Yitong Li

Lytttttt's activity

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

liked a dataset 14 days ago

xlangai/osworld_v2_tasks

Viewer • Updated Sep 10 • 1 • 6.3k • 53

liked a dataset 21 days ago

Lytttttt/pptxgym-runs

Updated Aug 14 • 1.22k • 2

updated 4 datasets 3 months ago

xlangai/recommendation

Updated Aug 19 • 111k

Lytttttt/pptxgym-runs

Updated Aug 14 • 1.22k • 2

xlangai/recommendation

Updated Aug 19 • 111k

Lytttttt/pptxgym-runs

Updated Aug 14 • 1.22k • 2

authored a paper 3 months ago

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

Paper • 2606.29537 • Published Jun 28 • 24

published a dataset 3 months ago

Lytttttt/pptxgym-runs

Updated Aug 14 • 1.22k • 2

New activity in xlangai/osworld_v2_tasks 3 months ago

task_075: deliver assets via mirrored zip instead of sparse git clone (fix solution-leak hack)

#56 opened 3 months ago by

Lytttttt

task_090: score only content that actually renders on the slide (fix off-canvas / pasted-image reward hack)

#54 opened 3 months ago by

Lytttttt

New activity in xlangai/osworld_v2_tasks 4 months ago

task_041: include BibTeX block in the instruction; drop un-instructed local-PDF check

#49 opened 4 months ago by

Lytttttt

task_008: make attachment vision descriptions discriminative between ticket receipts and boarding passes

#48 opened 4 months ago by

Lytttttt

task_089: score rendered layout via CDP instead of exact CSS literals; make requirement notes additive

#29 opened 4 months ago by

Lytttttt

task_090: fix nested-group shape flattening; align S14/S20 instruction with scoring

#28 opened 4 months ago by

Lytttttt

task_079: void VLM credit on slides faked with a full-slide picture background (anti-hacking)

#19 opened 4 months ago by

Lytttttt

task_056: serve degraded reference to agent + tighten MLT structure check (anti-hacking)

#18 opened 4 months ago by

Lytttttt

New activity in xlangai/osworld_v2_tasks 5 months ago

Fix evaluators: tasks 077 (L0 false positive) + 079/087/096 (L2 robustness)

#9 opened 5 months ago by

Lytttttt

updated a dataset 6 months ago

xlangai/osworld2.0_human_crosscheck

Updated Jun 17 • 1.17k

New activity in xlangai/osworld2.0_human_crosscheck 6 months ago

Add task_004 eval.log (manual cross-check)

#1 opened 6 months ago by

Lytttttt

updated a dataset 7 months ago

xlangai/osworld_v2_file_cache

Updated May 24 • 480 • 3