVE MORALLY IN TEXT-BASED GAMES. In 11th International Conference on Learning Representations Iclr 2023.
Self-imitation Learning for Action Generation in Text-based Games
Shi, Z., Xu, Y., Fang, M., & Chen, L. (2023). Self-imitation Learning for Action Generation in Text-based Games. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (pp. 703-726). Association for Computational Linguistics. doi:10.18653/v1/2023.eacl-main.50
2022
Learning Granularity-Unified Representations for Text-to-Image Person Re-identification
Shao, Z., Zhang, X., Fang, M., Lin, Z., Wang, J., & Ding, C. (2022). Learning Granularity-Unified Representations for Text-to-Image Person Re-identification. In Proceedings of the 30th ACM International Conference on Multimedia (pp. 5566-5574). ACM. doi:10.1145/3503161.3548028
RETHINKING GOAL-CONDITIONED SUPERVISED LEARNING AND ITS CONNECTION TO OFFLINE RL
Yang, R., Lu, Y., Li, W., Sun, H., Fang, M., Du, Y., . . . Zhang, C. (2022). RETHINKING GOAL-CONDITIONED SUPERVISED LEARNING AND ITS CONNECTION TO OFFLINE RL. In Iclr 2022 10th International Conference on Learning Representations.
TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
Cao, Y., Li, D., Fang, M., Zhou, T., Gao, J., Zhan, Y., & Tao, D. (2022). TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. doi:10.18653/v1/2022.emnlp-main.821
You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets
Huang, T., Chen, T., Fang, M., Menkovski, V., Zhao, J., Yin, L., . . . Liu, S. (2022). You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets. In Proceedings of Machine Learning Research Vol. 198.