- [2023/09/23] An In-depth Survey of Large Language Model-based Artificial Intelligence Agents. Pengyu Zhao et al.
arXiv. [pdf] [code]- This work explored the core differences and characteristics between LLM-based AI agents and traditional AI agents.
- [2023/09/14] The Rise and Potential of Large Language Model Based Agents: A Survey. Xi, Zhiheng, et al.
arXiv. [pdf] [code]- This work presented a general framework for LLM-based agents, comprising three main components: brain, perception, and action, and the framework can be tailored for different applications. Thus they explored the behavior and personality of LLM agents, thereby discussing the insights they provide into human society.
- [2023/03/30] HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face. Shen, Yongliang, et al.
arXiv. [pdf] [code]- This work advocated that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks, with language serving as a generic interface to empower this.
- [2023/11/17] Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation. Hu, Li, et al.
arXiv. [pdf] [code]- This work designed ReferenceNet to merge detail features via spatial attention and introduced an efficient pose guider to direct character's movements and employ an effective temporal modeling approach to ensure smooth inter-frame transitions between video frames.