Yitong Li

Lytttttt's activity

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

New activity in xlangai/osworld_v2_tasks 2 days ago

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

#54 opened 2 days ago by

Lytttttt

New activity in xlangai/osworld_v2_tasks 7 days ago

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

#49 opened 7 days ago by

Lytttttt

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

#48 opened 7 days ago by

Lytttttt

New activity in xlangai/osworld_v2_tasks 8 days ago

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

#29 opened 8 days ago by

Lytttttt

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

#28 opened 8 days ago by

Lytttttt

New activity in xlangai/osworld_v2_tasks 22 days ago

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

#19 opened 22 days ago by

Lytttttt

New activity in xlangai/osworld_v2_tasks 23 days ago

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

#18 opened 23 days ago by

Lytttttt

New activity in xlangai/osworld_v2_tasks about 2 months ago

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

#9 opened about 2 months ago by

Lytttttt

updated a dataset 3 months ago

xlangai/osworld2.0_human_crosscheck

Updated Jun 17 • 58

New activity in xlangai/osworld2.0_human_crosscheck 3 months ago

Add task_004 eval.log (manual cross-check)

#1 opened 3 months ago by

Lytttttt

updated a dataset 3 months ago

xlangai/osworld_v2_file_cache

Updated May 24 • 16.6k

updated a model 12 months ago

Lytttttt/combined-pretrained-chemformer

Updated Aug 12, 2025

published a model 12 months ago

Lytttttt/combined-pretrained-chemformer

Updated Aug 12, 2025