Publications

Bijal Bharadva, Manuel Kelly, Yingxue Zhang, Xin Zhang (2026). CURe: Conservative Unlearning with Soft-Gating Regularization for Offline Reinforcement Learning. In proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026).

Manuel Kelly, Yingxue Zhang, Fangzhou Lin, Yanhua Li, Xin Zhang (2026). Unlearning Diffusion Policies via Relative Fisher Forgetting. In proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026).

Yuhang Liu, Xinbo Zhao, Xin Zhang, Lei Le, Zhaohan Xi, Yingxue Zhang (2026). TrajMind: A Unified Large Language Model for Multi-City Trajectory Prediction. In 26th IEEE International Conference on Data Mining (ICDM), 2026.

Xin Zhang, Jonathan Martinez, Yanhua Li, Yingxue Zhang (2026). Decision Transformers As Zero-Shot Learners via Text-Behavior Alignment. In proceedings of the 43rd International Conference on Machine Learning (ICML 2026, Spotlight paper).

Luoxi Tang, Yuqiao Meng, Joseph Costa, Yingxue Zhang, Muchao Ye, Zhaohan Xi (2026). The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization. In proceedings of the 43rd International Conference on Machine Learning (ICML 2026, Spotlight paper).

Yuhang Liu, Yingxue Zhang, Xin Zhang, Yanhua Li, Jun Luo (2025). UniLLM: A Unified Large Language Model for Multi -Modal Urban Dynamics Prediction. In Proceedings of the 32st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’26), August 9–13, 2026, Jeju, Korea..

Yuhang Liu, Yingxue Zhang, Xin Zhang, Yu Yang, Yanhua Li, Jun Luo (2025). MARCEL: Multifaceted Spatial-Temporal Contrastive Learning for Generic Spatial-Temporal Representations. IEEE International Conference on Data Mining (ICDM), 2025. (Full paper acceptance rate = 13.5%).

Yuhang Liu, Yingxue Zhang, Xin Zhang, Yanhua Li, and Jun Luo (2025). UrbanMind: Urban Dynamics Prediction with Multifaceted Spatial-Temporal Large Language Models. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’25), August 3–7, 2025, Toronto, ON, Canada..

Yingxue Zhang, Yanhua Li, Xun Zhou, Zhenming Liu and Jun Luo (2024). C3-GAN+: Complex-Condition-Controlled Generative Adversarial Networks with Enhanced Embedding. ACM Transactions on Knowledge Discovery from Data (TKDD).

Ruohan Li, Yiqun Xie, Xiaowei Jia, Dongdong Wang, Yanhua Li, Yingxue Zhang, Zhihao Wang and Zhili Li (2024). SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting . NeurIPS 2024 (Datasets and Benchmarks Track), Vancouver, Canada (acceptance rate: ~25%).

Yuhang Liu, Yingxue Zhang, Xin Zhang, Yu Yang, Yiqun Xie, Sahar Ghanipoor Machiani, Yanhua Li, and Jun Luo (2024). Align Along Time and Space: A Graph Latent Diffusion Model for Traffic Dynamics Prediction. IEEE International Conference on Data Mining (ICDM), 9-12 December 2024, Abu Dhabi, UAE. (Acceptance rate = 19.5%).

Xinbo Zhao, Yingxue Zhang, Xin Zhang, Yu Yang, Yiqun Xie, Yanhua Li, and Jun Luo (2024). Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing. The 30th SIGKDD conference on Knowledge Discovery and Data Mining, Barcelona, Spain, August 25 to 29, 2024 (acceptance rate: ~20%).

Yingxue Zhang, Yanhua Li, Xun Zhou, Ziming Zhang, and Jun Luo (2022). STM-GAIL: Spatial-Temporal Meta-GAIL for Learning Diverse Human Driving Strategies. SIAM International Conference on Data Mining (SDM23), Minneapolis, April 27 - 39, 2023. (27.5% = 105/382 Acceptance Ratio).

Yingxue Zhang, Yanhua Li, Xun Zhou, and Jun Luo (2022). Mest-GAN: Cross-City Urban Traffic Estimation with Meta Spatial-Temporal Generative Adversarial Networks. IEEE International Conference on Data Mining, (9.77%=85/870 Full paper acceptance ratio), Orlando, FL, Nov. 28 - Dec 1, 2022.

Yingxue Zhang, Yanhua Li, Xun Zhou, Xiangnan Kong, and Jun Luo (2022). STrans-GAN: Spatially-Transferable Generative Adversarial Networks for Urban Traffic Estimation. IEEE International Conference on Data Mining, (9.77%=85/870 Full paper acceptance ratio), Orlando, FL, Nov. 28 - Dec 1, 2022.

Yingxue Zhang, Yanhua Li, Xun Zhou, Zhenming Liu, Jun Luo (2021). C3-GAN: Complex-Condition-Controlled Urban Traffic Estimation though Generative Adversarial Networks. In 2021 IEEE International Conference on Data Mining (ICDM 2021).

Yingxue Zhang, Yanhua Li, Xun Zhou, Jun Luo, Zhi-Li Zhang (2021). Urban Traffic Dynamics Prediction---A Continuous Meta-Learning Approach. In ACM Transactions on Intelligent Systems and Technology (TIST).

Yingxue Zhang, Yanhua Li, Xun Zhou, Jun Luo (2020). cST-ML: Continuous Spatial-Temporal Meta-Learning for Traffic Dynamics Prediction. In 2020 IEEE International Conference on Data Mining (ICDM).

Yingxue Zhang, Yanhua Li, Xun Zhou, Xiangnan Kong, Jun Luo (2020). Off-Deployment Traffic Estimation — A Traffic Generative Adversarial Networks Approach. In IEEE Transactions on Big Data.

Han Bao, Xun Zhou, Yingxue Zhang, Yanhua Li, Yiqun Xie (2020). COVID-GAN: Esti-mating Human Mobility Responses to COVID-19 Pandemic through Spatio-Temporal Conditional GenerativeAdversarial Networks. In Proceedings of the 28th ACM SIGSPATIAL International Conference on Advances inGeographic Information Systems (SIGSPATIAL).

Yingxue Zhang, Yanhua Li, Xun Zhou, Xiangnan Kong, Jun Luo (2020). Curb-GAN: Conditional Urban Traffic Estimation through Spatio-Temporal Generative Adversarial Networks. In Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.

Yingxue Zhang, Yanhua Li, Xun Zhou, Xiangnan Kong, Jun Luo (2019). TrafficGAN: Off-Deployment Traffic Estimation with Traffic Generative Adversarial Networks. In 2019 IEEE International Conference on Data Mining (ICDM).