OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Apr 11, 2024·
Tianbao Xie
,
Danyang Zhang
,
Jixuan Chen
,
Xiaochuan Li
,
Siheng Zhao
Ruisheng Cao
Ruisheng Cao
,
Toh Jing Hua
,
Zhoujun Cheng
,
Dongchan Shin
,
Fangyu Lei
,
Yitao Liu
,
Yiheng Xu
,
Shuyan Zhou
,
Silvio Savarese
,
Caiming Xiong
,
Victor Zhong
,
Tao Yu
· 0 min read
Type
Publication
Advances in Neural Information Processing Systems (NeurIPS), 2024
Multimodal Agents Large Language Model Interface Interaction and Understanding
Ruisheng Cao
Authors
Ruisheng Cao
4th-year CS PhD candidate
Research interests include structured natural language understanding, model-based data generation and iterative training, and LLM-based multi-modal agents.