OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Paper • 2404.07972 • Published • 52
Danyang Zhang
zdy023
AI & ML interests
Agent, LLM, RL, GUI Interaction
Recent Activity
upvoted a paper 1 day ago
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents updated a dataset 7 months ago
X-LANCE/WikiHow-taskset upvoted a collection 8 months ago
OpenCUA: Open Foundations for Computer-Use AgentsOrganizations
authored a
paper almost 2 years ago
authored a
paper over 2 years ago