Homepage

About Me

I am a Ph.D. student in Data Science and Information Technology at Tsinghua University, advised by Professor Mingyao Qi and Assistant Professor Chen Gao. My research focuses on embodied spatial intelligence: building an embodied brain that understands its environment, predicts future states, and acts to complete tasks.

Before my Ph.D., I received my M.Eng. and B.Eng. from South China University of Technology. During my master's studies, I was advised by Professor Wenhu Tang and worked on machine learning and optimization for energy systems. Beyond my primary research, I am also interested in quantitative investing.

Spatial IntelligenceVision-Language NavigationVision-Language ModelsWorld ModelsPost-Training

Research Highlights

Selected Industry Collaboration Projects

Education

Tsinghua University 清华大学 (Ph.D. Student)

Major: Data Science and Information Technology

Research: Foundation models and post-training for embodied spatial intelligence.

Honors: Tsinghua University Second-Class Scholarship; school-level Second-Class Scholarship.

South China University of Technology 华南理工大学 (M.Eng.)

Major: Electrical Engineering; Rank: 1 / 68 (Top 2%)

Research: Machine learning, operations research, and their applications to power systems.

Honors: Outstanding Graduate of the School.

South China University of Technology 华南理工大学 (B.Eng.)

Major: Electrical Engineering and Automation; Rank: 11 / 310 (Top 5%)

Honors: National Scholarship (Top 2%); Meritorious Winner, Mathematical Contest in Modeling (team leader); Provincial First Prize, National College Student Mathematics Competition; University First Prize, Mathematics Competition.

Academic Service

Reviewer: NeurIPS, ICML, ACL Rolling Review (ARR), and AAAI, among others.

All Publications

  1. B. Zhao, J. Xu, W. Feng, X. Zhang, Z. Wang, H. Wang, S. Ji, Z. Wang, J. Fang, Z. Zheng, W. Zhang, Y. Shang, W. Wu, C. Gao, X. Chen, Y. Li (2026). WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation. Advances in Neural Information Processing Systems (NeurIPS). (Accepted) (CCF-A)
  2. B. Zhao, R. Tang, M. Jia, Z. Wang, F. Man, X. Zhang, Y. Shang, W. Zhang, W. Wu, C. Gao, X. Chen, Y. Li (2025). AirScape: An Aerial Generative World Model with Motion Controllability. Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 12519–12528. (CCF-A)
  3. B. Zhao, Z. Wang, J. Fang, C. Gao, F. Man, J. Cui, X. Wang, X. Chen, Y. Li, W. Zhu (2025). Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning. Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 11071–11080. (CCF-A)
  4. B. Zhao, Z. Wang, J. Fang, Z. Zhou, Y. Xu, Y. Ji, J. Xu, Q. Zhang, W. Zhang, C. Gao, X. Chen (2026). How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace. Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 10326–10337. (Oral (Top 5%)) (CCF-A)
  5. B. Zhao, J. Fang, Z. Dai, Z. Wang, J. Zha, W. Zhang, C. Gao, Y. Wang, J. Cui, X. Chen, Y. Li (2025). UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 32400–32423. (Oral (Top 2%)) (CCF-A)
  6. B. Zhao, X. Wang, T. Zhang, R. Shi, F. Xu, F. Man, E. Chen, Y. Li, Y. Li, T. Sun, X. Chen (2024). Estimating and Modeling Spontaneous Mobility Changes during the COVID-19 Pandemic without Stay-at-Home Orders. Humanities and Social Sciences Communications, 11, Article 591. (JCR Q1)
  7. B. Zhao, T. Qian, W. Li, Y. Xin, W. Zhao, Z. Lin, W. Tang, X. Jin, W. Cao, T. Pan (2024). Fast Distributed Co-Optimization of Electricity and Natural Gas Systems Hedging against Wind Fluctuation and Uncertainty. Energy, 298, Article 131420. (JCR Q1)
  8. B. Zhao, T. Qian, W. Tang, Q. Liang (2022). A Data-Enhanced Distributionally Robust Optimization Method for Economic Dispatch of Integrated Electricity and Natural Gas Systems with Wind Uncertainty. Energy, 243, Article 123113. (JCR Q1)
  9. B. Zhao, Z. Niu, Q. Liang, Y. Xin, T. Qian, W. Tang, Q. Wu (2021). Signal-to-Signal Translation for Fault Diagnosis of Bearings and Gears with Few Fault Samples. IEEE Transactions on Instrumentation and Measurement, 70, pp. 1–10. (JCR Q1)
  10. B. Zhao, H. Lan, Z. Niu, H. Zhu, T. Qian, W. Tang (2021). Detection and Location of Safety Protective Wear in Power Substation Operation Using Wear-Enhanced YOLOv3 Algorithm. IEEE Access, 9, pp. 125540–125549. (JCR Q2)
  11. C. Gao, B. Zhao, W. Zhang, J. Mao, J. Zhang, Z. Zheng, F. Man, J. Fang, Z. Zhou, J. Cui, X. Chen, Y. Li (2024). EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-World City Environment. arXiv, arXiv:2410.09604.
  12. Y. Meng, B. Zhao, J. Wu, T. Wang, R. Tang, H. Zhang, W. Sun, C. Gao, Z. Chen, X. Chen, Y. Li, X. P. Zhang, C. Guo (2026). CoDrive: Cross-Vehicle World-Consistent Video Generation with Precise Trajectory Control for Cooperative Driving. arXiv, arXiv:2609.34749.
  13. Y. Xin, B. Zhao, Q. Liang, J. Zhou, T. Qian, Z. Yu, W. Tang (2022). Development of Improved Suppression Measures against Reignition Overvoltages Caused by Vacuum Circuit Breakers in Offshore Wind Farms. IEEE Transactions on Power Delivery, 37(1), pp. 517–527. (JCR Q2)
  14. Y. Xin, Y. H. Yang, B. Zhao, L. Xu, Z. Y. Yu, W. Tang (2022). Configuration of Suppression Schemes against High-Frequency Transient Reignition Overvoltages Caused by Shunt Reactor Switching-Off in Offshore Wind Farms. International Journal of Electrical Power & Energy Systems, 141, Article 108170. (JCR Q1)
  15. W. Tang, Z. Niu, B. Zhao, T. Ji, M. Li, Q. Wu (2020). Research and Application of Data-Driven Artificial Intelligence Technology for Condition Analysis of Power Equipment. High Voltage Engineering, 46(9), pp. 2985–2999. (In Chinese) (EI)
  16. W. Tang, Q. Liang, B. Zhao, Y. Xin, Y. Gu (2023). Short-Circuit Fault Classification Method for AC Submarine Cables in Offshore Wind Farms Based on Improved Sparse Representation. Proceedings of the CSEE, 43(6), pp. 2212–2222. (In Chinese) (EI)
  17. F. Man, X. Chen, H. Wang, B. Zhao, H. Li, X. Chen, Y. Li (2025). VAEER: Visual Attention-Inspired Emotion Elicitation Reasoning. arXiv, arXiv:2505.24342.
  18. Z. Niu, M. Z. Reformat, W. Tang, B. Zhao (2020). Electrical Equipment Identification Method with Synthetic Data Using Edge-Oriented Generative Adversarial Network. IEEE Access, 8, pp. 136487–136497. (JCR Q2)
  19. W. Tang, W. Zhao, T. Qian, B. Zhao, Z. Lin, Y. Xin (2022). Learning-Accelerated Asynchronous Decentralized Optimization for Integrated Transmission and Distribution Systems over Lossy Networks. Sustainable Energy, Grids and Networks, 31, Article 100724. (JCR Q1)
  20. G. Liu, J. Cui, X. Liu, B. Zhao, W. Li (2025). LLM-Driven Automatic Construction and Resource Optimization for Large-Scale UAV Simulation. International Conference on Bio-inspired System and Robotics, pp. 312–322.
  21. Z. Li, F. Man, X. Chen, B. Zhao, C. Wu, X. Chen (2022). TRACT: Towards Large-Scale Crowdsensing with High-Efficiency Swarm Path Planning. Adjunct Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp/ISWC), Workshop, pp. 409–414.
  22. W. Zhang, C. Gao, S. Yu, R. Peng, B. Zhao, Q. Zhang, J. Cui, X. Chen, Y. Li (2025). CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 31292–31309. (CCF-A)
  23. F. Man, H. Wang, J. Fang, Z. Deng, B. Zhao, X. Chen, Y. Li (2025). Context-Aware Sentiment Forecasting via LLM-Based Multi-Perspective Role-Playing Agents. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 2687–2703. (CCF-A)
  24. J. Fang, Y. Lei, Q. Wan, Z. Wang, Y. Huang, Y. Xu, B. Zhao, W. Zhang, C. Gao, X. Chen, Y. Li (2026). A Benchmark for Interactive World Models with a Unified Action Generation Framework. International Conference on Machine Learning (ICML). (CCF-A)
  25. W. Zhang, P. Tang, X. Zeng, F. Man, S. Yu, Z. Dai, B. Zhao, H. Chen, Y. Shang, W. Wu, C. Gao, X. Chen, X. Wang, Y. Li, W. Zhu (2026). Aerial World Model for Long-Horizon Visual Generation and Navigation in 3D Space. Proceedings of the ACM International Conference on Multimedia (ACM MM). (CCF-A)
  26. J. Fang, Y. Xu, Z. Wang, C. Gao, Y. Huang, Z. Wang, R. Tang, M. Jia, B. Zhao, W. Zhang, X. Zhang, H. Su, Y. Shang, W. Wu, X. Chen, Y. Li (2026). Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control. Advances in Neural Information Processing Systems (NeurIPS). (Accepted) (CCF-A)

Working Papers

  1. B. Zhao, S. Peng, Y. Wang, Z. Wang, X. Zhang, J. Xu, W. Feng, Z. Wang, J. Fang, W. Zhang, W. Wu, C. Gao, X. Chen, Y. Li. Reason-WAM: Vision-Language Reasoning for World Action Model in Urban Aerial Goal Navigation. Manuscript under review.
  2. Y. Meng, C. Gao, B. Zhao, M. Jia, R. Tang, Z. Wang, J. Fang, Q. Wan, Y. Lei, J. Tang, J. Li, X. Zhang, Y. Shang, W. Wu, X. Chen, X. Zhang, Y. Li. WorldScape: Efficient Real-Time Interactive World Modeling with Versatile Control. Manuscript under review.
  3. J. Fang, Z. Wang, B. Zhao, Z. Zheng, Z. Dai, C. Gao, X. Chen, Y. Li. SAWMAN: Spatial-Aware World Model Agent for Aerial Embodied Navigation. Manuscript under review.
  4. J. Tang, M. Jia, Z. Wang, X. Jin, X. Zhang, J. Fang, B. Zhao, Y. Shang, C. Gao, W. Wu, Y. Li. WorldREPA: Extending Representation Alignment to Multi-Source World Knowledge Learning. Manuscript under review.