XLang NLP Lab

xlangai's activity

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

adlsdztony 

updated a dataset about 3 hours ago

xlangai/v2-image

Updated Jul 16 • 1.78k

mengqi-20 

in xlangai/osworld_v2_tasks about 9 hours ago

Provision OpenBoard for Task 093

#80 opened about 9 hours ago by

mengqi-20

Fix Task 041 GitLab URL handling

#79 opened about 9 hours ago by

mengqi-20

Fix GitLab URL handling and OpenBoard setup

1

#78 opened about 9 hours ago by

mengqi-20

wuwm1415 

updated a dataset about 12 hours ago

xlangai/recommendation

Updated about 12 hours ago • 28.7k

zhenqiii 

updated a dataset 1 day ago

xlangai/recommendation

Updated about 12 hours ago • 28.7k

cuikq 

in xlangai/recommendation 3 days ago

Fix task_096 golden models and input drawing

#21 opened 3 days ago by

cuikq

aurorajy 

updated a dataset 4 days ago

xlangai/recommendation

Updated about 12 hours ago • 28.7k

Lytttttt 

updated a dataset 5 days ago

xlangai/recommendation

Updated about 12 hours ago • 28.7k

wuwm1415 

authored 2 papers 7 days ago

Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use

Paper • 2607.01084 • Published Jul 1

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Paper • 2606.29537 • Published Jun 28 • 24

cuikq 

in xlangai/recommendation 7 days ago

Add FreeCAD numeric QA images 0931001-0931200

#20 opened 7 days ago by

cuikq

Add task_096 CAD exercise assets

#19 opened 7 days ago by

cuikq

Add FreeCAD sketch2d assets 0940101-0940250

1

#18 opened 7 days ago by

cuikq

FrankeMING 

updated 2 datasets 8 days ago

xlangai/osworld_v2_assets

Viewer • Updated 8 days ago • 345 • 353k • 4

xlangai/recommendation

Updated about 12 hours ago • 28.7k

mengqi-20 

updated a dataset 10 days ago

xlangai/osworld_v2_tasks

Viewer • Updated about 9 hours ago • 1 • 2.94k • 20

DucktapeDulce1206 

updated a dataset 10 days ago

xlangai/recommendation

Updated about 12 hours ago • 28.7k

Lytttttt 

authored a paper 10 days ago

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Paper • 2606.29537 • Published Jun 28 • 24

mengqi-20 

in xlangai/osworld_v2_tasks 10 days ago

Fix task 055 replay evaluator portability

#77 opened 10 days ago by

mengqi-20