Qiushi

QiushiSun's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 7 days ago • 194

upvoted a paper 3 days ago

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published 6 days ago • 56

upvoted a paper 6 days ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 10 days ago • 64

updated a dataset 13 days ago

QiushiSun/osreward-open-release

Updated 13 days ago • 34

published a dataset 13 days ago

QiushiSun/osreward-open-release

Updated 13 days ago • 34

updated a dataset 24 days ago

OS-Copilot/OS-Shepherd-100K

Viewer • Updated 24 days ago • 103k • 464 • 4

upvoted a paper 24 days ago

FrontierChallenge: Evaluating Scientific Workflow Completion

Paper • 2608.24979 • Published 27 days ago • 150

authored 4 papers 30 days ago

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Paper • 2607.28609 • Published Jul 30 • 74

OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis

Paper • 2604.15093 • Published Apr 16 • 30

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published Mar 26 • 132

TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents

Paper • 2602.02196 • Published Feb 2 • 35

updated a collection about 1 month ago

OSReward & OS-Shepherd

Collection

5 items • Updated Aug 19 • 3

upvoted a collection about 1 month ago

OSReward & OS-Shepherd

Collection

5 items • Updated Aug 19 • 3

updated a collection about 1 month ago

OSReward & OS-Shepherd

Collection

5 items • Updated Aug 19 • 3

liked a dataset about 1 month ago

OS-Copilot/OSReward

Viewer • Updated Aug 17 • 1.3k • 1.54k • 8

updated a dataset about 1 month ago

OS-Copilot/OSReward

Viewer • Updated Aug 17 • 1.3k • 1.54k • 8

updated a model about 1 month ago

OS-Copilot/OS-Shepherd-9B

Image-Text-to-Text • 9B • Updated Aug 7 • 93 • 4

upvoted a paper about 1 month ago

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Paper • 2607.28609 • Published Jul 30 • 74

submitted a paper to Daily Papers about 1 month ago

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Paper • 2607.28609 • Published Jul 30 • 74