[September 26, 2026] MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization. Guowei Zou, H. Chen, H. Wang, B. Zhang, N. Yan, H. Wu. [Project Page] [arXiv] [Code]

[July 28, 2026] MA-WAM: Multi-Agent World-Action Model for Test-Time Planning (Under review). Guowei Zou, H. Wang, G. Wang, B. Zhang, Z. Chen, G. Wang, H. Wu. [Project Page] [arXiv] [Code]

[July 28, 2026] G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies (Under review). Guowei Zou, H. Wang, G. Wang, Z. Chen, B. Zhang, G. Wang, H. Wu. [Project Page] [arXiv] [Code]

[June 7, 2026] Co-π-tree: Distilling LLM Reasoning into an Interpretable Policy Tree for Human-AI Collaboration (The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)). B. Zhang, Y. Liang, Guowei Zou, H. Wang, H. Wu. [Project Page] [Paper] [Videos]

[May 2, 2026] CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making. Guowei Zou, H. Wang, B. Zhang, B. Zhang, H. Wu. [Project Page] [Code] [arXiv]

[January 28, 2026] OGPO: One-Step Generative Policy Optimization for Real-Time Robot Control (The 34th ACM International Conference on Multimedia (ACM MM 2026)). Guowei Zou, H. Wang, H. Wu, Y. Qian, Y. Wang, W. Li. [Project Page] [Code] [arXiv]

[October 29, 2025] PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork. B. Zhang, Y. Liang, Guowei Zou, H. Wang, C. Liu, H. Wu. [arXiv]

[October 9, 2025] DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation. Guowei Zou, H. Wang, H. Wu, Y. Qian, Y. Wang, W. Li. [Project Page] [Code] [arXiv]

[August 4, 2025] D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss (AAAI Conference on Artificial Intelligence (AAAI) 2026). Guowei Zou, W. Li, H. Wu, Y. Qian, Y. Wang, H. Wang. [Project Page] [Code] [arXiv]