arxiv:2607.28609
Qiushi
QiushiSun
AI & ML interests
Code Intelligence; Large Langauge Models; AI Agents
Recent Activity
updated a dataset 1 day ago
OS-Copilot/OS-Shepherd-100K upvoted a paper 1 day ago
FrontierChallenge: Evaluating Scientific Workflow Completion authored a paper 7 days ago
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models