Our Projects
Explore our current and past projects dedicated to advancing open-source development and AGI research.
Research Philosophy
- 🔍Make user interfaces more intuitive for understanding and interpreting AI decision-making processes
- 🧮Formulate real-world applications into mathematical models to find optimal solutions
- 🔄Bridge the gap between academic research and production applications by raising the bar on code quality
- 📊Conduct detailed ablation studies to examine when and why approaches work better
Publications
- VisualTreeSearch: An Intuitive Interface for Understanding Web Agent Decision Processes[To be submitted]Danqing Zhang, Yuanli Wang, Shiying He, Yaoyao Qian, Jingyi Ni, Junyu Cao(Author list may be modified)
- Web Agent Evaluation Metrics[work in progress]Shiying He, Yaoyao Qian, Danqing Zhang, Yuanli Wang(Paper title and author list may be modified)
- 3D Embodied Embodied Agent benchmark in Roblox Games[work in progress]Danqing Zhang, Zhuo Tao(Paper title and author list may be modified)
- LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications[Paper]Danqing Zhang, Balaji Rama, Jingyi Ni, Shiying He, Fu Zhao, Kunyu Chen, Arnold Chen, Junyu CaoNAACL'25: 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics -- System Demonstration Track
Current Projects
- Enhancing web agents with tree search algorithms for improved decision-making and task completion.
- Exploring advanced reasoning capabilities in artificial intelligence systems.
- Collection of resources on advanced reasoning and cognitive architectures for AGI.
- Developing embodied AI agents for Roblox games.
- Curated list of resources for 3D embodied AI research and development.
Past Projects
- A library for LLM-based multi-agent applications.
- A library for LLM-based web-agent applications.
- A library for VLM-based computer control agent. To be released.
- Collection of Materials on AI Agents.
- Takes a natural language command and directly calls into the OS.