AI & ML interests
None defined yet.
Recent Activity
We are OS-Copilot Team from Shanghai AI Lab
𤩠Please check out our previous efforts on (multimodal) autonomous agents:
ScienceBoard (Preprint)
š ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific WorkflowsOS-Genesis (ACL'25)
š OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisOS-Atlas (ICLR'25 Spotlight)
š OS-ATLAS: A Foundation Action Model for Generalist GUI AgentsAgentStore (ACL'25)
š AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer AssistantOS-Copilot (LLMAgents@ICLR'24)
š OS-Copilot: Towards Generalist Computer Agents with Self-ImprovementSeeClick (ACL'24)
š SeeClick: Harnessing GUI Grounding for Advanced Visual GUI AgentsSymbol-LLM (ACL'24)
š Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language ModelsENVISIONS (ACL'25)
š Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language ModelsCorex (COLM'24)
š Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
-
OS-Copilot/OS-Genesis-7B-AC
Image-Text-to-Text ⢠8B ⢠Updated ⢠5 ⢠7 -
OS-Copilot/OS-Genesis-8B-AC
Image-Text-to-Text ⢠8B ⢠Updated ⢠3 ⢠4 -
OS-Copilot/OS-Genesis-4B-AC
Image-Text-to-Text ⢠4B ⢠Updated ⢠1 ⢠7 -
OS-Copilot/OS-Genesis-mobile-data
Viewer ⢠Updated ⢠51.1k ⢠82 ⢠3
-
OS-Copilot/OS-Genesis-7B-AC
Image-Text-to-Text ⢠8B ⢠Updated ⢠5 ⢠7 -
OS-Copilot/OS-Genesis-8B-AC
Image-Text-to-Text ⢠8B ⢠Updated ⢠3 ⢠4 -
OS-Copilot/OS-Genesis-4B-AC
Image-Text-to-Text ⢠4B ⢠Updated ⢠1 ⢠7 -
OS-Copilot/OS-Genesis-mobile-data
Viewer ⢠Updated ⢠51.1k ⢠82 ⢠3