BAAI-Agents
Beijing Academy of Artificial Intelligence (BAAI) - Multimodal Interaction Research Group
Pinned Repositories
.github
Cradle
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
GPA-LM
This repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".
Steve-Eye
Paper repo for publication: "Steve-Eye: Equiping LLM-based Embodied Agents with Visual Perception in Open Worlds".
BAAI-Agents's Repositories
BAAI-Agents/Cradle
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
BAAI-Agents/GPA-LM
This repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".
BAAI-Agents/Steve-Eye
Paper repo for publication: "Steve-Eye: Equiping LLM-based Embodied Agents with Visual Perception in Open Worlds".
BAAI-Agents/.github